Release 3.49.16 (#1006)

* Release 3.49.16

Version bump across configure.ac, htsglobal.h, version.rc and the AppStream
metainfo, plus the release notes for history.txt and debian/changelog.

VERSION_INFO 3:7:0 -> 3:8:0: no installed struct or exported signature moved
this cycle, so the soname stays .so.3 and Debian needs no package rename.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

* Correct the 3.49.16 release notes

The AppStream metainfo describes WebHTTrack and is read by Linux software
centres, so it now lists only WebHTTrack-visible changes: the macOS bullet and
the nine option-dialog strings (WinHTTrack-only, no hits outside lang/) are out,
the charset re-encoding is in. Drop the task-switcher claim, which webhttrack
cannot make: it is a script that launches a browser.

Fix two over-claims in history.txt. Only the trailer section after the
terminating chunk was rejected, not any chunked page. The cache aborted the
mirror on an over-long URL rather than merely refusing one it had accepted.

Cite #901 rather than the PR that closed it.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

---------

Signed-off-by: Xavier Roche <roche@httrack.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

.gitattributes

@@ -6,3 +6,6 @@
 # bash die on $'\r' on every line of them.
 *.test text eol=lf
 *.sh text eol=lf
+
+# Scoped to this file so a union can never touch build logic.
+tests/tests-list.mk merge=union

.github/dependabot.yml

@@ -12,3 +12,9 @@ updates:
     directory: /
     schedule:
       interval: weekly
+
+  # src/coucal is a hard build dependency, and nothing else notices when it moves.
+  - package-ecosystem: gitsubmodule
+    directory: /
+    schedule:
+      interval: weekly

.github/workflows/appstream-network.yml

@@ -0,0 +1,34 @@
+# The per-PR lint runs --no-net so an httrack.com outage can't red an unrelated
+# PR; that also blinds it to a broken screenshot URL, which this job catches.
+name: appstream metainfo (networked)
+
+on:
+  schedule:
+    - cron: "12 6 * * 1"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  validate:
+    name: appstreamcli validate (network)
+    # Scheduled workflows run per-fork independently; skip anywhere but upstream.
+    if: github.repository == 'xroche/httrack'
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Install appstreamcli
+        run: |
+          set -euo pipefail
+          sudo apt-get update
+          sudo apt-get install -y --no-install-recommends appstream
+          appstreamcli --version
+
+      # appstreamcli exits 3 on a warning, so a dead screenshot fails the job.
+      - name: AppStream metainfo validation (network)
+        run: |
+          set -euo pipefail
+          appstreamcli validate --explain \
+            html/server/div/com.httrack.WebHTTrack.metainfo.xml

.github/workflows/ci.yml

@@ -79,7 +79,10 @@ jobs:
       - name: Build
         run: make -j"$(nproc)"
 
+      # A backstop only: tests/test-timeout.sh bounds each test, and a healthy run
+      # is a minute here, two on macOS. Without it a stall ran to the job's 6h default.
       - name: Test
+        timeout-minutes: 20
         run: |
           jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
           make check -j"$jobs"
@@ -119,6 +122,7 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test without python3
+        timeout-minutes: 20
         run: |
           set -euo pipefail
           # Hide every python3* so `command -v python3` fails like it does in the
@@ -139,7 +143,7 @@ jobs:
   # so point configure at it; everything else is in the SDK or default paths.
   macos:
     name: build (macOS arm64, clang)
-    runs-on: macos-14
+    runs-on: macos-15
     steps:
       - uses: actions/checkout@v7
         with:
@@ -173,6 +177,7 @@ jobs:
           sudo ifconfig lo0 alias 127.0.0.3 up
 
       - name: Test
+        timeout-minutes: 20
         run: |
           jobs=$(( $(sysctl -n hw.ncpu) * 2 )); [ "$jobs" -le 16 ] || jobs=16
           make check -j"$jobs"
@@ -186,7 +191,7 @@ jobs:
   # temp prefix, then check webhttrack brings up htsserver and serves the UI.
   webhttrack-macos:
     name: webhttrack smoke (macOS arm64)
-    runs-on: macos-14
+    runs-on: macos-15
     steps:
       - uses: actions/checkout@v7
         with:
@@ -212,6 +217,112 @@ jobs:
       - name: Smoke-test webhttrack
         run: bash tests/webhttrack-smoke.sh "$RUNNER_TEMP/inst"
 
+  # Same smoke on the platform that ships webhttrack as a package: the install layout
+  # it asserts (a relative data symlink, #885) is what Debian consumes, and the macOS
+  # job alone left that untested on Linux.
+  webhttrack-linux:
+    name: webhttrack smoke (Linux x86-64)
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v7
+        with:
+          submodules: recursive
+
+      - name: Install build dependencies
+        run: |
+          set -euo pipefail
+          sudo apt-get update
+          sudo apt-get install -y --no-install-recommends \
+            build-essential autoconf automake libtool autoconf-archive \
+            zlib1g-dev libssl-dev libbrotli-dev libzstd-dev
+
+      - name: Build and install into a temp prefix
+        run: |
+          set -euo pipefail
+          ./bootstrap
+          ./configure --prefix="$RUNNER_TEMP/inst"
+          make -j"$(nproc)"
+          make install
+
+      - name: Smoke-test webhttrack
+        run: bash tests/webhttrack-smoke.sh "$RUNNER_TEMP/inst"
+
+  # The macOS app bundle (#886): assemble it, then prove it still works after being
+  # moved, which is the only thing a .app has to survive that a prefix install does not.
+  macos-app:
+    name: macOS app bundle (arm64)
+    runs-on: macos-15
+    steps:
+      - uses: actions/checkout@v7
+        with:
+          submodules: recursive
+
+      - name: Install build dependencies
+        run: |
+          set -euo pipefail
+          brew install autoconf automake libtool autoconf-archive brotli zstd
+
+      # --disable-shared keeps libhttrack inside the binaries, so the bundle carries no
+      # absolute dylib path back to the staging prefix.
+      - name: Build and install into a temp prefix
+        run: |
+          set -euo pipefail
+          ssl="$(brew --prefix openssl@3)"
+          brewp="$(brew --prefix)"
+          ./bootstrap
+          ./configure CPPFLAGS="-I${ssl}/include -I${brewp}/include" \
+            LDFLAGS="-L${ssl}/lib -L${brewp}/lib" \
+            --prefix="$RUNNER_TEMP/inst" --disable-shared
+          make -j"$(sysctl -n hw.ncpu)"
+          make install
+
+      - name: Assemble HTTrack.app
+        run: |
+          set -euo pipefail
+          make macos-app APP_FLAGS="--prefix $RUNNER_TEMP/inst --out $RUNNER_TEMP"
+          plutil -lint "$RUNNER_TEMP/HTTrack.app/Contents/Info.plist"
+
+      - name: Run it through the bundle stub
+        run: |
+          set -euo pipefail
+          app="$RUNNER_TEMP/HTTrack.app"
+          bash tests/webhttrack-smoke.sh "$app/Contents/Resources" "$app/Contents/MacOS/HTTrack"
+
+      - name: Run it again after moving it
+        run: |
+          set -euo pipefail
+          mkdir -p "$RUNNER_TEMP/moved"
+          mv "$RUNNER_TEMP/HTTrack.app" "$RUNNER_TEMP/moved/"
+          rm -rf "$RUNNER_TEMP/inst"
+          app="$RUNNER_TEMP/moved/HTTrack.app"
+          bash tests/webhttrack-smoke.sh "$app/Contents/Resources" "$app/Contents/MacOS/HTTrack"
+
+      # The load-command check cannot fail while the loader can still reach Homebrew (#901).
+      - name: Run it with Homebrew's libraries out of reach
+        run: |
+          set -euo pipefail
+          app="$RUNNER_TEMP/moved/HTTrack.app"
+          # Without this the hiding below proves nothing: an empty Frameworks passes it.
+          ls "$app/Contents/Frameworks"/libssl.*.dylib >/dev/null
+          # The kegs, not just the opt symlinks: a source build records the Cellar path.
+          hidden=""
+          for keg in openssl@3 brotli zstd; do
+            for d in "$(brew --prefix)/opt/$keg" "$(brew --prefix)/Cellar/$keg"; do
+              if [ -e "$d" ]; then sudo mv "$d" "$d.hidden"; hidden="$hidden $d"; fi
+            done
+          done
+          trap 'for d in $hidden; do sudo mv "$d.hidden" "$d"; done' EXIT
+          test -n "$hidden"
+          bash tests/webhttrack-smoke.sh "$app/Contents/Resources" "$app/Contents/MacOS/HTTrack"
+
+      # The release path (macos-release.yml) minus Apple, so a bundle that cannot be
+      # signed or packed fails on the PR rather than on release day.
+      - name: Sign and pack the bundle, ad hoc
+        run: |
+          set -euo pipefail
+          bash tools/macos-release.sh --app "$RUNNER_TEMP/moved/HTTrack.app" \
+            --identity - --skip-notarize
+
   # Portability/hardening: 32-bit (i386) build on the x86-64 runner via multilib
   # -- no extra hardware. Exercises the 32-bit size_t/pointer ABI, where size
   # and bounds math can truncate or wrap in ways 64-bit never reveals (the axis
@@ -245,6 +356,7 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test
+        timeout-minutes: 20
         run: |
           jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
           make check -j"$jobs"
@@ -302,6 +414,7 @@ jobs:
         env:
           ASAN_OPTIONS: detect_leaks=0:abort_on_error=1:halt_on_error=1:strict_string_checks=1:malloc_fill_byte=202:max_malloc_fill_size=2147483647:free_fill_byte=203:max_free_fill_size=2147483647
           UBSAN_OPTIONS: print_stacktrace=1:halt_on_error=1
+        timeout-minutes: 20
         run: |
           jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
           make check -j"$jobs"
@@ -345,6 +458,7 @@ jobs:
       - name: Test (offline self-tests under MSan)
         env:
           MSAN_OPTIONS: abort_on_error=1:halt_on_error=1
+        timeout-minutes: 20
         run: |
           set -euo pipefail
           # 01_engine-* only; zlib-dependent self-tests are named 01_zlib-* and
@@ -426,6 +540,7 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test
+        timeout-minutes: 20
         run: |
           jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
           make check -j"$jobs"
@@ -434,6 +549,36 @@ jobs:
         if: failure()
         run: cat tests/test-suite.log 2>/dev/null || true
 
+  # OpenSSL 4.0 removes the API 3.x deprecated. Building with that set hidden
+  # keeps the engine ready for it: a deprecated call fails here rather than the
+  # day a distro moves. Compile-only, since the headers are what is under test.
+  openssl-no-deprecated:
+    name: build (OpenSSL, no deprecated API)
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v7
+        with:
+          submodules: recursive
+
+      - name: Install build dependencies
+        run: |
+          set -euo pipefail
+          sudo apt-get update
+          sudo apt-get install -y --no-install-recommends \
+            build-essential autoconf automake libtool autoconf-archive \
+            zlib1g-dev libssl-dev libbrotli-dev libzstd-dev
+
+      - name: Configure (deprecated OpenSSL API hidden)
+        run: |
+          set -euo pipefail
+          autoreconf -fi
+          ./configure CPPFLAGS=-DOPENSSL_NO_DEPRECATED
+          # A build with https off would pass this job vacuously.
+          grep -q "define HTS_USEOPENSSL 1" config.h
+
+      - name: Build
+        run: make -j"$(nproc)"
+
   # Validate the Debian packaging via the same script maintainers release with.
   # One amd64/gcc run is enough: packaging (control/rules/manifest/lintian/quilt
   # source build) is arch- and compiler-independent, and the build matrix above
@@ -554,9 +699,12 @@ jobs:
         man/makeman.sh
         src/htsbasiccharsets.sh
         src/htsentities.sh
-        src/webhttrack
+        src/webhttrack.in
         tests/*.sh
         tests/*.test
+        tools/macos-app.sh
+        tools/macos-bundle.sh
+        tools/macos-release.sh
         tools/mkdeb.sh
     steps:
       - uses: actions/checkout@v7
@@ -567,8 +715,9 @@ jobs:
           sudo apt-get update
           # noble ships shfmt 3.8.0 (universe), matching the pinned local dev
           # version; use it rather than fetching a release binary from github.com.
-          sudo apt-get install -y --no-install-recommends shellcheck shfmt
+          sudo apt-get install -y --no-install-recommends shellcheck shfmt appstream
           shfmt --version
+          appstreamcli --version
 
       - name: shellcheck
         run: shellcheck $SHELL_SCRIPTS
@@ -586,6 +735,14 @@ jobs:
             echo "ok $f"
           done
 
+      # A software centre quietly ignores a metainfo it cannot parse. Errors and
+      # warnings fail; --no-net so the gate is on the file, not httrack.com's uptime.
+      - name: AppStream metainfo validation
+        run: |
+          set -euo pipefail
+          appstreamcli validate --no-net --explain \
+            html/server/div/com.httrack.WebHTTrack.metainfo.xml
+
   # Check clang-format on CHANGED LINES ONLY. The engine predates clang-format
   # (it was shaped by an old Visual Studio formatter) and does not round-trip,
   # so we never reformat the whole tree -- only the lines a PR touches.
@@ -618,7 +775,12 @@ jobs:
           set -euo pipefail
           git fetch --no-tags origin \
             "+refs/heads/${{ github.base_ref }}:refs/remotes/origin/${{ github.base_ref }}"
-          base="origin/${{ github.base_ref }}"
+          # Merge base, not the branch tip: master moves during a run, and a
+          # tip-relative diff blames its new C on this PR.
+          if ! base="$(git merge-base "origin/${{ github.base_ref }}" HEAD)"; then
+            echo "::error::no merge base with origin/${{ github.base_ref }}; cannot scope the check."
+            exit 1
+          fi
           set +e
           diff="$(git clang-format --binary clang-format-19 --style=file \
                     --diff --extensions c,h "$base")"
@@ -641,6 +803,21 @@ jobs:
               exit 1 ;;
           esac
 
+  docs:
+    name: documentation (chrome in sync, links resolve)
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v7
+
+      # The pages carry their navigation as real markup, because they are read from
+      # disk as often as over http and file:// has no includes. Regenerating has to
+      # be a no-op, or a page has drifted from tools/doc-chrome.py.
+      - name: Shared chrome is in sync
+        run: python3 tools/doc-chrome.py --check
+
+      - name: Relative links and anchors resolve
+        run: python3 tools/doc-links.py html
+
   man-page-sync:
     name: man page / html in sync
     if: github.event_name == 'pull_request'
@@ -660,6 +837,8 @@ jobs:
           git fetch --no-tags origin \
             "+refs/heads/${{ github.base_ref }}:refs/remotes/origin/${{ github.base_ref }}"
           base="origin/${{ github.base_ref }}"
+          # Three dots: merge-base scoped, so commits landing on master mid-run
+          # are not counted as this PR's.
           changed="$(git diff --name-only "$base"...HEAD)"
           has() { printf '%s\n' "$changed" | grep -qx "$1"; }
           if has man/httrack.1 && ! has html/httrack.man.html; then

.github/workflows/codeql.yml

@@ -38,7 +38,7 @@ jobs:
             build-essential autoconf automake libtool autoconf-archive \
             zlib1g-dev libssl-dev
 
-      - uses: github/codeql-action/init@v4
+      - uses: github/codeql-action/init@v4.37.4
         with:
           languages: c-cpp
           build-mode: manual
@@ -67,6 +67,6 @@ jobs:
           ./configure
           make -j"$(nproc)"
 
-      - uses: github/codeql-action/analyze@v4
+      - uses: github/codeql-action/analyze@v4.37.4
         with:
           category: "/language:c-cpp"

.github/workflows/macos-release.yml

@@ -0,0 +1,162 @@
+# Signed, notarized HTTrack.dmg (#901). Its own workflow because a fork's pull request
+# never gets the Developer ID secrets, and each run spends two notarization submissions.
+name: macOS release
+
+on:
+  push:
+    tags: ["[0-9]*"]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  dmg:
+    name: signed DMG (macOS arm64)
+    runs-on: macos-15
+    permissions:
+      contents: write   # attach the DMG to the release the tag belongs to
+    steps:
+      - uses: actions/checkout@v7
+        with:
+          submodules: recursive
+
+      # Notarization is minutes in; a missing secret should not surface there.
+      - name: Check the signing secrets are present
+        env:
+          MACOS_CERT_P12: ${{ secrets.MACOS_CERT_P12 }}
+          MACOS_CERT_PASSWORD: ${{ secrets.MACOS_CERT_PASSWORD }}
+          MACOS_NOTARY_KEY: ${{ secrets.MACOS_NOTARY_KEY }}
+          MACOS_NOTARY_KEY_ID: ${{ secrets.MACOS_NOTARY_KEY_ID }}
+          MACOS_NOTARY_ISSUER_ID: ${{ secrets.MACOS_NOTARY_ISSUER_ID }}
+        run: |
+          set -euo pipefail
+          hint="see secrets/apple/README.md in httrack-works"
+          : "${MACOS_CERT_P12:?unset repository secret ($hint)}"
+          : "${MACOS_CERT_PASSWORD:?unset repository secret ($hint)}"
+          : "${MACOS_NOTARY_KEY:?unset repository secret ($hint)}"
+          : "${MACOS_NOTARY_KEY_ID:?unset repository secret ($hint)}"
+          : "${MACOS_NOTARY_ISSUER_ID:?unset repository secret ($hint)}"
+
+      - name: Install build dependencies
+        run: |
+          set -euo pipefail
+          brew install autoconf automake libtool autoconf-archive brotli zstd
+
+      # --disable-shared keeps libhttrack inside the binaries.
+      - name: Build and install into a temp prefix
+        run: |
+          set -euo pipefail
+          ssl="$(brew --prefix openssl@3)"
+          brewp="$(brew --prefix)"
+          ./bootstrap
+          ./configure CPPFLAGS="-I${ssl}/include -I${brewp}/include" \
+            LDFLAGS="-L${ssl}/lib -L${brewp}/lib" \
+            --prefix="$RUNNER_TEMP/inst" --disable-shared
+          make -j"$(sysctl -n hw.ncpu)"
+          make install
+
+      - name: Assemble HTTrack.app
+        run: |
+          set -euo pipefail
+          make macos-app APP_FLAGS="--prefix $RUNNER_TEMP/inst --out $RUNNER_TEMP"
+          plutil -lint "$RUNNER_TEMP/HTTrack.app/Contents/Info.plist"
+
+      - name: Import the Developer ID certificate
+        env:
+          CERT_P12: ${{ secrets.MACOS_CERT_P12 }}
+          CERT_PASSWORD: ${{ secrets.MACOS_CERT_PASSWORD }}
+        run: |
+          set -euo pipefail
+          kc="$RUNNER_TEMP/signing.keychain-db"
+          kcpass="$(openssl rand -base64 24)"
+          echo "::add-mask::$kcpass"
+          security create-keychain -p "$kcpass" "$kc"
+          # Notarization holds the job well past the five-minute default lock.
+          security set-keychain-settings -lut 21600 "$kc"
+          security unlock-keychain -p "$kcpass" "$kc"
+          # Armed before the file exists: a failed import must not leave the key on a
+          # disk that later steps run repository code against.
+          trap 'rm -f "$RUNNER_TEMP/cert.p12"' EXIT HUP INT TERM
+          # openssl, not base64: macOS spells the decode flag -D and GNU spells it -d.
+          printf '%s' "$CERT_P12" | openssl base64 -d -A -out "$RUNNER_TEMP/cert.p12"
+          security import "$RUNNER_TEMP/cert.p12" -k "$kc" -P "$CERT_PASSWORD" \
+            -T /usr/bin/codesign
+          # Without this codesign blocks on a UI prompt no runner can answer.
+          security set-key-partition-list -S apple-tool:,apple:,codesign: \
+            -s -k "$kcpass" "$kc" >/dev/null
+          security list-keychains -d user -s "$kc"
+          id="$(security find-identity -v -p codesigning "$kc" |
+                awk '/Developer ID Application/ {print $2; exit}')"
+          test -n "$id" || {
+            security find-identity -v -p codesigning "$kc" >&2
+            echo "the .p12 holds no Developer ID Application identity" >&2
+            exit 1
+          }
+          echo "SIGN_IDENTITY=$id" >>"$GITHUB_ENV"
+
+      - name: Sign, notarize and pack the DMG
+        env:
+          NOTARY_KEY: ${{ secrets.MACOS_NOTARY_KEY }}
+          NOTARY_KEY_ID: ${{ secrets.MACOS_NOTARY_KEY_ID }}
+          NOTARY_ISSUER_ID: ${{ secrets.MACOS_NOTARY_ISSUER_ID }}
+        run: |
+          set -euo pipefail
+          key="$RUNNER_TEMP/notary.p8"
+          trap 'rm -f "$key"' EXIT HUP INT TERM
+          printf '%s' "$NOTARY_KEY" | openssl base64 -d -A -out "$key"
+          bash tools/macos-release.sh --app "$RUNNER_TEMP/HTTrack.app" \
+            --identity "$SIGN_IDENTITY" --out "$RUNNER_TEMP" \
+            --notary-key "$key" --notary-key-id "$NOTARY_KEY_ID" \
+            --notary-issuer "$NOTARY_ISSUER_ID"
+
+      # The DMG round-trip is the one thing that can strip the stapled ticket, so assess
+      # the copy that came out of it rather than the app the signing step still holds.
+      - name: Assess a quarantined copy out of the DMG
+        run: |
+          set -euo pipefail
+          dmg="$(echo "$RUNNER_TEMP"/HTTrack-*.dmg)"
+          test -f "$dmg"
+          hdiutil attach -nobrowse -readonly -mountpoint "$RUNNER_TEMP/mnt" "$dmg"
+          trap 'hdiutil detach "$RUNNER_TEMP/mnt" >/dev/null || true' EXIT
+          app="$RUNNER_TEMP/quarantined/HTTrack.app"
+          ditto "$RUNNER_TEMP/mnt/HTTrack.app" "$app"
+          # On the root only, as a real download lands it; -r would also chase symlinks.
+          xattr -w com.apple.quarantine "0083;00000000;Safari;" "$app"
+          # --no-cache, or the verdict already cached for this cdhash answers instead.
+          log="$RUNNER_TEMP/assess.log"
+          spctl --assess --type exec --ignore-cache --no-cache -vv "$app" >"$log" 2>&1 || {
+            cat "$log" >&2
+            exit 1
+          }
+          cat "$log"
+          grep -q "source=Notarized Developer ID" "$log"
+          # spctl alone can be answered online; this is the offline-launch proof.
+          xcrun stapler validate "$app"
+          # Not a Gatekeeper check: the stub is a script, so nothing here goes through
+          # LaunchServices. It proves the hardened runtime did not break the dylib loads.
+          bash tests/webhttrack-smoke.sh "$app/Contents/Resources" "$app/Contents/MacOS/HTTrack"
+
+      - name: Upload the DMG
+        uses: actions/upload-artifact@v7
+        with:
+          name: HTTrack-macos-arm64-dmg
+          path: ${{ runner.temp }}/HTTrack-*.dmg
+          if-no-files-found: error
+
+      # Releases are cut by hand, so a tag can land before one exists.
+      - name: Attach the DMG to the release
+        if: github.ref_type == 'tag'
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          set -euo pipefail
+          if gh release view "$GITHUB_REF_NAME" >/dev/null 2>&1; then
+            gh release upload "$GITHUB_REF_NAME" "$RUNNER_TEMP"/HTTrack-*.dmg --clobber
+          else
+            echo "no release $GITHUB_REF_NAME yet -- the DMG is on this run's artifacts"
+          fi
+
+      - name: Delete the signing keychain
+        if: always()
+        run: security delete-keychain "$RUNNER_TEMP/signing.keychain-db" || true

.github/workflows/screenshots.yml

@@ -0,0 +1,72 @@
+# Documentation screenshots: drive the WebHTTrack UI and capture every screen.
+# Manual, and deliberately not part of the build gate -- run it after adding or
+# changing a UI page, and the artifact is the new set of shots.
+name: screenshots
+
+on:
+  # A push trigger as well as the button: workflow_dispatch is only offered for
+  # workflows that already exist on the default branch.
+  push:
+    paths:
+      - '.github/workflows/screenshots.yml'
+      - 'tools/screenshot-walk.py'
+  workflow_dispatch:
+    inputs:
+      lang:
+        description: 'lang.indexes number to render the UI in (1 = English)'
+        default: '1'
+      scale:
+        description: 'device pixel ratio'
+        default: '2'
+
+permissions:
+  contents: read
+
+jobs:
+  capture:
+    runs-on: ubuntu-24.04
+    timeout-minutes: 20
+    steps:
+      - uses: actions/checkout@v7
+        with:
+          submodules: recursive
+
+      - name: Install build dependencies
+        run: |
+          set -euo pipefail
+          sudo apt-get update
+          sudo apt-get install -y --no-install-recommends \
+            build-essential autoconf automake libtool autoconf-archive \
+            zlib1g-dev libssl-dev libbrotli-dev libzstd-dev
+
+      - name: Build
+        run: |
+          set -euo pipefail
+          autoreconf -fi
+          ./configure
+          make -j"$(nproc)" -C src htsserver
+
+      - name: Install the browser
+        run: |
+          set -euo pipefail
+          pip install --quiet playwright
+          playwright install --with-deps chromium
+
+      - name: Capture
+        env:
+          LANGN: ${{ inputs.lang || '1' }}
+          SCALE: ${{ inputs.scale || '2' }}
+        run: |
+          set -euo pipefail
+          # --root is the dist root; the source tree already holds every piece
+          # htsserver reads, so this needs no install.
+          python3 tools/screenshot-walk.py --htsserver src/htsserver --root . \
+            --lang "$LANGN" --scale "$SCALE" --out shots
+
+      - name: Upload the screens
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: screenshots
+          path: shots
+          if-no-files-found: error

.github/workflows/windows-build.yml

@@ -15,6 +15,11 @@ on:
 permissions:
   contents: read
 
+# Cancel superseded runs on the same branch or PR.
+concurrency:
+  group: windows-build-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   libhttrack:
     runs-on: windows-2022
@@ -167,72 +172,8 @@ jobs:
         working-directory: tests
         timeout-minutes: 45
         run: |
-          set -u
-          bin="$(cygpath -u "$GITHUB_WORKSPACE")/src/${{ matrix.platform }}/${{ matrix.configuration }}"
-          export PATH="$bin:$PATH"
-          command -v httrack >/dev/null || { echo "::error::no httrack.exe in $bin"; exit 1; }
-
-          # httrack.exe is native, so MSYS rewrites any argument shaped like a
-          # POSIX path, and a URL path is shaped exactly like one: "/a/b.html"
-          # reached the engine as "C:/Program Files/Git/a/b.html". Switch that
-          # off, and hand the tests a TMPDIR that is already a Windows path.
-          export MSYS_NO_PATHCONV=1
-          export MSYS2_ARG_CONV_EXCL='*'
-          TMPDIR="$(cygpath -m "$RUNNER_TEMP")"
-          export TMPDIR
-
-          # Mirror what configure hands the suite. LC_ALL sets the codeset MSYS maps
-          # a UTF-8 mirror name onto UTF-16 with, which the intl crawls "test -f".
-          export HTTPS_SUPPORT=yes BROTLI_ENABLED=yes ZSTD_ENABLED=yes
-          export LC_ALL=C.UTF-8
-
-          # A wedged crawl must not eat the job's timeout budget. timeout(1)'s
-          # signals can't reap a native httrack.exe (MSYS signals don't reach it),
-          # so a hang orphaned processes that starved the runner; run_with_timeout
-          # TerminateProcess-es the whole tree. 600s clears the slowest multi-pass
-          # crawl (a few passes at --max-time=120 each).
-          . ./testlib.sh
-
-          pass=0 fail=0 skip=0 failed="" skipped=""
-          for t in 00_runnable.test 01_engine-*.test 01_zlib-*.test \
-                   *_local-*.test 13_crawl_proxy_https.test 58_watchdog.test \
-                   60_crawl-log-salvage.test; do
-            rc=0
-            run_with_timeout 600 bash "$t" >"$t.log" 2>&1 || rc=$?
-            case "$rc" in
-              0) pass=$((pass + 1)); echo "PASS $t" ;;
-              77) skip=$((skip + 1)) skipped="$skipped $t"; echo "SKIP $t" ;;
-              124)
-                fail=$((fail + 1)) failed="$failed $t"
-                echo "FAIL $t (timed out, tree killed)"
-                # Re-running a wedge traced would just hang again: salvage the
-                # killed crawl's own logs into the artifact instead.
-                dump_crawl_logs >>"$t.log"
-                tail -n 25 "$t.log" | sed 's/^/      /'
-                ;;
-              *)
-                fail=$((fail + 1)) failed="$failed $t"
-                echo "FAIL $t (exit $rc)"
-                # These assert with `test "$(...)" == "..." || exit 1`, which
-                # says nothing at all on failure. Re-run traced, still bounded.
-                run_with_timeout 600 bash -x "$t" >>"$t.log" 2>&1 || true
-                tail -n 25 "$t.log" | sed 's/^/      /'
-                ;;
-            esac
-          done
-          echo "ran=$((pass + fail + skip)) pass=$pass fail=$fail skip=$skip" |
-            tee -a "$GITHUB_STEP_SUMMARY"
-
-          # Every gate here exits 77, so an all-skipped suite would report green having
-          # tested nothing: pin the skips, and floor the passes in case the glob empties.
-          # footer-overflow skips on Windows (needs a path past MAX_PATH); crange pending #581;
-          # webdav-mime needs a reapable background listener, which MSYS cannot give it;
-          # badmtime needs a filesystem that stores an mtime past gmtime's range;
-          # single-file ends on a GUI half needing htsserver, which this job does not build.
-          expected_skips=" 01_engine-footer-overflow.test 48_local-crange-memresume.test 71_local-crange-repaircache.test 79_local-proxytrack-webdav-mime.test 88_local-proxytrack-badmtime.test 94_local-single-file.test"
-          [ "$pass" -ge 90 ] || { echo "::error::only $pass tests passed ($skip skipped)"; exit 1; }
-          [ "$skipped" = "$expected_skips" ] || { echo "::error::unexpected skips:$skipped"; exit 1; }
-          [ "$fail" -eq 0 ] || { echo "::error::failing:$failed"; exit 1; }
+          bash ./ci-windows-suite.sh \
+            "$(cygpath -u "$GITHUB_WORKSPACE")/src/${{ matrix.platform }}/${{ matrix.configuration }}"
 
       - name: Upload the test logs
         if: always()

.gitignore

@@ -24,8 +24,11 @@ Makefile.in
 /config.log
 /config.status
 /stamp-h1
+# src/webhttrack.in is the source; an in-tree build generates this one (#887).
+/src/webhttrack
 Makefile
 .deps/
+.dirstamp
 .libs/
 *.o
 *.lo
@@ -34,6 +37,15 @@ Makefile
 *.so.*
 *.a
 
+# Built into the checkout by an in-tree "make" / "make check".
+/src/httrack
+/src/htsserver
+/src/proxytrack
+/tools/Info.plist
+/tests/stringoom
+/tests/*.log
+/tests/*.trs
+
 # make dist output; dist/ holds httrack-gh-release staging artifacts.
 /httrack-*.tar.gz
 /dist/

AGENTS.md

@@ -19,19 +19,25 @@ the operational checklist: toolchain, invariants, and how to ship a change.
   (`request_queue_size`) so macOS/BSD don't drop connections under a parallel
   `-c16` bigcrawl the way Python's default backlog of 5 did.
   Or run `sh build.sh` to do bootstrap + configure + make in one shot.
-- A `tests/NN_*.test` runs only if listed in `tests/Makefile.am`'s `TESTS`; an
+- A `tests/NN_*.test` runs only if listed in `tests/tests-list.mk`; an
   unregistered file is silently skipped.
 - `make check` prepends the build's `src/` to `PATH`, but a hand-run `.test` does
   not — an installed `/usr/bin/httrack` then shadows your build. Run via `make
   check`, or `PATH="<bld>/src:$PATH"` for a manual run.
 - Give new `.test` scripts `set -e`: the older ones predate the rule, so several
   `local-crawl.sh` calls with no `set -e` report PASS on any non-last failure.
-- Never assert with `cmd | grep -q MARKER && fail`. Under `pipefail` the
-  pipeline is non-zero both when `cmd` fails and when `grep -q` matches early
-  and SIGPIPEs it, so the `&&` never fires and a probe that proved nothing reads
-  as "marker absent". Capture the reply, assert the status line it must carry
-  (an empty, truncated or redirected one is marker-free too), then match with a
-  here-string.
+- Run teardown with errexit off: `trap 'set +e; cleanup' EXIT`. Under `set -e` a
+  failing cleanup command becomes the test's exit status (#773). Keep the other
+  signals on their own `trap` line, or errexit stays off for the rest of the run.
+  The guard also resets `$?`, so save it first if teardown reads it.
+- Never pipe into `grep -q`: it exits on the first match, so whatever the
+  producer had left to write takes SIGPIPE, and under `pipefail` that becomes
+  the pipeline's status. `cmd | grep -q M && fail` then never fires and a probe
+  that proved nothing reads as "marker absent"; `cmd | grep -q M || fail` fails
+  a test whose marker was present. bash issues one `write()` per line, so any
+  match that is not on the last line is exposed. Capture the reply, assert the
+  status line it must carry (an empty, truncated or redirected one is
+  marker-free too), then match with a here-string: `grep -q M <<<"$reply"`.
 
 ## Hard invariants
 - **Generated autotools files are NOT in git.** `configure`, every

Makefile.am

@@ -6,13 +6,33 @@ ACLOCAL_AMFLAGS = -I m4
 EXTRA_DIST = INSTALL.Linux \
 		gpl-fr.txt license.txt greetings.txt history.txt \
 		httrack-doc.html lang.def README.md tools/mkdeb.sh \
+		tools/macos-app.sh tools/macos-bundle.sh tools/macos-release.sh \
+		tools/httrack-launcher.c \
+		tools/Info.plist.in tools/HTTrack.icns \
 		bootstrap build.sh
 
 # Build the signed Debian packages from a clean source export. Pass the signing
 # key and other options through DEB_FLAGS, e.g.:
 #   make deb DEB_FLAGS="--key BB71C7E6CB1AD8FAF53FE42A60C3AA7180598EFB"
-# See tools/mkdeb.sh --help for all options.
+# See tools/mkdeb.sh --help for all options. Not $(SHELL): mkdeb.sh is bash, and dash chokes (#891).
 DEB_FLAGS =
 deb:
-	$(SHELL) $(top_srcdir)/tools/mkdeb.sh $(DEB_FLAGS)
+	$(BASH_SHELL) $(top_srcdir)/tools/mkdeb.sh $(DEB_FLAGS)
 .PHONY: deb
+
+# Assemble the macOS application bundle from an installed prefix, e.g.
+#   make macos-app APP_FLAGS="--prefix /tmp/inst --out /tmp"
+APP_FLAGS =
+macos-app:
+	$(SHELL) $(top_srcdir)/tools/macos-app.sh --plist tools/Info.plist \
+		--icon $(top_srcdir)/tools/HTTrack.icns $(APP_FLAGS)
+.PHONY: macos-app
+
+# Sign, notarize and pack that bundle into the DMG we publish, e.g.
+#   make macos-release RELEASE_FLAGS="--app /tmp/HTTrack.app --identity ABCD1234 \
+#       --notary-key AuthKey.p8 --notary-key-id KEYID --notary-issuer ISSUERID"
+# See tools/macos-release.sh for the rest; .github/workflows/macos-release.yml runs it.
+RELEASE_FLAGS =
+macos-release:
+	$(SHELL) $(top_srcdir)/tools/macos-release.sh $(RELEASE_FLAGS)
+.PHONY: macos-release

configure.ac

@@ -1,6 +1,6 @@
 AC_PREREQ([2.71])
 
-AC_INIT([httrack], [3.49.14], [roche+packaging@httrack.com], [httrack], [http://www.httrack.com/])
+AC_INIT([httrack], [3.49.16], [roche+packaging@httrack.com], [httrack], [http://www.httrack.com/])
 AC_COPYRIGHT([
 HTTrack Website Copier, Offline Browser for Windows and Unix
 Copyright (C) 1998-2015 Xavier Roche and other contributors
@@ -29,15 +29,80 @@ AC_CONFIG_SRCDIR(src/httrack.c)
 AC_CONFIG_MACRO_DIR([m4])
 AC_CONFIG_HEADERS(config.h)
 AM_INIT_AUTOMAKE([subdir-objects])
-# 3:6:0: 3.49.14 grows two installed structs from the inside (htsoptstate sits mid-
-# httrackp, htsblk mid-lien_back), so the fields after them shift: httrackp.cookies_file
-# +8, lien_back.http11 +48. Soname deliberately stays .so.3: the shifted fields are
-# 3.49-era additions no external consumer reaches, and a libhttrack3 rename isn't worth it.
+# 3:8:0: revision-only bump, no ABI change.
+# 3:7:0: htsblk gained a tail field and lien_back embeds it by value, so
+# lien_back.is_update and everything after it shift +8 (httrackp's own tail growth
+# moves nothing). Soname stays .so.3: HTTrackQt is the only consumer of the installed
+# headers, so a libhttrack4 rename isn't worth it.
 # (3:0:0 was the htsblk mime-buffer widening, the ABI break that moved .so.2 -> .so.3.)
-VERSION_INFO="3:6:0"
+VERSION_INFO="3:8:0"
 AM_MAINTAINER_MODE
 AC_USE_SYSTEM_EXTENSIONS
 
+# A real bash, for "make deb" and the test harness. Not searched into BASH: bash presets
+# that to its own path, and macOS /bin/sh is a bash, so the macro never searches (#895).
+# BASH_SHELL isn't preset the way BASH is, so AC_ARG_VAR needs no guard. Kept ahead of the
+# compiler probes so a bad override dies before them.
+AC_ARG_VAR([BASH_SHELL], [path to a real (non-POSIX-mode) bash])
+# AC_PATH_PROGS drops a relative override and searches instead, which loses the user's intent.
+# Nothing quotes $(BASH_SHELL) in the Makefiles, and quoting could not save it anyway: make
+# splits on whitespace, expands '$' and treats '#' as a comment before any shell sees it.
+case $BASH_SHELL in
+*[[[:space:]]]* | *'#'* | *'$'* | *'`'* | *'\'* | *'"'* | *"'"* | *';'* | *'&'* | *'|'* | \
+*'<'* | *'>'* | *'('* | *')'* | *'*'* | *'?'* | *'@<:@'* | *'@:>@'* | *'{'* | *'}'*)
+  AC_MSG_ERROR([BASH_SHELL must not contain shell or make metacharacters, got: $BASH_SHELL]) ;;
+'' | [[\\/]]* | ?:[[\\/]]*) ;;
+*) AC_MSG_ERROR([BASH_SHELL must be an absolute path, got: $BASH_SHELL]) ;;
+esac
+hts_bash_override=$BASH_SHELL
+AC_PATH_PROGS([BASH_SHELL], [bash], [/bin/bash])
+
+# An absolute override is taken verbatim, so BASH_SHELL=/bin/sh would put #895 back and only
+# surface at "make check" or "make deb" (#908). What we found ourselves is only a warning:
+# a box with no bash still builds, it just cannot run those two.
+AC_MSG_CHECKING([whether $BASH_SHELL is a bash outside POSIX mode])
+hts_bash_why=
+hts_bash_env=no
+# AS_EXECUTABLE_P, not "test -x": the PATH search above already demands a regular file, and
+# bash blocks forever reading a FIFO it failed to exec, so -x alone hangs configure (#922).
+if ! AS_EXECUTABLE_P(["$BASH_SHELL"]); then
+  hts_bash_why="not an executable regular file"
+elif test -z "$("$BASH_SHELL" -c 'echo "${BASH_VERSINFO[[0]]}"' 2>/dev/null)"; then
+  # Not BASH_VERSION: that is an ordinary variable, so any shell echoes back a spoofed one.
+  hts_bash_why="not a bash: it reports no BASH_VERSINFO"
+else
+  # sh-mode bash reports a version too, so only SHELLOPTS tells the two apart.
+  case $("$BASH_SHELL" -c 'echo ":$SHELLOPTS:"' 2>/dev/null) in
+  *:posix:*)
+    hts_bash_why="a bash in POSIX sh-mode"
+    # POSIXLY_CORRECT and an exported SHELLOPTS do that to every bash on the box, so no path
+    # can pass and blaming this one would send the user hunting for another. Reading them
+    # here would not do: configure puts its own shell in posix mode, which sets both.
+    case $(env -u POSIXLY_CORRECT -u SHELLOPTS "$BASH_SHELL" -c 'echo ":$SHELLOPTS:"' 2>/dev/null) in
+    '' | *:posix:*) ;; # no "env -u", or posix whatever the environment: blame the path
+    *) hts_bash_env=yes ;;
+    esac
+    ;;
+  esac
+fi
+if test -z "$hts_bash_why"; then
+  AC_MSG_RESULT([yes])
+else
+  AC_MSG_RESULT([no])
+  hts_bash_msg="POSIXLY_CORRECT or SHELLOPTS forces every bash into POSIX sh-mode, $BASH_SHELL included. Clear them for configure and for make, which hands them to make check and make deb: env -u POSIXLY_CORRECT -u SHELLOPTS ..."
+  if test "$hts_bash_env" = yes; then
+    if test -n "$hts_bash_override"; then
+      AC_MSG_ERROR([$hts_bash_msg])
+    fi
+    AC_MSG_WARN([$hts_bash_msg])
+  else
+    if test -n "$hts_bash_override"; then
+      AC_MSG_ERROR([BASH_SHELL=$BASH_SHELL is $hts_bash_why])
+    fi
+    AC_MSG_WARN([no usable bash found: $BASH_SHELL is $hts_bash_why. "make check" and "make deb" need one; pass BASH_SHELL=/path/to/bash])
+  fi
+fi
+
 AC_PROG_CC
 AM_PROG_CC_C_O
 m4_warn([obsolete],
@@ -48,14 +113,13 @@ m4_warn([obsolete],
 # script's behavior did not change.  They are probably safe to remove.
 AC_CHECK_INCLUDES_DEFAULT
 AC_PROG_EGREP
+# $(SED) substitutes $(datadir) into src/webhttrack
+AC_PROG_SED
 
 LT_INIT
 AC_PROG_LN_S
 LT_INIT
 
-# bash, used to run the test scripts (see tests/Makefile.am TEST_LOG_COMPILER)
-AC_PATH_PROGS([BASH], [bash], [/bin/bash])
-
 # Export LD_LIBRARY_PATH name or equivalent.
 AC_SUBST(SHLIBPATH_VAR,$shlibpath_var)
 
@@ -100,6 +164,9 @@ AX_CHECK_COMPILE_FLAG([-fstack-protector-strong], [DEFAULT_CFLAGS="$DEFAULT_CFLA
 	[AX_CHECK_COMPILE_FLAG([-fstack-protector], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fstack-protector"], [], [-Werror])], [-Werror])
 AX_CHECK_COMPILE_FLAG([-fstack-clash-protection], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fstack-clash-protection"], [], [-Werror])
 AX_CHECK_COMPILE_FLAG([-fcf-protection], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fcf-protection"], [], [-Werror])
+# backtrace() unwinds through these; armhf, unlike amd64/arm64, defaults them off
+# and printed frameless crash reports.
+AX_CHECK_COMPILE_FLAG([-fasynchronous-unwind-tables], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fasynchronous-unwind-tables"], [], [-Werror])
 # No --discard-all: it drops the local symbols naming every static function, so
 # a trace misattributes them to the nearest surviving global. Costs 0.6% size.
 AX_CHECK_LINK_FLAG([-Wl,--no-undefined], [DEFAULT_LDFLAGS="$DEFAULT_LDFLAGS -Wl,--no-undefined"])
@@ -131,6 +198,115 @@ AC_SUBST([LDFLAGS_PIE])
 # Ties a crash trace from a stripped build back to its separate debug symbols.
 AX_CHECK_LINK_FLAG([-Wl,--build-id], [DEFAULT_LDFLAGS="$DEFAULT_LDFLAGS -Wl,--build-id"])
 
+# tools/macos-app.sh rewrites load commands to @rpath, which needs header room ld64 does
+# not leave by default; the probe fails on GNU ld, so this self-gates on Darwin.
+AX_CHECK_LINK_FLAG([-Wl,-headerpad_max_install_names],
+	[DEFAULT_LDFLAGS="$DEFAULT_LDFLAGS -Wl,-headerpad_max_install_names"])
+
+### Relocatable install (#906)
+# libtool records the configured libdir as an absolute rpath, so a copied tree
+# cannot find libhttrack. A binary-relative rpath fixes that where the loader
+# expands the token, which the BSDs disagree on: probe by running one.
+AC_ARG_ENABLE([origin-rpath],
+	AS_HELP_STRING([--disable-origin-rpath],
+		[link the binaries without a binary-relative rpath]),
+	[hts_origin_asked=yes], [enable_origin_rpath=yes; hts_origin_asked=no])
+
+# hts_origin_ref_make survives make's expansion and libtool's eval of the link line.
+hts_origin_ref='$ORIGIN'
+hts_origin_ref_make='\$$ORIGIN'
+
+AS_CASE([$host_os], [darwin*], [hts_origin_darwin=yes], [hts_origin_darwin=no])
+
+hts_save_prefix=$prefix
+hts_save_exec_prefix=$exec_prefix
+test "x$prefix" = xNONE && prefix=$ac_default_prefix
+test "x$exec_prefix" = xNONE && exec_prefix=$prefix
+eval hts_libdir=\"$libdir\"
+eval hts_libdir=\"$hts_libdir\"
+prefix=$hts_save_prefix
+exec_prefix=$hts_save_exec_prefix
+
+# Enumerated, not read from libtool's sys_lib_dlsearch_path_spec: that one is
+# only augmented when /etc/ld.so.conf exists, so a sysroot or minimal container
+# would let a distribution libdir through. Spelled out rather than globbed as
+# /lib*, which would swallow /libfoo and /usr/libexec.
+AS_CASE([$hts_libdir],
+	[/lib | /lib/* | /lib32 | /lib32/* | /lib64 | /lib64/* | /libx32 | /libx32/*], [hts_origin_sysdir=yes],
+	[/usr/lib | /usr/lib/* | /usr/lib32 | /usr/lib32/* | /usr/lib64 | /usr/lib64/* | /usr/libx32 | /usr/libx32/*], [hts_origin_sysdir=yes],
+	[hts_origin_sysdir=no])
+
+ORIGIN_RPATH=no
+RPATH_ORIGIN_LDFLAGS=""
+if test "x$enable_origin_rpath" = xno; then
+	AC_MSG_NOTICE([binary-relative rpath disabled by request])
+elif test "x$hts_origin_darwin" = xyes; then
+	# dyld reads LC_RPATH only for an @rpath/ load path, and libtool stamps the
+	# dylib with an absolute -install_name, so the entry would never be consulted.
+	AC_MSG_NOTICE([binary-relative rpath not used: libtool records an absolute install_name on Darwin])
+elif test "x$enable_shared" = xno; then
+	AC_MSG_NOTICE([binary-relative rpath not needed: no shared libraries])
+elif test "x$hts_origin_sysdir" = xyes; then
+	# A distribution libdir is already searched, and an rpath there is a lintian tag.
+	AC_MSG_NOTICE([binary-relative rpath not used: $hts_libdir is a system libdir])
+elif test "x$cross_compiling" = xyes && test "x$hts_origin_asked" = xno; then
+	AC_MSG_NOTICE([binary-relative rpath not probed: cross compiling, pass --enable-origin-rpath to force it])
+else
+	AC_MSG_CHECKING([whether the loader honours a binary-relative rpath])
+	AC_CACHE_VAL([hts_cv_origin_rpath], [
+		hts_cv_origin_rpath=no
+		# Cross compiling cannot run the probe, so take the stricter spelling first.
+		hts_origin_cands="none origin"
+		test "x$cross_compiling" = xyes && hts_origin_cands="origin none"
+		rm -rf conftest.origin
+		AS_MKDIR_P([conftest.origin/bin])
+		AS_MKDIR_P([conftest.origin/lib])
+		AS_MKDIR_P([conftest.origin/run])
+		cat >conftest.origin/lib.c <<_ACEOF
+int hts_origin_probe(void);
+int hts_origin_probe(void) { return 42; }
+_ACEOF
+		cat >conftest.origin/main.c <<_ACEOF
+int hts_origin_probe(void);
+int main(void) { return hts_origin_probe() == 42 ? 0 : 1; }
+_ACEOF
+		hts_origin_mklib="$CC $CFLAGS -fPIC -shared -o conftest.origin/lib/libhtsorigin.so conftest.origin/lib.c"
+		hts_origin_link="-Lconftest.origin/lib -lhtsorigin"
+		if $hts_origin_mklib >&AS_MESSAGE_LOG_FD 2>&1; then
+			for hts_origin_cand in $hts_origin_cands; do
+				# Solaris and the older BSDs expand the token only with -z origin.
+				hts_origin_try=
+				test "x$hts_origin_cand" = xorigin && hts_origin_try=-Wl,-z,origin
+				$CC $CFLAGS $LDFLAGS -o conftest.origin/bin/probe conftest.origin/main.c \
+					$hts_origin_link $hts_origin_try "-Wl,-rpath,$hts_origin_ref/../lib" \
+					>&AS_MESSAGE_LOG_FD 2>&1 || continue
+				# From an unrelated cwd, so a loader taking the token literally fails.
+				if test "x$cross_compiling" = xyes ||
+					(unset LD_LIBRARY_PATH
+					cd conftest.origin/run && ../bin/probe) >&AS_MESSAGE_LOG_FD 2>&1; then
+					hts_cv_origin_rpath=$hts_origin_cand
+					break
+				fi
+			done
+		fi
+		rm -rf conftest.origin
+	])
+	AS_CASE([$hts_cv_origin_rpath],
+		[no], [AC_MSG_RESULT([no])],
+		[
+			# $(libdir) first, so the token only answers once the configured
+			# libdir is gone: $(bindir)/../lib is a different directory under a
+			# lib64 or split-bindir layout and must not shadow it.
+			RPATH_ORIGIN_LDFLAGS='-Wl,-rpath,$(libdir)'
+			test "x$hts_cv_origin_rpath" = xorigin && RPATH_ORIGIN_LDFLAGS="$RPATH_ORIGIN_LDFLAGS -Wl,-z,origin"
+			RPATH_ORIGIN_LDFLAGS="$RPATH_ORIGIN_LDFLAGS -Wl,-rpath,$hts_origin_ref_make/../lib"
+			ORIGIN_RPATH=yes
+			AC_MSG_RESULT([yes ($hts_origin_ref/../lib)])
+		])
+fi
+AC_SUBST([ORIGIN_RPATH])
+AC_SUBST([RPATH_ORIGIN_LDFLAGS])
+
 ### Check for -fvisibility=hidden support
 gl_VISIBILITY
 AM_CFLAGS="$AM_CFLAGS $CFLAG_VISIBILITY"
@@ -173,10 +349,7 @@ AC_CHECK_TYPE(sa_family_t, [], [AC_DEFINE([sa_family_t], [uint16_t], [sa_family_
 AX_CHECK_ALIGNED_ACCESS_REQUIRED
 
 # check for various headers
-AC_CHECK_HEADERS([execinfo.h sys/ioctl.h sys/random.h])
-
-## CSPRNG for the --single-file mark; /dev/urandom is the fallback
-AC_CHECK_FUNCS([getrandom])
+AC_CHECK_HEADERS([execinfo.h sys/ioctl.h])
 
 ### zlib (mandatory)
 CHECK_ZLIB()
@@ -363,5 +536,6 @@ html/Makefile
 libtest/Makefile
 tests/Makefile
 fuzz/Makefile
+tools/Info.plist
 ])
 AC_OUTPUT

debian/changelog

@@ -1,3 +1,21 @@
+httrack (3.49.16-1) unstable; urgency=medium
+
+  * New upstream release: two ProxyTrack buffer overflows fixed, chunked
+    trailer handling, relocatable installs, crash-report backtraces on armhf,
+    a hicolor icon theme and translation fixes; full list in history.txt.
+
+ -- Xavier Roche <xavier@debian.org>  Tue, 04 Aug 2026 18:32:40 +0200
+
+httrack (3.49.15-1) unstable; urgency=medium
+
+  * New upstream release: single-file mirrors with inlined assets, sitemap
+    ingestion, a change report between crawls, and numerous --update, FTP and
+    parser fixes; full list in history.txt.
+  * httrack-doc grows by roughly 1 MB: the offline guide now ships screenshots
+    of the WinHTTrack, WebHTTrack and Android interfaces.
+
+ -- Xavier Roche <xavier@debian.org>  Thu, 30 Jul 2026 10:40:08 +0200
+
 httrack (3.49.14-1) unstable; urgency=medium
 
   * New upstream release: WARC/WACZ archive output, Windows long-path support,

fuzz/.gitignore

@@ -0,0 +1,14 @@
+# Anchored: a glob like /fuzz-* would also swallow the tracked fuzz-*.c sources.
+/fuzz-charset
+/fuzz-meta
+/fuzz-idna
+/fuzz-entities
+/fuzz-unescape
+/fuzz-filters
+/fuzz-url
+/fuzz-header
+/fuzz-cachendx
+/fuzz-htsparse
+/fuzz-singlefile
+/fuzz-sitemap
+/fuzz-arc

fuzz/Makefile.am

@@ -2,7 +2,7 @@
 if FUZZERS
 noinst_PROGRAMS = fuzz-charset fuzz-meta fuzz-idna fuzz-entities \
 	fuzz-unescape fuzz-filters fuzz-url fuzz-header fuzz-cachendx \
-	fuzz-htsparse fuzz-singlefile fuzz-sitemap
+	fuzz-htsparse fuzz-singlefile fuzz-sitemap fuzz-arc
 endif
 
 AM_CPPFLAGS = \
@@ -30,6 +30,11 @@ fuzz_htsparse_SOURCES = fuzz-htsparse.c fuzz.h
 fuzz_singlefile_SOURCES = fuzz-singlefile.c fuzz.h
 fuzz_sitemap_SOURCES = fuzz-sitemap.c fuzz.h
 
+# proxytrack does not link libhttrack, so its store compiles into the harness;
+# coucal, minizip and md5 still come from the static libhttrack above.
+fuzz_arc_SOURCES = fuzz-arc.c fuzz.h $(top_srcdir)/src/proxy/store.c
+fuzz_arc_CPPFLAGS = $(AM_CPPFLAGS) -DZLIB_CONST
+
 # List corpus files explicitly: automake does not expand EXTRA_DIST globs.
 EXTRA_DIST = README.md run-fuzzers.sh \
 	corpus/charset/utf8.txt corpus/charset/latin1.txt corpus/charset/sjis.txt \
@@ -55,4 +60,6 @@ EXTRA_DIST = README.md run-fuzzers.sh \
 	corpus/singlefile/srcset.html corpus/singlefile/rawtext.html \
 	corpus/singlefile/malformed.html corpus/singlefile/many-attrs.html \
 	corpus/sitemap/urlset.xml corpus/sitemap/sitemapindex.xml \
-	corpus/sitemap/truncated.xml corpus/sitemap/urlset.xml.gz
+	corpus/sitemap/truncated.xml corpus/sitemap/urlset.xml.gz \
+	corpus/arc/roundtrip.arc corpus/arc/truncated.arc \
+	corpus/arc/regress-null-body.arc

fuzz/README.md

@@ -13,3 +13,5 @@ bash /path/to/httrack/fuzz/run-fuzzers.sh fuzz 60   # 60s per target
 ```
 
 Run one target by hand: `fuzz/fuzz-url -max_total_time=300 corpusdir fuzz/corpus/url`. Seed corpora live in `corpus/<target>/`; a crash reproducer is replayed with `fuzz/fuzz-url crash-file`.
+
+`fuzz-arc` is the odd one out: it drives proxytrack's `.arc` reader the way `--convert` does, through a temp file rather than a buffer, and it compiles `src/proxy/store.c` into the harness because proxytrack does not link libhttrack. Both readers and the writer print to stderr on malformed input, so pass `-close_fd_mask=2` for anything longer than a corpus replay.

fuzz/corpus/arc/regress-null-body.arc

@@ -0,0 +1,9 @@
+filedesc://t.arc 0.0.0.0 20250101000000 text/plain 200 - - 0 t.arc 9
+2 0 test
+
+
+http://example.com/p.html 0.0.0.0 20250101000000 text/html -1 - - 0 t.arc 77
+HTTP/1.1 -1 Broken
+Content-Type: text/html
+Content-Length: 10
+

fuzz/corpus/arc/roundtrip.arc

@@ -0,0 +1,11 @@
+filedesc://t.arc 0.0.0.0 20250101000000 text/plain 200 - - 0 t.arc 9
+2 0 test
+
+
+http://example.com/p.html 0.0.0.0 20250101000000 text/html 200 - - 0 t.arc 120
+HTTP/1.1 200 OK
+Content-Type: text/html
+Last-Modified: Wed, 01 Jan 2025 00:00:00 GMT
+Content-Length: 10
+
+BODYMARKER

fuzz/corpus/arc/truncated.arc

@@ -0,0 +1,9 @@
+filedesc://t.arc 0.0.0.0 20250101000000 text/plain 200 - - 0 t.arc 9
+2 0 test
+
+
+http://example.com/q.html 0.0.0.0 20250101000000 text/html 200 - - 0 t.arc 2000000000
+HTTP/1.1 200 OK
+Content-Type: text/html
+
+HI

fuzz/corpus/singlefile/img-src.html

@@ -1,4 +1,3 @@
-<img src="a.png#!htsinline">
-<img src=big.png#!htsinline alt=over-cap>
-<img src="../escape.png#!htsinline"><img src="/abs.png#!htsinline">
-<img src="data:,x#!htsinline">
+<img src="a.png">
+<img src=big.png alt=over-cap>
+<img src="../escape.png"><img src="/abs.png"><img src="data:,x">

fuzz/corpus/singlefile/link-rel.html

@@ -1,3 +1,4 @@
-<link rel="stylesheet" href="s.css#!htsinline">
-<link rel="icon" href="a.png#!htsinline">
-<link rel="canonical" href="other.html#!htsinline">
+<link rel="stylesheet" href="s.css">
+<link rel=icon href=a.png>
+<link rel="next" href="p2.html">
+<link rel="preload" href="j.js">

fuzz/corpus/singlefile/malformed.html

@@ -1,3 +1,5 @@
-<p a=1 b=2 c=3 d=4 e=5 f=6 g=7 h=8 i=9 j=10 title="> <img src=a.png#!htsinline>">x</p>
-<!--><img src="a.png#!htsinline">
-<img src="a.png#!htsinline" >
+<img src="unterminated.png
+<div style="background:url(a.png">
+<style>@import url(
+<!-- unterminated comment
+<a href=

fuzz/corpus/singlefile/many-attrs.html

@@ -0,0 +1 @@
+<img src="a.png" a0="v" a1="v" a2="v" a3="v" a4="v" a5="v" a6="v" a7="v" a8="v" a9="v" a10="v" a11="v" a12="v" a13="v" a14="v" a15="v" a16="v" a17="v" a18="v" a19="v" a20="v" a21="v" a22="v" a23="v" a24="v" a25="v" a26="v" a27="v" a28="v" a29="v" a30="v" a31="v" a32="v" a33="v" a34="v" a35="v" a36="v" a37="v" a38="v" a39="v" a40="v" a41="v" a42="v" a43="v" a44="v" a45="v" a46="v" a47="v" a48="v" a49="v" a50="v" a51="v" a52="v" a53="v" a54="v" a55="v" a56="v" a57="v" a58="v" a59="v" a60="v" a61="v" a62="v" a63="v" a64="v" a65="v" a66="v" a67="v" a68="v" a69="v">

fuzz/corpus/singlefile/mark-at-eof.html

@@ -1 +0,0 @@
-a.png#!htsinline

fuzz/corpus/singlefile/mark-degenerate.html

@@ -1,5 +0,0 @@
-#!htsinline#!htsinline#!htsinline
-=#!htsinline=
-"#!htsinline"
-a.png#!htsinlin
-#!htsinlin

fuzz/corpus/singlefile/mark-only.html

@@ -1 +0,0 @@
-#!htsinline

fuzz/corpus/singlefile/rawtext.html

@@ -1,3 +1,4 @@
-<script src="j.js#!htsinline"></script>
-<script>var u="a.png#!htsinline";</script>
-<textarea>a.png#!htsinline</textarea>
+<script>var s="</scripting>"; if(a</b) x=1;</script>
+<script src="j.js"></script>
+<textarea></textareas></textarea>
+<title></titles></title>

fuzz/corpus/singlefile/srcset.html

@@ -1 +1,2 @@
-<img srcset="a.png#!htsinline 1x, big.png#!htsinline 2x, a.png#!htsinline 480w">
+<img srcset="a.png 1x, big.png 2x, a.png 100w">
+<source srcset="a.png,, a.png 2x," src="a.png">

fuzz/corpus/singlefile/style-attr.html

@@ -1,2 +1,2 @@
-<div style="background:url(a.png#!htsinline)"></div>
-<div style='background:url("a.png#!htsinline")'></div>
+<div style="background:url(a.png);list-style:url('a.png')"></div>
+<p style='background:url("a.png")'>x</p>

fuzz/corpus/singlefile/style-block.html

@@ -1,4 +1,5 @@
-<style>@import "s.css#!htsinline";
-@import url(sub/b.css#!htsinline);
-div{background:url(a.png#!htsinline)}
+<style>@import "s.css";
+@import url(sub/b.css);
+div{background:url(a.png)}
+/* url(a.png) */ p:after{content:"url(a.png)"}
 </style>

fuzz/corpus/singlefile/traversal.html

@@ -1,4 +0,0 @@
-<img src="../../../../etc/passwd#!htsinline">
-<img src="a.png#!htsinline#frag?q=1">
-<img src="sub/../a.png#!htsinline">
-<img src="./a.png#!htsinline">

fuzz/fuzz-arc.c

@@ -0,0 +1,106 @@
+/* ------------------------------------------------------------ */
+/*
+HTTrack Website Copier, Offline Browser for Windows and Unix
+Copyright (C) 2026 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Ethical use: we kindly ask that you NOT use this software to harvest email
+addresses or to collect any other private information about people. Doing so
+would dishonor our work and waste the many hours we have spent on it.
+
+Please visit our Website: http://www.httrack.com
+*/
+
+/* Fuzz proxytrack's .arc reader the way `--convert` drives it: the record loop
+   seeks on lengths read from the file, and every entry reaches a writer. */
+#include "fuzz.h"
+
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "coucal.h"
+#include "proxy/store.h"
+
+/* An .arc past this size says nothing a smaller one cannot. */
+#define FUZZ_ARC_MAXSIZE (1024 * 1024)
+
+static char arc_dir[256];
+static char arc_in[sizeof(arc_dir) + sizeof("/in.arc")];
+static char arc_out[sizeof(arc_dir) + sizeof("/out.arc")];
+
+static void fuzz_arc_cleanup(void) {
+  (void) unlink(arc_in);
+  (void) unlink(arc_out);
+  (void) rmdir(arc_dir);
+}
+
+/* proxytrack's main() installs one; without it coucal logs stats per free */
+static void fuzz_arc_coucal_log(coucal_opaque arg, coucal_loglevel level,
+                                const char *format, va_list args) {
+  (void) arg;
+  (void) level;
+  (void) format;
+  (void) args;
+}
+
+/* PT_GetType() picks the format from the extension, so the names end in .arc */
+static int fuzz_arc_setup(void) {
+  if (arc_in[0] == '\0') {
+    const char *const tmp = getenv("TMPDIR");
+
+    coucal_set_global_assert_handler(fuzz_arc_coucal_log, NULL);
+
+    snprintf(arc_dir, sizeof(arc_dir), "%s/fuzz-arc-XXXXXX",
+             tmp != NULL && *tmp != '\0' ? tmp : "/tmp");
+    if (mkdtemp(arc_dir) == NULL) {
+      return -1;
+    }
+    snprintf(arc_out, sizeof(arc_out), "%s/out.arc", arc_dir);
+    snprintf(arc_in, sizeof(arc_in), "%s/in.arc", arc_dir);
+    atexit(fuzz_arc_cleanup);
+  }
+  return 0;
+}
+
+int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
+  PT_Indexes indexes;
+  FILE *fp;
+  hts_boolean written;
+
+  if (size > FUZZ_ARC_MAXSIZE || fuzz_arc_setup() != 0) {
+    return 0;
+  }
+  if ((fp = fopen(arc_in, "wb")) == NULL) {
+    return 0;
+  }
+  written = fwrite(data, 1, size, fp) == size ? HTS_TRUE : HTS_FALSE;
+  if (fclose(fp) != 0 || !written) {
+    return 0;
+  }
+
+  indexes = PT_New();
+  if (indexes != NULL) {
+    if (PT_AddIndex(indexes, arc_in) > 0) {
+      /* the writer reads back every entry the loader indexed */
+      (void) PT_SaveCache(indexes, arc_out);
+    }
+    PT_Delete(indexes);
+  }
+  return 0;
+}

fuzz/fuzz-singlefile.c

@@ -95,13 +95,10 @@ static void sf_init(void) {
   sf_write("a.png", png, sizeof(png) - 1);
   sf_write("big.png", big, sizeof(big));
   sf_text("j.js", "var x=1;\n");
-  /* Marked, so an inlined stylesheet recurses into its own marks and its
-     un-inlinable reference is rebased; unmarked assets leave the target as a
-     bare scan that reaches nothing. */
-  sf_text("s.css", "@import url(sub/b.css" SINGLEFILE_MARK ");\n"
-                   "div{background:url(a.png" SINGLEFILE_MARK ")}\n"
-                   "p{background:url(big.png" SINGLEFILE_MARK ")}\n");
-  sf_text("sub/b.css", "p{background:url(../a.png" SINGLEFILE_MARK ")}\n");
+  /* @import plus a url(), so an inlined stylesheet recurses and its own
+     relative reference is rebased. */
+  sf_text("s.css", "@import url(sub/b.css);\ndiv{background:url(a.png)}\n");
+  sf_text("sub/b.css", "p{background:url(../a.png)}\n");
 }
 
 int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {

fuzz/fuzz.h

@@ -38,7 +38,7 @@ Please visit our Website: http://www.httrack.com
 #include "htsbase.h"
 
 /* Heap NUL-terminated copy of the fuzzer input, so ASan bounds every read. */
-static char *fuzz_strdup(const uint8_t *data, size_t size) {
+HTS_UNUSED static char *fuzz_strdup(const uint8_t *data, size_t size) {
   char *s = malloct(size + 1);
 
   memcpy(s, data, size);

history.txt

@@ -4,6 +4,56 @@ HTTrack Website Copier release history:
 
 This file lists all changes and fixes that have been made for HTTrack
 
+3.49-16
++ New: macOS ships a signed and notarized HTTrack.app with its own icon, bundling the OpenSSL it needs so a downloaded copy launches (#890, #900, #901, #950)
++ New: the desktop icons install into the hicolor theme, scalable SVG included, so Icon=httrack resolves in a launcher (#932, #933)
++ Fixed: an unauthenticated PROPFIND overflowed the ProxyTrack DAV item buffer (#836)
++ Fixed: the cached-headers block was built with an unbounded sprintf (#841)
++ Fixed: a chunked response carrying trailers was rejected as "Invalid chunk" (#855)
++ Fixed: an over-long URL aborted the whole mirror inside the cache instead of reading as a miss (#935, #936)
++ Fixed: ProxyTrack could not re-read the .arc it writes, and crashed on a record whose body it could not read (#834, #929, #931)
++ Fixed: ProxyTrack logged a hashtable stats line and every PROPFIND body to stderr (#911, #918)
++ Fixed: the frozen-slot spool was written inside the mirror namespace, so it landed in the mirrored tree (#859)
++ Fixed: a stack overflow killed httrack with no diagnostic, crash reports named no frame of the executable, and on armhf they had no frames at all (#866, #889, #892)
++ Fixed: an install moved away from its configured prefix could not find its data directory, its shared library, or the html symlink (#885, #887, #894, #906)
++ Fixed: tooltips in the web GUI broke on a translation containing an apostrophe; the escaping now also covers quotes, backslashes, markup and DBCS lead bytes (#864)
++ Fixed: nine strings of the Windows GUI's option dialogs were untranslated in 26 of the 30 language files, and six language files disagreed with their own declared charset (#863, #963)
++ Fixed: the AppStream metainfo still advertised WebHTTrack 3.49.8 (#884)
++ Fixed: the installed development headers did not compile standalone (#943)
++ Fixed: configure discarded a user-supplied BASH_SHELL, resolved bash to /bin/sh on macOS, and hung on one pointing at a FIFO (#891, #895, #908, #922)
++ Changed: the masthead wordmark and the rings background are SVG, so they stay sharp on a hi-DPI screen (#910, #916)
++ Changed: multiple internal hardening, build, test and CI improvements
+
+3.49-15
++ New: --single-file rewrites each saved page with its assets inlined as data: URIs (#713)
++ New: --changes reports what a crawl added, updated or removed against the previous mirror (#714)
++ New: --sitemap and --sitemap-url ingest sitemaps, so pages nothing links to are still found (#712)
++ New: webhttrack exposes --warc-cdx, --wacz and --warc-max-size (#862)
++ Fixed: --update and --purge-old destroyed a good local copy when the re-fetch got no response, was aborted mid-read, or when the backup meant to protect it failed (#746, #748, #758, #775)
++ Fixed: an FTP re-fetch truncated the mirrored file, resumed a complete mirror with REST and spliced the old body into the new one, and a successful transfer was blanked when its backlog slot was swapped out (#771, #797, #798, #823)
++ Fixed: a chunked response cut at a chunk boundary was stored and cached as complete (#840)
++ Fixed: cache repair deleted the old cache before a rename it never checked, and the unlink-then-rename fallback could lose the destination (#779, #786, #790, #824)
++ Fixed: several backward scans from strlen(s) - 1 read before their buffer on an empty string (#730, #768, #770, #814, #821)
++ Fixed: a URL could be saved onto the engine's own temporary files, and the final path segment was never clamped (#774, #842, #852)
++ Fixed: a query-string character reference the page charset cannot represent was left unescaped, changing how the query parses (#854)
++ Fixed: a second --update pass overwrote the previous WARC and regenerated a page-less WACZ (#759)
++ Fixed: WARC output dropped URLs of 1005 bytes or more, archived nothing for a 304 revisit, and marked an engine-forced not-modified as one the server sent (#778, #785, #826, #838, #839)
++ Fixed: ProxyTrack overflowed its .arc header block, walked past the end of an .ndx buffer, trusted an unparsed offset, and crashed on a PROPFIND or on an entry with no usable Last-Modified (#793, #820, #825, #828)
++ Fixed: webhttrack leaked the session id into crawled pages, overflowed its command line so a quoted value could inject flags, let a posted project path repoint the served root, and built its redirect Location in a 256-byte stack buffer (#700, #706, #707, #710)
++ Fixed: in the web GUI, options ticked on by default could not be un-ticked, "max site size" set a per-file cap instead of the HTML one, and the mirror link on the finished page could not be followed (#708, #709, #725)
++ Fixed: htsserver labelled every PNG as image/gif and offered JPEG as a download, and an unauthenticated GET of a directory spun the server forever (#724, #875)
++ Fixed: webhttrack hung at exit when no mirror had been launched (#753)
++ Fixed: oversized cache and header fields aborted the engine or overflowed a neighbouring field instead of being clipped (#701, #715, #717, #722, #732)
++ Fixed: a -%S rules file of 4 GB or more overran the heap (#702)
++ Fixed: the CLI display did not repaint when the terminal was resized (#97)
++ Fixed: a document with no declared charset double-encoded the title lifted for the local index (#848)
++ Fixed: a fragment on an inlined reference was dropped, losing an SVG sprite selector (#766)
++ Fixed: several time helpers handed out libc's shared gmtime/localtime static rather than a reentrant breakdown (#794, #806)
++ Changed: fatal-signal backtraces name engine frames instead of a bare module and offset (#705)
++ Changed: --without-zlib is rejected at configure time rather than failing at link (#735)
++ Changed: the offline documentation gains one GUI guide with screenshots, an Android option reference, and a restructured index
++ Changed: multiple internal hardening, test and CI improvements
+
 3.49-14
 + New: WARC/1.1 archive output (--warc), with a sorted CDXJ index (--warc-cdx) and WACZ packaging (--wacz), also available from webhttrack (#668)
 + New: -%F takes named footer fields such as {url}, {lastmodified}, {mime}, {charset} and {status} instead of a fixed layout (#667)
@@ -98,7 +148,7 @@ This file lists all changes and fixes that have been made for HTTrack
 + Fixed: report why a -%L URL list could not be loaded (#49)
 + Changed: multiple internal hardening, build and CI improvements
 
-.49-9
+3.49-9
 + Fixed: file-type detection from the Content-Type header: trust a declared type over a binary URL extension, honor --assume under the delayed type check, and keep a known extension against a bogus or empty Content-Type (#267, #29, #56)
 + Fixed: an uninitialized-buffer read when the Content-Type is empty (#411)
 + Fixed: restored C++ source-compatibility of the installed headers so reverse dependencies (httraqt) build again (#413)

html/Makefile.am

@@ -11,6 +11,10 @@ WebPixmapdir = $(datadir)/pixmaps
 WebIcon16x16dir = $(datadir)/icons/hicolor/16x16/apps
 WebIcon32x32dir = $(datadir)/icons/hicolor/32x32/apps
 WebIcon48x48dir = $(datadir)/icons/hicolor/48x48/apps
+WebIcon64x64dir = $(datadir)/icons/hicolor/64x64/apps
+WebIcon128x128dir = $(datadir)/icons/hicolor/128x128/apps
+WebIcon256x256dir = $(datadir)/icons/hicolor/256x256/apps
+WebIconScalabledir = $(datadir)/icons/hicolor/scalable/apps
 VFolderEntrydir = $(prefix)/share/applications
 MetaInfodir = $(datadir)/metainfo
 
@@ -19,32 +23,29 @@ MetaInfodir = $(datadir)/metainfo
 # Explicit filenames (e.g. ../history.txt, div/search.sh) resolve via VPATH and
 # need no prefix.
 HelpHtmlroot_DATA = ../httrack-doc.html ../history.txt
-HelpHtml_DATA = $(srcdir)/*.html
+HelpHtml_DATA = $(srcdir)/*.html $(srcdir)/*.js $(srcdir)/*.css
 HelpHtmldiv_DATA = div/search.sh
 HelpHtmlimg_DATA  = $(srcdir)/img/*
 HelpHtmlimages_DATA = $(srcdir)/images/*
 HelpHtmlTxt_DATA = ../greetings.txt ../history.txt ../license.txt
 WebHtml_DATA = $(srcdir)/server/*.html $(srcdir)/server/*.js $(srcdir)/server/*.css
 WebHtmlimages_DATA = $(srcdir)/server/images/*
-# note: converted & normalized by
-# ico2xpm favicon.ico -o httrack.xpm
-# mogrify -format xpm -map /usr/share/doc/menu/examples/cmap.xpm httrack.xpm
+# Generated from the brand master by gen/export.py. Asserted by tests/160.
+# httrack.xpm duplicates the 32x32 one under the bare basename the .desktop
+# Icon= key falls back to here when no icon theme is installed (#932).
 WebPixmap_DATA = $(srcdir)/server/div/*.xpm
 WebIcon16x16_DATA = $(srcdir)/server/div/16x16/*.png
 WebIcon32x32_DATA = $(srcdir)/server/div/32x32/*.png
 WebIcon48x48_DATA = $(srcdir)/server/div/48x48/*.png
+WebIcon64x64_DATA = $(srcdir)/server/div/64x64/*.png
+WebIcon128x128_DATA = $(srcdir)/server/div/128x128/*.png
+WebIcon256x256_DATA = $(srcdir)/server/div/256x256/*.png
+WebIconScalable_DATA = $(srcdir)/server/div/scalable/*.svg
 VFolderEntry_DATA = $(srcdir)/server/div/*.desktop
 MetaInfo_DATA = $(srcdir)/server/div/*.metainfo.xml
 
 EXTRA_DIST = $(HelpHtml_DATA) $(HelpHtmlimg_DATA) $(HelpHtmlimages_DATA) \
 	$(HelpHtmldiv_DATA) $(WebHtml_DATA) $(WebHtmlimages_DATA) \
 	$(WebPixmap_DATA) $(WebIcon16x16_DATA) $(WebIcon32x32_DATA) $(WebIcon48x48_DATA) \
-	$(VFolderEntry_DATA) $(MetaInfo_DATA) \
-	httrack.css
-
-install-data-hook:
-	if test ! -L $(DESTDIR)$(prefix)/share/httrack/html ; then \
-		( cd $(DESTDIR)$(prefix)/share/httrack \
-			&& $(LN_S) $(htmldir) html \
-		) \
-	fi
+	$(WebIcon64x64_DATA) $(WebIcon128x128_DATA) $(WebIcon256x256_DATA) \
+	$(WebIconScalable_DATA) $(VFolderEntry_DATA) $(MetaInfo_DATA)

html/abuse.html

@@ -1,111 +1,74 @@
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
-
+<!DOCTYPE html>
+<html lang="en">
 <head>
-	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
-	<meta name="description" content="HTTrack is an easy-to-use website mirror utility. It allows you to download a World Wide website from the Internet to a local directory,building recursively all structures, getting html, images, and other files from the server to your computer. Links are rebuiltrelatively so that you can freely browse to the local site (works with any browser). You can mirror several sites together so that you can jump from one toanother. You can, also, update an existing mirror site, or resume an interrupted download. The robot is fully configurable, with an integrated help" />
-	<meta name="keywords" content="httrack, HTTRACK, HTTrack, winhttrack, WINHTTRACK, WinHTTrack, offline browser, web mirror utility, aspirateur web, surf offline, web capture, www mirror utility, browse offline, local  site builder, website mirroring, aspirateur www, internet grabber, capture de site web, internet tool, hors connexion, unix, dos, windows 95, windows 98, solaris, ibm580, AIX 4.0, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
-	<title>HTTrack Website Copier - Offline Browser</title>
-
-	<style type="text/css">
-	<!--
-
-body {
-	margin: 0;  padding: 0;  margin-bottom: 15px;  margin-top: 8px;
-	background: #77b;
-}
-body, td {
-	font: 14px "Trebuchet MS", Verdana, Arial, Helvetica, sans-serif;
-	}
-
-#subTitle {
-	background: #000;  color: #fff;  padding: 4px;  font-weight: bold; 
-	}
-
-#siteNavigation a, #siteNavigation .current {
-	font-weight: bold;  color: #448;
-	}
-#siteNavigation a:link    { text-decoration: none; }
-#siteNavigation a:visited { text-decoration: none; }
-
-#siteNavigation .current { background-color: #ccd; }
-
-#siteNavigation a:hover   { text-decoration: none;  background-color: #fff;  color: #000; }
-#siteNavigation a:active  { text-decoration: none;  background-color: #ccc; }
-
-
-a:link    { text-decoration: underline;  color: #00f; }
-a:visited { text-decoration: underline;  color: #000; }
-a:hover   { text-decoration: underline;  color: #c00; }
-a:active  { text-decoration: underline; }
-
-#pageContent {
-	clear: both;
-	border-bottom: 6px solid #000;
-	padding: 10px;  padding-top: 20px;
-	line-height: 1.65em;
-	background-image: url(images/bg_rings.gif);
-	background-repeat: no-repeat;
-	background-position: top right;
-	}
-
-#pageContent, #siteNavigation {
-	background-color: #ccd;
-	}
-
-
-.imgLeft  { float: left;   margin-right: 10px;  margin-bottom: 10px; }
-.imgRight { float: right;  margin-left: 10px;   margin-bottom: 10px; }
-
-hr { height: 1px;  color: #000;  background-color: #000;  margin-bottom: 15px; }
-
-h1 { margin: 0;  font-weight: bold;  font-size: 2em; }
-h2 { margin: 0;  font-weight: bold;  font-size: 1.6em; }
-h3 { margin: 0;  font-weight: bold;  font-size: 1.3em; }
-h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
-
-.blak { background-color: #000; }
-.hide { display: none; }
-.tableWidth { min-width: 400px; }
-
-.tblRegular       { border-collapse: collapse; }
-.tblRegular td    { padding: 6px;  background-image: url(fade.gif);  border: 2px solid #99c; }
-.tblHeaderColor, .tblHeaderColor td { background: #99c; }
-.tblNoBorder td   { border: 0; }
-
-
-// -->
-</style>
-
+<!-- doc-chrome:head -->
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<meta name="description" content="How to mirror a site without hammering the server, and what a webmaster can do about crawlers that do.">
+<link rel="stylesheet" href="doc.css">
+<script src="doc.js" defer></script>
+<!-- /doc-chrome:head -->
+<title>Using HTTrack responsibly</title>
 </head>
+<body>
 
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-	<tr>
-	<td><img src="images/header_title_4.gif" width="400" height="34" alt="HTTrack Website Copier" title="" border="0" id="title" /></td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="3" class="tableWidth">
-	<tr>
-	<td id="subTitle">Open Source offline browser</td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-<tr class="blak">
-<td>
-	<table width="100%" border="0" align="center" cellspacing="1" cellpadding="0">
-	<tr>
-	<td colspan="6"> 
-		<table width="100%" border="0" align="center" cellspacing="0" cellpadding="10">
-		<tr> 
-		<td id="pageContent"> 
-<!-- ==================== End prologue ==================== -->
+<!-- doc-chrome:top -->
+<a class="skip" href="#main">Skip to content</a>
 
-<h3>For HTTrack users:</h3>
+<header class="masthead">
+	<img src="images/wordmark.svg" width="400" height="36" alt="HTTrack Website Copier">
+	<div class="tagline">Open Source offline browser</div>
+</header>
+
+<div class="wrap">
+
+<nav class="toc" aria-label="Documentation">
+	<h2>On this page</h2>
+	<ul>
+		<li><a href="#for-httrack-users">For HTTrack users</a></li>
+		<li><a href="#for-webmasters-having-problems-with-band">For webmasters having problems with bandwidth abuse / other abuses related to HTTrack</a></li>
+		<li><a href="#please-follow-these-common-sense-rules-t">Please follow these common sense rules to avoid any network abuse</a></li>
+		<li><a href="#how-to-limit-network-abuse-httrack-websi">How to limit network abuse HTTrack Website Copier FAQ (updated - DRAFT)</a></li>
+	</ul>
+	<h2>Start here</h2>
+	<ul>
+		<li><a href="guide.html">Interface guide</a></li>
+		<li><a href="faq.html">FAQ and troubleshooting</a></li>
+		<li><a href="abuse.html" aria-current="page" class="here">Using HTTrack responsibly</a></li>
+	</ul>
+	<h2>Command line</h2>
+	<ul>
+		<li><a href="cmdguide.html">Command-line guide</a></li>
+		<li><a href="httrack.man.html">Option reference</a></li>
+		<li><a href="filters.html">Filter syntax</a></li>
+	</ul>
+	<h2>Developers</h2>
+	<ul>
+		<li><a href="dev.html">Programming</a></li>
+		<li><a href="library.html">libhttrack API</a></li>
+		<li><a href="plug.html">Callbacks</a></li>
+		<li><a href="scripting.html">Scripting</a></li>
+		<li><a href="cache.html">Cache format</a></li>
+		<li><a href="changes.html">Change report format</a></li>
+	</ul>
+	<h2>More</h2>
+	<ul>
+		<li><a href="fcguide.html">Users Guide (3.10)</a></li>
+		<li><a href="contact.html">Contact and credits</a></li>
+		<li><a href="index.html">All documentation</a></li>
+	</ul>
+</nav>
+
+<main id="main">
+<!-- /doc-chrome:top -->
+
+<h3 id="for-httrack-users">For HTTrack users:</h3>
 <ul>
 <li><a href="#USERS">Advice & what <u>not</u> to do when you are using HTTrack</a></li>
 </ul>
 <br>
 
-<h3>For webmasters having problems with bandwidth abuse / other abuses related to HTTrack:</h3>
+<h3 id="for-webmasters-having-problems-with-band">For webmasters having problems with bandwidth abuse / other abuses related to HTTrack:</h3>
 <ul>
 <li><a href="#WEBMASTERS">Abuse FAQ for <u>webmasters</a></u></li>
 </ul>
@@ -121,9 +84,9 @@ h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
 
 
 
-<h2 align="center"><em>Advice & what <u>not</u> to do</em></h2>
+<h1>Advice & what <u>not</u> to do</h1>
 
-<center><h3>Please follow these <i>common sense</i> rules to avoid any network abuse</h3></center>
+<center><h3 id="please-follow-these-common-sense-rules-t">Please follow these <i>common sense</i> rules to avoid any network abuse</h3></center>
 
 <br>
 
@@ -178,9 +141,9 @@ Downloading a site can overload it, if you have a fast pipe, or if you capture t
 
 
 
-<h2 align="center"><em>Abuse FAQ for <u>webmasters</u></em></h2>
+<h2 id="abuse-faq-for-webmasters" align="center"><em>Abuse FAQ for <u>webmasters</u></em></h2>
 
-<center><h3>How to limit network abuse
+<center><h3 id="how-to-limit-network-abuse-httrack-websi">How to limit network abuse
 <br>
 HTTrack Website Copier FAQ (updated - DRAFT)
 </h3></center>
@@ -338,19 +301,19 @@ Bad: Radical (your site will only be available online for all users), not easy t
 How to do: Create fake links with &quot;killing&quot; targets<br>
 Example: Use things like &lt;a href=&quot;killme.cgi&quot;&gt;&lt;nothing&gt;&lt;/a&gt;
 (again an example in php:)<br>
-<tt>
+<tt>
+<pre>
+&lt;?php
+	// Add IP.
+	add_temp_firewall_rule($REMOTE_ADDR,"30s");
+?&gt;
+function add_temp_firewall_rule($addr) {
+	// The chain chhttp is flushed in a cron job to avoid ipchains overflow
+    system("/usr/bin/sudo -u root /sbin/ipchains -I 1 chhttp -p tcp -s ".$addr." --dport 80 -j REJECT");
+    syslog("user rejected due to too many copy attemps : ".$addr);
+}
+
 <pre>
-&lt;?php
-	// Add IP.
-	add_temp_firewall_rule($REMOTE_ADDR,"30s");
-?&gt;
-function add_temp_firewall_rule($addr) {
-	// The chain chhttp is flushed in a cron job to avoid ipchains overflow
-    system("/usr/bin/sudo -u root /sbin/ipchains -I 1 chhttp -p tcp -s ".$addr." --dport 80 -j REJECT");
-    syslog("user rejected due to too many copy attemps : ".$addr);
-}
-
-<pre>
 
 </tt>
 <br>
@@ -409,9 +372,9 @@ Example:<br>
 &nbsp;&nbsp;&nbsp; FOS('mycompany.com','smith?subject=Hi, John','Click here to email me!')<br>
 &nbsp;&nbsp;&nbsp; // --&gt;<br>
 &nbsp;&nbsp;&nbsp; &lt;/script&gt;<br>
-&nbsp;&nbsp;&nbsp; &lt;noscript&gt;<br>
-&nbsp;&nbsp;&nbsp;&nbsp;smith at mycompany dot com<br>
-&nbsp;&nbsp;&nbsp; &lt;/noscript&gt;<br>
+&nbsp;&nbsp;&nbsp; &lt;noscript&gt;<br>
+&nbsp;&nbsp;&nbsp;&nbsp;smith at mycompany dot com<br>
+&nbsp;&nbsp;&nbsp; &lt;/noscript&gt;<br>
 </tt>
 <br>
 </li><li>Another one is to create images of emails<br>
@@ -566,26 +529,14 @@ And then, put the email address in your pages through:
 
 <br>
 
-<!-- ==================== Start epilogue ==================== -->
-		</td>
-		</tr>
-		</table>
-	</td>
-	</tr>
-	</table>
-</td>
-</tr>
-</table>
+<!-- doc-chrome:bottom -->
+</main>
+</div>
 
-<table width="76%" border="0" align="center" valign="bottom" cellspacing="0" cellpadding="0">
-	<tr>
-	<td id="footer"><small>&copy; 1998-2026 Xavier Roche & other contributors - Web Design: Leto Kauler.</small></td>
-	</tr>
-</table>
+<dialog id="zoom" aria-label="Enlarged image"><img src="" alt=""></dialog>
+
+<footer>&copy; 1998-2026 Xavier Roche &amp; other contributors - Web Design: Leto Kauler.</footer>
+<!-- /doc-chrome:bottom -->
 
 </body>
-
 </html>
-
-
-

html/addurl.html

@@ -1,155 +1,10 @@
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
-
+<!DOCTYPE html>
+<html lang="en">
 <head>
-	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
-	<meta name="description" content="HTTrack is an easy-to-use website mirror utility. It allows you to download a World Wide website from the Internet to a local directory,building recursively all structures, getting html, images, and other files from the server to your computer. Links are rebuiltrelatively so that you can freely browse to the local site (works with any browser). You can mirror several sites together so that you can jump from one toanother. You can, also, update an existing mirror site, or resume an interrupted download. The robot is fully configurable, with an integrated help" />
-	<meta name="keywords" content="httrack, HTTRACK, HTTrack, winhttrack, WINHTTRACK, WinHTTrack, offline browser, web mirror utility, aspirateur web, surf offline, web capture, www mirror utility, browse offline, local  site builder, website mirroring, aspirateur www, internet grabber, capture de site web, internet tool, hors connexion, unix, dos, windows 95, windows 98, solaris, ibm580, AIX 4.0, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
-	<title>HTTrack Website Copier - Offline Browser</title>
-
-	<style type="text/css">
-	<!--
-
-body {
-	margin: 0;  padding: 0;  margin-bottom: 15px;  margin-top: 8px;
-	background: #77b;
-}
-body, td {
-	font: 14px "Trebuchet MS", Verdana, Arial, Helvetica, sans-serif;
-	}
-
-#subTitle {
-	background: #000;  color: #fff;  padding: 4px;  font-weight: bold; 
-	}
-
-#siteNavigation a, #siteNavigation .current {
-	font-weight: bold;  color: #448;
-	}
-#siteNavigation a:link    { text-decoration: none; }
-#siteNavigation a:visited { text-decoration: none; }
-
-#siteNavigation .current { background-color: #ccd; }
-
-#siteNavigation a:hover   { text-decoration: none;  background-color: #fff;  color: #000; }
-#siteNavigation a:active  { text-decoration: none;  background-color: #ccc; }
-
-
-a:link    { text-decoration: underline;  color: #00f; }
-a:visited { text-decoration: underline;  color: #000; }
-a:hover   { text-decoration: underline;  color: #c00; }
-a:active  { text-decoration: underline; }
-
-#pageContent {
-	clear: both;
-	border-bottom: 6px solid #000;
-	padding: 10px;  padding-top: 20px;
-	line-height: 1.65em;
-	background-image: url(images/bg_rings.gif);
-	background-repeat: no-repeat;
-	background-position: top right;
-	}
-
-#pageContent, #siteNavigation {
-	background-color: #ccd;
-	}
-
-
-.imgLeft  { float: left;   margin-right: 10px;  margin-bottom: 10px; }
-.imgRight { float: right;  margin-left: 10px;   margin-bottom: 10px; }
-
-hr { height: 1px;  color: #000;  background-color: #000;  margin-bottom: 15px; }
-
-h1 { margin: 0;  font-weight: bold;  font-size: 2em; }
-h2 { margin: 0;  font-weight: bold;  font-size: 1.6em; }
-h3 { margin: 0;  font-weight: bold;  font-size: 1.3em; }
-h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
-
-.blak { background-color: #000; }
-.hide { display: none; }
-.tableWidth { min-width: 400px; }
-
-.tblRegular       { border-collapse: collapse; }
-.tblRegular td    { padding: 6px;  background-image: url(fade.gif);  border: 2px solid #99c; }
-.tblHeaderColor, .tblHeaderColor td { background: #99c; }
-.tblNoBorder td   { border: 0; }
-
-
-// -->
-</style>
-
+<meta charset="utf-8">
+<title>Moved to the HTTrack interface guide</title>
+<link rel="canonical" href="guide.html#step-address">
+<meta http-equiv="refresh" content="0; url=guide.html#step-address">
 </head>
-
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-	<tr>
-	<td><img src="images/header_title_4.gif" width="400" height="34" alt="HTTrack Website Copier" title="" border="0" id="title" /></td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="3" class="tableWidth">
-	<tr>
-	<td id="subTitle">Open Source offline browser</td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-<tr class="blak">
-<td>
-	<table width="100%" border="0" align="center" cellspacing="1" cellpadding="0">
-	<tr>
-	<td colspan="6"> 
-		<table width="100%" border="0" align="center" cellspacing="0" cellpadding="10">
-		<tr> 
-		<td id="pageContent"> 
-<!-- ==================== End prologue ==================== -->
-
-<h2 align="center"><em>Add a URL</em></h2>
-
-<br>
-
-<ol>
-  <li>Enter a typical Web address</li>
-  <br><small>Just type in your address in the field</small><br><br>
-  <center><img src="img/addurl1.gif" border="0"></center>
-<br><br>OR<br><br>
-  <li>Enter a Web address with authentication</li>
-  <br><small>Useful when you need basic authentication to watch the Web page</small><br><br>
-  <center><img src="img/addurl2.gif" border="0"></center>
-<br><br>OR<br><br>
-  <li>Capture a link from your Web browser to HTTrack</li>
-  <br><small>Use this tool only for form-based pages (pages delivered after submiting a form) that need some analysis</small><br><br>
-  <center><img src="img/addurl3.gif" border="0"></center>
-  <br>
-  <br>
-<small>Set, as explained, your Web browser proxy preferences to the values indicated : set the proxy's address, and the proxy's port,
-  then click on the button or link as you usually do in your Web browser. 
-  <br>The temporary proxy, installed by HTTrack, will then
-  capture the link and display a confirmation page.
-  <br><br>
-</small>
-  <center><img src="img/addurl4.gif" border="0"></center>
-  <br>
-  <center><img src="img/addurl5.gif" border="0"></center>
-</ol>
-
-<br><br><br><br>
-<p align="right">Back to <a href="index.html">Home</a></p>
-
-<!-- ==================== Start epilogue ==================== -->
-		</td>
-		</tr>
-		</table>
-	</td>
-	</tr>
-	</table>
-</td>
-</tr>
-</table>
-
-<table width="76%" border="0" align="center" valign="bottom" cellspacing="0" cellpadding="0">
-	<tr>
-	<td id="footer"><small>&copy; 1998-2026 Xavier Roche & other contributors - Web Design: Leto Kauler.</small></td>
-	</tr>
-</table>
-
-</body>
-
+<body><p>Adding a URL is now part of <a href="guide.html#step-address">the HTTrack interface guide</a>.</p></body>
 </html>
-
-

html/android.html

@@ -1,223 +1,11 @@
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
-
+<!DOCTYPE html>
+<html lang="en">
 <head>
-	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
-	<meta name="description" content="How to mirror a website with HTTrack on Android: install the app, create a project, enter the address, run the mirror, and browse the result on your device." />
-	<meta name="keywords" content="httrack, HTTrack, android, offline browser, web mirror utility, website mirroring, mobile, Google Play" />
-	<title>HTTrack on Android</title>
-
-	<style type="text/css">
-	<!--
-
-body {
-	margin: 0;  padding: 0;  margin-bottom: 15px;  margin-top: 8px;
-	background: #77b;
-}
-body, td {
-	font: 14px "Trebuchet MS", Verdana, Arial, Helvetica, sans-serif;
-	}
-
-#subTitle {
-	background: #000;  color: #fff;  padding: 4px;  font-weight: bold;
-	}
-
-#siteNavigation a, #siteNavigation .current {
-	font-weight: bold;  color: #448;
-	}
-#siteNavigation a:link    { text-decoration: none; }
-#siteNavigation a:visited { text-decoration: none; }
-
-#siteNavigation .current { background-color: #ccd; }
-
-#siteNavigation a:hover   { text-decoration: none;  background-color: #fff;  color: #000; }
-#siteNavigation a:active  { text-decoration: none;  background-color: #ccc; }
-
-
-a:link    { text-decoration: underline;  color: #00f; }
-a:visited { text-decoration: underline;  color: #000; }
-a:hover   { text-decoration: underline;  color: #c00; }
-a:active  { text-decoration: underline; }
-
-#pageContent {
-	clear: both;
-	border-bottom: 6px solid #000;
-	padding: 10px;  padding-top: 20px;
-	line-height: 1.65em;
-	background-image: url(images/bg_rings.gif);
-	background-repeat: no-repeat;
-	background-position: top right;
-	}
-
-#pageContent, #siteNavigation {
-	background-color: #ccd;
-	}
-
-
-.imgLeft  { float: left;   margin-right: 10px;  margin-bottom: 10px; }
-.imgRight { float: right;  margin-left: 10px;   margin-bottom: 10px; }
-
-hr { height: 1px;  color: #000;  background-color: #000;  margin-bottom: 15px; }
-
-h1 { margin: 0;  font-weight: bold;  font-size: 2em; }
-h2 { margin: 0;  font-weight: bold;  font-size: 1.6em; }
-h3 { margin: 0;  font-weight: bold;  font-size: 1.3em; }
-h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
-
-.blak { background-color: #000; }
-.hide { display: none; }
-.tableWidth { min-width: 400px; }
-
-.tblRegular       { border-collapse: collapse; }
-.tblRegular td    { padding: 6px;  background-image: url(fade.gif);  border: 2px solid #99c; }
-.tblHeaderColor, .tblHeaderColor td { background: #99c; }
-.tblNoBorder td   { border: 0; }
-
-
-// -->
-</style>
-
+<meta charset="utf-8">
+<title>Moved to the HTTrack interface guide</title>
+<link rel="canonical" href="guide.html">
+<meta http-equiv="refresh" content="0; url=guide.html#droid/">
 </head>
-
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-	<tr>
-	<td><img src="images/header_title_4.gif" width="400" height="34" alt="HTTrack Website Copier" title="" border="0" id="title" /></td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="3" class="tableWidth">
-	<tr>
-	<td id="subTitle">Open Source offline browser</td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-<tr class="blak">
-<td>
-	<table width="100%" border="0" align="center" cellspacing="1" cellpadding="0">
-	<tr>
-	<td colspan="6">
-		<table width="100%" border="0" align="center" cellspacing="0" cellpadding="10">
-		<tr>
-		<td id="pageContent">
-<!-- ==================== End prologue ==================== -->
-
-<h2 align="center"><em>HTTrack on Android</em></h2>
-
-<br>
-
-<p>HTTrack downloads a website to your device so you can read it offline. The
-Android app runs the same mirroring engine as the desktop version behind a touch
-interface. It needs Android 7.0 or later, and is available on
-<a href="https://play.google.com/store/apps/details?id=com.httrack.android">Google Play</a>.</p>
-
-<p>The steps below follow one mirror from start to finish.</p>
-
-<br>
-
-<ol>
-
-  <li><b>Grant storage access</b></li>
-  <br><small>On first launch the app asks for permission to store mirrors on your
-  device. The prompt reads <em>"Allow HTTrack Website Copier to access photos,
-  media, and files on your device?"</em>. Tap <b>ALLOW</b>: without it the app
-  cannot save the downloaded files.</small>
-  <br><br><center><img src="img/android_permission.png" width="320" alt="First-run storage permission dialog" border="0"></center>
-  <br><small>If you have used an older release, a second prompt offers to bring its
-  mirrors into the app. Tap <b>Import</b> to move them, or <b>Not now</b> to
-  skip.</small>
-  <br><br><center><img src="img/android_import.png" width="320" alt="Import mirrors from an older version" border="0"></center>
-<br><br>
-
-  <li><b>Start</b></li>
-  <br><small>The welcome screen shows the engine version at the bottom. Tap
-  <b>Next</b> to create a project, or <b>Browse sites</b> to open a mirror you
-  already made.</small>
-  <br><br><center><img src="img/android_startup.png" width="320" alt="Welcome screen" border="0"></center>
-<br><br>
-
-  <li><b>Name the project</b></li>
-  <br><small>Give the project a name, and optionally a category to group related
-  mirrors. <b>Base path</b> shows where the files will be written. Tap
-  <b>Next</b>.</small>
-  <br><br><center><img src="img/android_project.png" width="320" alt="Project name, category, and base path" border="0"></center>
-<br><br>
-
-  <li><b>Enter the address</b></li>
-  <br><small>Type the site address. If a project of the same name already exists,
-  pick <b>Continue interrupted download</b> or <b>Update existing download</b>.
-  Tap <b>Options</b> to adjust the crawl, or <b>Start</b> to begin.</small>
-  <br><br><center><img src="img/android_url.png" width="320" alt="Web address and download action" border="0"></center>
-<br><br>
-
-  <li><b>Options (optional)</b></li>
-  <br><small>The <b>Options</b> screen holds the crawl settings, grouped into
-  eleven tabs. It uses the same profile format as the desktop version, so a tab you
-  know from WinHTTrack behaves the same way here.</small>
-  <br><br><center><img src="img/android_options.png" width="320" alt="Options tab list" border="0"></center>
-  <br><small>The tabs are:</small>
-  <ul>
-    <li><small><b>Scan Rules</b>: wildcard filters for the addresses to keep or skip.</small></li>
-    <li><small><b>Limits</b>: caps on depth, size, time, speed, and number of connections.</small></li>
-    <li><small><b>Flow Control</b>: simultaneous connections, timeouts, and retries.</small></li>
-    <li><small><b>Links</b>: how far to follow links, and which extra files to fetch.</small></li>
-    <li><small><b>Build</b>: how the saved files and folders are named.</small></li>
-    <li><small><b>Browser ID</b>: the user-agent, language, and headers sent to servers.</small></li>
-    <li><small><b>Spider</b>: cookies, robots.txt handling, and request behavior.</small></li>
-    <li><small><b>Proxy address</b>: proxy host and port.</small></li>
-    <li><small><b>Log, Index, Cache</b>: log files, the search index, and the update cache.</small></li>
-    <li><small><b>Type/MIME associations</b>: map file extensions to MIME types.</small></li>
-    <li><small><b>Experts Only</b>: scan mode, how far the crawl may travel, and link rewriting.</small></li>
-  </ul>
-  <br><center><img src="img/android_scanrules.png" width="320" alt="Scan Rules tab" border="0"></center>
-  <br><center><img src="img/android_experts.png" width="320" alt="Experts Only tab" border="0"></center>
-  <br><small>The <a href="step9.html">desktop option reference</a> describes every
-  setting in full. A few desktop options are missing or fixed on Android: the proxy
-  tab has a host and port but no login and password, the download folder is fixed
-  inside the app's storage so there is no output-path setting, and the MIME table
-  holds up to eight entries.</small>
-<br><br>
-
-  <li><b>Run the mirror</b></li>
-  <br><small>HTTrack downloads the site and reports live figures: bytes saved,
-  links scanned, transfer rate, and errors. Tap <b>Abort</b> to stop early; a
-  partial mirror can be resumed later.</small>
-  <br><br><center><img src="img/android_progress.png" width="320" alt="Crawl in progress with live statistics" border="0"></center>
-<br><br>
-
-  <li><b>Browse the result</b></li>
-  <br><small>When the crawl finishes the app reports <b>Success</b> and the mirror
-  location. Tap <b>Browse Mirrored Website</b> to read the copy in your browser,
-  <b>View log</b> to see what happened, or <b>New project</b> to start
-  again.</small>
-  <br><br><center><img src="img/android_finished.png" width="320" alt="Mirror finished, success" border="0"></center>
-<br><br>
-
-  <li><b>Where the files are</b></li>
-  <br><small>Mirrors are written under <tt>/storage/emulated/0/HTTrack/Websites</tt>,
-  in a folder named after the project. That folder lives in your device's shared
-  storage, so a file manager or a USB connection can reach it. Opening
-  <tt>index.html</tt> there browses a mirror without the app.</small>
-
-</ol>
-
-<br><br><br><br>
-<p align="right">Back to <a href="index.html">Home</a></p>
-
-<!-- ==================== Start epilogue ==================== -->
-		</td>
-		</tr>
-		</table>
-	</td>
-	</tr>
-	</table>
-</td>
-</tr>
-</table>
-
-<table width="76%" border="0" align="center" valign="bottom" cellspacing="0" cellpadding="0">
-	<tr>
-	<td id="footer"><small>&copy; 1998-2026 Xavier Roche & other contributors - Web Design: Leto Kauler.</small></td>
-	</tr>
-</table>
-
-</body>
-
+<body><p>This page is now part of
+<a href="guide.html#droid/">the HTTrack interface guide</a>.</p></body>
 </html>

html/cache.html

@@ -1,293 +1,238 @@
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
-
+<!DOCTYPE html>
+<html lang="en">
 <head>
-	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
-	<meta name="description" content="HTTrack is an easy-to-use website mirror utility. It allows you to download a World Wide website from the Internet to a local directory,building recursively all structures, getting html, images, and other files from the server to your computer. Links are rebuiltrelatively so that you can freely browse to the local site (works with any browser). You can mirror several sites together so that you can jump from one toanother. You can, also, update an existing mirror site, or resume an interrupted download. The robot is fully configurable, with an integrated help" />
-	<meta name="keywords" content="httrack, HTTRACK, HTTrack, winhttrack, WINHTTRACK, WinHTTrack, offline browser, web mirror utility, aspirateur web, surf offline, web capture, www mirror utility, browse offline, local  site builder, website mirroring, aspirateur www, internet grabber, capture de site web, internet tool, hors connexion, unix, dos, windows 95, windows 98, solaris, ibm580, AIX 4.0, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
-	<title>HTTrack Website Copier - Cache format specification</title>
-
-	<style type="text/css">
-	<!--
-
-body {
-	margin: 0;  padding: 0;  margin-bottom: 15px;  margin-top: 8px;
-	background: #77b;
-}
-body, td {
-	font: 14px "Trebuchet MS", Verdana, Arial, Helvetica, sans-serif;
-	}
-
-#subTitle {
-	background: #000;  color: #fff;  padding: 4px;  font-weight: bold; 
-	}
-
-#siteNavigation a, #siteNavigation .current {
-	font-weight: bold;  color: #448;
-	}
-#siteNavigation a:link    { text-decoration: none; }
-#siteNavigation a:visited { text-decoration: none; }
-
-#siteNavigation .current { background-color: #ccd; }
-
-#siteNavigation a:hover   { text-decoration: none;  background-color: #fff;  color: #000; }
-#siteNavigation a:active  { text-decoration: none;  background-color: #ccc; }
-
-
-a:link    { text-decoration: underline;  color: #00f; }
-a:visited { text-decoration: underline;  color: #000; }
-a:hover   { text-decoration: underline;  color: #c00; }
-a:active  { text-decoration: underline; }
-
-#pageContent {
-	clear: both;
-	border-bottom: 6px solid #000;
-	padding: 10px;  padding-top: 20px;
-	line-height: 1.65em;
-	background-image: url(images/bg_rings.gif);
-	background-repeat: no-repeat;
-	background-position: top right;
-	}
-
-#pageContent, #siteNavigation {
-	background-color: #ccd;
-	}
-
-
-.imgLeft  { float: left;   margin-right: 10px;  margin-bottom: 10px; }
-.imgRight { float: right;  margin-left: 10px;   margin-bottom: 10px; }
-
-hr { height: 1px;  color: #000;  background-color: #000;  margin-bottom: 15px; }
-
-h1 { margin: 0;  font-weight: bold;  font-size: 2em; }
-h2 { margin: 0;  font-weight: bold;  font-size: 1.6em; }
-h3 { margin: 0;  font-weight: bold;  font-size: 1.3em; }
-h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
-
-.blak { background-color: #000; }
-.hide { display: none; }
-.tableWidth { min-width: 400px; }
-
-.tblRegular       { border-collapse: collapse; }
-.tblRegular td    { padding: 6px;  background-image: url(fade.gif);  border: 2px solid #99c; }
-.tblHeaderColor, .tblHeaderColor td { background: #99c; }
-.tblNoBorder td   { border: 0; }
-
-
-// -->
-</style>
-
+<!-- doc-chrome:head -->
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<meta name="description" content="The format of the HTTrack cache in hts-cache, and how to read it.">
+<link rel="stylesheet" href="doc.css">
+<script src="doc.js" defer></script>
+<!-- /doc-chrome:head -->
+<title>HTTrack cache format</title>
 </head>
+<body>
 
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-	<tr>
-	<td><img src="images/header_title_4.gif" width="400" height="34" alt="HTTrack Website Copier" title="" border="0" id="title" /></td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="3" class="tableWidth">
-	<tr>
-	<td id="subTitle">Open Source offline browser</td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-<tr class="blak">
-<td>
-	<table width="100%" border="0" align="center" cellspacing="1" cellpadding="0">
-	<tr>
-	<td colspan="6"> 
-		<table width="100%" border="0" align="center" cellspacing="0" cellpadding="10">
-		<tr> 
-		<td id="pageContent"> 
-<!-- ==================== End prologue ==================== -->
+<!-- doc-chrome:top -->
+<a class="skip" href="#main">Skip to content</a>
 
-<h2 align="center"><em>Cache format specification</em></h2>
+<header class="masthead">
+	<img src="images/wordmark.svg" width="400" height="36" alt="HTTrack Website Copier">
+	<div class="tagline">Open Source offline browser</div>
+</header>
+
+<div class="wrap">
+
+<nav class="toc" aria-label="Documentation">
+	<h2>Start here</h2>
+	<ul>
+		<li><a href="guide.html">Interface guide</a></li>
+		<li><a href="faq.html">FAQ and troubleshooting</a></li>
+		<li><a href="abuse.html">Using HTTrack responsibly</a></li>
+	</ul>
+	<h2>Command line</h2>
+	<ul>
+		<li><a href="cmdguide.html">Command-line guide</a></li>
+		<li><a href="httrack.man.html">Option reference</a></li>
+		<li><a href="filters.html">Filter syntax</a></li>
+	</ul>
+	<h2>Developers</h2>
+	<ul>
+		<li><a href="dev.html">Programming</a></li>
+		<li><a href="library.html">libhttrack API</a></li>
+		<li><a href="plug.html">Callbacks</a></li>
+		<li><a href="scripting.html">Scripting</a></li>
+		<li><a href="cache.html" aria-current="page" class="here">Cache format</a></li>
+		<li><a href="changes.html">Change report format</a></li>
+	</ul>
+	<h2>More</h2>
+	<ul>
+		<li><a href="fcguide.html">Users Guide (3.10)</a></li>
+		<li><a href="contact.html">Contact and credits</a></li>
+		<li><a href="index.html">All documentation</a></li>
+	</ul>
+</nav>
+
+<main id="main">
+<!-- /doc-chrome:top -->
+
+<h1>Cache format specification</h1>
 
 <br />
 
-For updating purpose, HTTrack stores original (untouched) HTML data, 
-references to downloaded files, and other meta-data (especially parts of the HTTP headers) in a cache, 
-located in the hts-cache directory. Because local html pages are always modified to "fit" the local
-filesystem structure, and because meta-data such as the last-Modified date and Etag can not be stored
-with the associated files, the cache is absolutely mandatory for reprocessing (update/continue) phases.
-
-<br /><br />
-
-<h3>The (new) cache.zip format</h3>
-
-The 3.31 release of HTTrack introduces a new cache format, more extensible and efficient than the previous one (ndx/dat format).
-
-The main advantages of this cache are:
-
-<ul>
-<li>One single file for a complete website cache archive</li>
-<li>Standard <a href="http://www.pkware.com/products/enterprise/white_papers/appnote.txt" target="_new">ZIP</a> format, that can be easily reused on most platforms and languages</li>
-<li>Compressed data with the efficient and opened <a href="http://www.gzip.org/zlib/" target="_new">zlib</a> format</li>
-</ul>
-
-The cache is made of ZIP files entries ; with one ZIP file entry per fetched URL (successfully or not - errors are also stored).<br />
-For each entry:
-<ul>
-<li>The ZIP file name is the original URL [<small><a href="#orig">see notes below</a></small>]</li>
-<li>The ZIP file contents, <b>if available</b>, is the original (compressed, using the deflate algorythm) data</li>
-<li>The ZIP file extra field (in the local file header) contains a list of meta-fields, very similar to the <a href="http://www.ietf.org/rfc/rfc2616.txt?number=2616" target="new_">HTTP</a> headers fields. See also <a href="http://www.ietf.org/rfc/rfc2396.txt?number=2396" target="new_">RFC</a>.</li><br />
-<li>The ZIP file timestamp follows the "Last-Modified-Since" field given for this URL, if any</li>
-</ul>
-
-Example of cache file:
-<br />
-
-<pre>
-$ unzip -l hts-cache/new.zip
-Archive:  hts-cache/new.zip
-HTTrack Website Copier/3.31-ALPHA-4 mirror complete in 3 seconds : 5 links scanned, 
-3 files written (16109 bytes overall) [17690 bytes received at 5896 bytes/sec]
-(1 errors, 0 warnings, 0 messages)
-  Length     Date   Time    Name
- --------    ----   ----    ----
-       94  07-18-03 08:59   http://www.httrack.com/robots.txt
-     9866  01-17-04 01:09   http://www.httrack.com/html/cache.html
-        0  05-11-03 13:31   http://www.httrack.com/html/images/bg_rings.gif
-      207  01-19-04 05:49   http://www.httrack.com/html/fade.gif
-        0  05-11-03 13:31   http://www.httrack.com/html/images/header_title_4.gif
- --------                   -------
-    10167                   5 files
-</pre>
-
-Example of cache file meta-data:
-<br />
-
-<pre>
-HTTP/1.1 200 OK
-X-In-Cache: 1
-X-StatusCode: 200
-X-StatusMessage: OK
-X-Size: 94
-Content-Type: text/plain
-Last-Modified: Fri, 18 Jul 2003 08:59:11 GMT
-Etag: "40ebb5-5e-3f17b6df"
-X-Addr: www.httrack.com
-X-Fil: /robots.txt
-</pre>
-
-There are also specific issues regarding this format:
-
-<ul>
-<li>The data in the central directory (such as CD extra field, and CD comments) are not used</li>
-<li>The ZIP archive is allowed to contains more than 2^16 files (65535) ; in such case the total number of entries in the 32-bit central directory is 65536 (0xffff), but the presence of the 64-bit central directory is not mandatory</li>
-<li>The ZIP archive is allowed to contains more than 2^32 bytes (4GiB) ; in such case the 64-bit central directory is emitted automatically (a single stored entry of 4GiB or more is not supported)</li>
-</ul>
-
-<br />
-<b>Meta-data stored in the "extra field" of the local file headers</b><br />
-
-The extra field is composed of text data, and this text data is composed of distinct lines of headers.
-The end of text, <b>or</b> a double CR/LF, mark the end of this zone.
-This method allows you to optionally store original HTTP headers just after the "meta-data" headers for informational use.<br />
-
-<br />
-<b>The status line (the first headers line)</b><br />
-
-Status-Line = HTTP-Version SP Status-Code SP X-Reason-Phrase CRLF<br />
-
-<br />
-<b>Other lines:</b><br />
-
-<br />
-<b>Specific fields:</b><br />
-<ul>
-<li>X-In-Cache</li><br>
-Indicates if the data are present (value=1) in the cache (that is, as ZIP data), or in an external file (value=0).
-This field MUST be the first field.
-
-<li>X-StatusCode</li><br>
-The modified (by httrack) status code after processing. 304 error codes ("Not modified"), for example, are transformed into "200" codes after processing.
-
-<li>X-StatusMessage</li><br>
-The modified (by httrack) status message.
-
-<li>X-Size</li><br>
-The stored (either in cache, or in an external file) data size.
-
-<li>X-Charset</li><br>
-The original charset.
-
-<li>X-Addr</li><br>
-The original URL address part.
-
-<li>X-Fil</li><br>
-The original URL path part.
-
-<li>X-Save</li><br>
-The local filename, depending on user's "build structure" preferences.
-
-</ul>
-
-<br />
-<b>Standard (RFC 2616) "useful" fields:</b><br />
-<ul>
-<li>Content-Type</li>
-<li>Last-Modified</li>
-<li>Etag</li>
-<li>Location</li>
-<li>Content-Disposition</li>
-</ul>
-
-<br />
-<b>Specific fields in "BNF-like" grammar:</b><br />
-
-<pre>
-X-In-Cache          = "X-In-Cache" ":" 1*DIGIT
-X-StatusCode        = "X-StatusCode" ":" 1*DIGIT
-X-StatusMessage     = "X-StatusMessage" ":" *&lt;TEXT, excluding CR, LF&gt;
-X-Size              = "X-Size" ":" 1*DIGIT
-X-Charset           = "X-Charset" ":" value
-X-Addr              = "X-Addr" ":" scheme ":" "//" authority
-X-Fil               = "X-Fil" ":" rel_path
-X-Save              = "X-Save" ":" rel_path
-</pre>
-
-<b>RFC standard fields:</b><br />
-
-<pre>
-Content-Type        = "Content-Type" ":" media-type
-Last-Modified       = "Last-Modified" ":" HTTP-date
-Etag                = "ETag" ":" entity-tag
-Location            = "Location" ":" absoluteURI
-Content-Disposition = "Content-Disposition" ":" disposition-type *( ";" disposition-parm )
-</pre>
-
-<br />
-And, for your information,
-<pre>
-X-Reason-Phrase     = *&lt;TEXT, with a maximum of 32 characters, and excluding CR, LF&gt;
-</pre>
-
-
-<a name="orig">Note: Because the URLs may have an unexpected format, especially with double "/" inside, and other reserved characters ("?", "&" ..),
-various ZIP uncompressors can potentially have troubles accessing or decompressing the data.
-Libraries should generally handle this peculiar format, however.
-</a>
+For updating purpose, HTTrack stores original (untouched) HTML data, 
+references to downloaded files, and other meta-data (especially parts of the HTTP headers) in a cache, 
+located in the hts-cache directory. Because local html pages are always modified to "fit" the local
+filesystem structure, and because meta-data such as the last-Modified date and Etag can not be stored
+with the associated files, the cache is absolutely mandatory for reprocessing (update/continue) phases.
 
 <br /><br />
 
-<!-- ==================== Start epilogue ==================== -->
-		</td>
-		</tr>
-		</table>
-	</td>
-	</tr>
-	</table>
-</td>
-</tr>
-</table>
+<h3 id="the-new-cache-zip-format">The (new) cache.zip format</h3>
 
-<table width="76%" border="0" align="center" valign="bottom" cellspacing="0" cellpadding="0">
-	<tr>
-	<td id="footer"><small>&copy; 1998-2026 Xavier Roche & other contributors - Web Design: Leto Kauler.</small></td>
-	</tr>
-</table>
+The 3.31 release of HTTrack introduces a new cache format, more extensible and efficient than the previous one (ndx/dat format).
+
+The main advantages of this cache are:
+
+<ul>
+<li>One single file for a complete website cache archive</li>
+<li>Standard <a href="http://www.pkware.com/products/enterprise/white_papers/appnote.txt" target="_new">ZIP</a> format, that can be easily reused on most platforms and languages</li>
+<li>Compressed data with the efficient and opened <a href="http://www.gzip.org/zlib/" target="_new">zlib</a> format</li>
+</ul>
+
+The cache is made of ZIP files entries ; with one ZIP file entry per fetched URL (successfully or not - errors are also stored).<br />
+For each entry:
+<ul>
+<li>The ZIP file name is the original URL [<small><a href="#orig">see notes below</a></small>]</li>
+<li>The ZIP file contents, <b>if available</b>, is the original (compressed, using the deflate algorythm) data</li>
+<li>The ZIP file extra field (in the local file header) contains a list of meta-fields, very similar to the <a href="http://www.ietf.org/rfc/rfc2616.txt?number=2616" target="new_">HTTP</a> headers fields. See also <a href="http://www.ietf.org/rfc/rfc2396.txt?number=2396" target="new_">RFC</a>.</li><br />
+<li>The ZIP file timestamp follows the "Last-Modified-Since" field given for this URL, if any</li>
+</ul>
+
+Example of cache file:
+<br />
+
+<pre>
+$ unzip -l hts-cache/new.zip
+Archive:  hts-cache/new.zip
+HTTrack Website Copier/3.31-ALPHA-4 mirror complete in 3 seconds : 5 links scanned, 
+3 files written (16109 bytes overall) [17690 bytes received at 5896 bytes/sec]
+(1 errors, 0 warnings, 0 messages)
+  Length     Date   Time    Name
+ --------    ----   ----    ----
+       94  07-18-03 08:59   http://www.httrack.com/robots.txt
+     9866  01-17-04 01:09   http://www.httrack.com/html/cache.html
+        0  05-11-03 13:31   http://www.httrack.com/html/images/bg_rings.gif
+      207  01-19-04 05:49   http://www.httrack.com/html/fade.gif
+        0  05-11-03 13:31   http://www.httrack.com/html/images/header_title_4.gif
+ --------                   -------
+    10167                   5 files
+</pre>
+
+Example of cache file meta-data:
+<br />
+
+<pre>
+HTTP/1.1 200 OK
+X-In-Cache: 1
+X-StatusCode: 200
+X-StatusMessage: OK
+X-Size: 94
+Content-Type: text/plain
+Last-Modified: Fri, 18 Jul 2003 08:59:11 GMT
+Etag: "40ebb5-5e-3f17b6df"
+X-Addr: www.httrack.com
+X-Fil: /robots.txt
+</pre>
+
+There are also specific issues regarding this format:
+
+<ul>
+<li>The data in the central directory (such as CD extra field, and CD comments) are not used</li>
+<li>The ZIP archive is allowed to contains more than 2^16 files (65535) ; in such case the total number of entries in the 32-bit central directory is 65536 (0xffff), but the presence of the 64-bit central directory is not mandatory</li>
+<li>The ZIP archive is allowed to contains more than 2^32 bytes (4GiB) ; in such case the 64-bit central directory is emitted automatically (a single stored entry of 4GiB or more is not supported)</li>
+</ul>
+
+<br />
+<b>Meta-data stored in the "extra field" of the local file headers</b><br />
+
+The extra field is composed of text data, and this text data is composed of distinct lines of headers.
+The end of text, <b>or</b> a double CR/LF, mark the end of this zone.
+This method allows you to optionally store original HTTP headers just after the "meta-data" headers for informational use.<br />
+
+<br />
+<b>The status line (the first headers line)</b><br />
+
+Status-Line = HTTP-Version SP Status-Code SP X-Reason-Phrase CRLF<br />
+
+<br />
+<b>Other lines:</b><br />
+
+<br />
+<b>Specific fields:</b><br />
+<ul>
+<li>X-In-Cache</li><br>
+Indicates if the data are present (value=1) in the cache (that is, as ZIP data), or in an external file (value=0).
+This field MUST be the first field.
+
+<li>X-StatusCode</li><br>
+The modified (by httrack) status code after processing. 304 error codes ("Not modified"), for example, are transformed into "200" codes after processing.
+
+<li>X-StatusMessage</li><br>
+The modified (by httrack) status message.
+
+<li>X-Size</li><br>
+The stored (either in cache, or in an external file) data size.
+
+<li>X-Charset</li><br>
+The original charset.
+
+<li>X-Addr</li><br>
+The original URL address part.
+
+<li>X-Fil</li><br>
+The original URL path part.
+
+<li>X-Save</li><br>
+The local filename, depending on user's "build structure" preferences.
+
+</ul>
+
+<br />
+<b>Standard (RFC 2616) "useful" fields:</b><br />
+<ul>
+<li>Content-Type</li>
+<li>Last-Modified</li>
+<li>Etag</li>
+<li>Location</li>
+<li>Content-Disposition</li>
+</ul>
+
+<br />
+<b>Specific fields in "BNF-like" grammar:</b><br />
+
+<pre>
+X-In-Cache          = "X-In-Cache" ":" 1*DIGIT
+X-StatusCode        = "X-StatusCode" ":" 1*DIGIT
+X-StatusMessage     = "X-StatusMessage" ":" *&lt;TEXT, excluding CR, LF&gt;
+X-Size              = "X-Size" ":" 1*DIGIT
+X-Charset           = "X-Charset" ":" value
+X-Addr              = "X-Addr" ":" scheme ":" "//" authority
+X-Fil               = "X-Fil" ":" rel_path
+X-Save              = "X-Save" ":" rel_path
+</pre>
+
+<b>RFC standard fields:</b><br />
+
+<pre>
+Content-Type        = "Content-Type" ":" media-type
+Last-Modified       = "Last-Modified" ":" HTTP-date
+Etag                = "ETag" ":" entity-tag
+Location            = "Location" ":" absoluteURI
+Content-Disposition = "Content-Disposition" ":" disposition-type *( ";" disposition-parm )
+</pre>
+
+<br />
+And, for your information,
+<pre>
+X-Reason-Phrase     = *&lt;TEXT, with a maximum of 32 characters, and excluding CR, LF&gt;
+</pre>
+
+
+<a name="orig">Note: Because the URLs may have an unexpected format, especially with double "/" inside, and other reserved characters ("?", "&" ..),
+various ZIP uncompressors can potentially have troubles accessing or decompressing the data.
+Libraries should generally handle this peculiar format, however.
+</a>
+
+<br /><br />
+
+<!-- doc-chrome:bottom -->
+</main>
+</div>
+
+<dialog id="zoom" aria-label="Enlarged image"><img src="" alt=""></dialog>
+
+<footer>&copy; 1998-2026 Xavier Roche &amp; other contributors - Web Design: Leto Kauler.</footer>
+<!-- /doc-chrome:bottom -->
 
 </body>
-
 </html>
-
-

html/changes.html

@@ -1,105 +1,70 @@
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
-
+<!DOCTYPE html>
+<html lang="en">
 <head>
-	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
-	<meta name="description" content="HTTrack is an easy-to-use website mirror utility. It allows you to download a World Wide website from the Internet to a local directory,building recursively all structures, getting html, images, and other files from the server to your computer. Links are rebuiltrelatively so that you can freely browse to the local site (works with any browser). You can mirror several sites together so that you can jump from one toanother. You can, also, update an existing mirror site, or resume an interrupted download. The robot is fully configurable, with an integrated help" />
-	<meta name="keywords" content="httrack, HTTRACK, HTTrack, winhttrack, WINHTTRACK, WinHTTrack, offline browser, web mirror utility, aspirateur web, surf offline, web capture, www mirror utility, browse offline, local  site builder, website mirroring, aspirateur www, internet grabber, capture de site web, internet tool, hors connexion, unix, dos, windows 95, windows 98, solaris, ibm580, AIX 4.0, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
-	<title>HTTrack Website Copier - Change report format specification</title>
-
-	<style type="text/css">
-	<!--
-
-body {
-	margin: 0;  padding: 0;  margin-bottom: 15px;  margin-top: 8px;
-	background: #77b;
-}
-body, td {
-	font: 14px "Trebuchet MS", Verdana, Arial, Helvetica, sans-serif;
-	}
-
-#subTitle {
-	background: #000;  color: #fff;  padding: 4px;  font-weight: bold; 
-	}
-
-#siteNavigation a, #siteNavigation .current {
-	font-weight: bold;  color: #448;
-	}
-#siteNavigation a:link    { text-decoration: none; }
-#siteNavigation a:visited { text-decoration: none; }
-
-#siteNavigation .current { background-color: #ccd; }
-
-#siteNavigation a:hover   { text-decoration: none;  background-color: #fff;  color: #000; }
-#siteNavigation a:active  { text-decoration: none;  background-color: #ccc; }
-
-
-a:link    { text-decoration: underline;  color: #00f; }
-a:visited { text-decoration: underline;  color: #000; }
-a:hover   { text-decoration: underline;  color: #c00; }
-a:active  { text-decoration: underline; }
-
-#pageContent {
-	clear: both;
-	border-bottom: 6px solid #000;
-	padding: 10px;  padding-top: 20px;
-	line-height: 1.65em;
-	background-image: url(images/bg_rings.gif);
-	background-repeat: no-repeat;
-	background-position: top right;
-	}
-
-#pageContent, #siteNavigation {
-	background-color: #ccd;
-	}
-
-
-.imgLeft  { float: left;   margin-right: 10px;  margin-bottom: 10px; }
-.imgRight { float: right;  margin-left: 10px;   margin-bottom: 10px; }
-
-hr { height: 1px;  color: #000;  background-color: #000;  margin-bottom: 15px; }
-
-h1 { margin: 0;  font-weight: bold;  font-size: 2em; }
-h2 { margin: 0;  font-weight: bold;  font-size: 1.6em; }
-h3 { margin: 0;  font-weight: bold;  font-size: 1.3em; }
-h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
-
-.blak { background-color: #000; }
-.hide { display: none; }
-.tableWidth { min-width: 400px; }
-
-.tblRegular       { border-collapse: collapse; }
-.tblRegular td    { padding: 6px;  background-image: url(fade.gif);  border: 2px solid #99c; }
-.tblHeaderColor, .tblHeaderColor td { background: #99c; }
-.tblNoBorder td   { border: 0; }
-
-
-// -->
-</style>
-
+<!-- doc-chrome:head -->
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<meta name="description" content="The change report HTTrack writes after an update, field by field.">
+<link rel="stylesheet" href="doc.css">
+<script src="doc.js" defer></script>
+<!-- /doc-chrome:head -->
+<title>HTTrack change report format</title>
 </head>
+<body>
 
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-	<tr>
-	<td><img src="images/header_title_4.gif" width="400" height="34" alt="HTTrack Website Copier" title="" border="0" id="title" /></td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="3" class="tableWidth">
-	<tr>
-	<td id="subTitle">Open Source offline browser</td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-<tr class="blak">
-<td>
-	<table width="100%" border="0" align="center" cellspacing="1" cellpadding="0">
-	<tr>
-	<td colspan="6"> 
-		<table width="100%" border="0" align="center" cellspacing="0" cellpadding="10">
-		<tr> 
-		<td id="pageContent"> 
-<!-- ==================== End prologue ==================== -->
+<!-- doc-chrome:top -->
+<a class="skip" href="#main">Skip to content</a>
 
-<h2 align="center"><em>Change report format specification</em></h2>
+<header class="masthead">
+	<img src="images/wordmark.svg" width="400" height="36" alt="HTTrack Website Copier">
+	<div class="tagline">Open Source offline browser</div>
+</header>
+
+<div class="wrap">
+
+<nav class="toc" aria-label="Documentation">
+	<h2>On this page</h2>
+	<ul>
+		<li><a href="#what-changed-means">What "changed" means</a></li>
+		<li><a href="#with-the-cache-off">With the cache off</a></li>
+		<li><a href="#fields">Fields</a></li>
+		<li><a href="#encoding">Encoding</a></li>
+		<li><a href="#example">Example</a></li>
+		<li><a href="#notes">Notes</a></li>
+	</ul>
+	<h2>Start here</h2>
+	<ul>
+		<li><a href="guide.html">Interface guide</a></li>
+		<li><a href="faq.html">FAQ and troubleshooting</a></li>
+		<li><a href="abuse.html">Using HTTrack responsibly</a></li>
+	</ul>
+	<h2>Command line</h2>
+	<ul>
+		<li><a href="cmdguide.html">Command-line guide</a></li>
+		<li><a href="httrack.man.html">Option reference</a></li>
+		<li><a href="filters.html">Filter syntax</a></li>
+	</ul>
+	<h2>Developers</h2>
+	<ul>
+		<li><a href="dev.html">Programming</a></li>
+		<li><a href="library.html">libhttrack API</a></li>
+		<li><a href="plug.html">Callbacks</a></li>
+		<li><a href="scripting.html">Scripting</a></li>
+		<li><a href="cache.html">Cache format</a></li>
+		<li><a href="changes.html" aria-current="page" class="here">Change report format</a></li>
+	</ul>
+	<h2>More</h2>
+	<ul>
+		<li><a href="fcguide.html">Users Guide (3.10)</a></li>
+		<li><a href="contact.html">Contact and credits</a></li>
+		<li><a href="index.html">All documentation</a></li>
+	</ul>
+</nav>
+
+<main id="main">
+<!-- /doc-chrome:top -->
+
+<h1>Change report format specification</h1>
 
 <br />
 
@@ -111,7 +76,7 @@ summary of the same counts.
 
 <br /><br />
 
-<h3>What "changed" means</h3>
+<h3 id="what-changed-means">What "changed" means</h3>
 
 A resource is changed when its bytes differ, not when the server merely re-sent
 it. HTTrack compares the payload it just received against the copy the previous
@@ -129,7 +94,7 @@ server that answers 200 rather than 304 reads as changed. Keeping the cache on
 
 <br /><br />
 
-<h3>With the cache off</h3>
+<h3 id="with-the-cache-off">With the cache off</h3>
 
 <tt>--cache=0</tt> costs the report more than the digest of a parsed page. The
 mirror's file index (<tt>hts-cache/new.lst</tt>) is what records which files a
@@ -142,7 +107,7 @@ compare against and fall back to the transfer signal.
 
 <br /><br />
 
-<h3>Fields</h3>
+<h3 id="fields">Fields</h3>
 
 <ul>
 <li><tt>schema</tt>: format version, currently <tt>1</tt>. It is bumped only
@@ -179,7 +144,7 @@ copy the previous run left.</li>
 
 <br />
 
-<h3>Encoding</h3>
+<h3 id="encoding">Encoding</h3>
 
 The file is JSON, UTF-8. URLs and local paths reach HTTrack as raw bytes and are
 not guaranteed to be valid UTF-8; any byte sequence that is not becomes
@@ -188,7 +153,7 @@ rather than on <tt>url</tt> when a mirror is known to carry legacy-charset URLs.
 
 <br /><br />
 
-<h3>Example</h3>
+<h3 id="example">Example</h3>
 
 <pre>
 {
@@ -216,7 +181,7 @@ rather than on <tt>url</tt> when a mirror is known to carry legacy-charset URLs.
 
 <br /><br />
 
-<h3>Notes</h3>
+<h3 id="notes">Notes</h3>
 
 <ul>
 <li>A file listed under <tt>gone</tt> is only deleted when <tt>--purge-old</tt> is
@@ -239,25 +204,14 @@ scope: both change what a mirror directory contains.</li>
 
 <br /><br />
 
-<!-- ==================== Start epilogue ==================== -->
-		</td>
-		</tr>
-		</table>
-	</td>
-	</tr>
-	</table>
-</td>
-</tr>
-</table>
+<!-- doc-chrome:bottom -->
+</main>
+</div>
 
-<table width="76%" border="0" align="center" valign="bottom" cellspacing="0" cellpadding="0">
-	<tr>
-	<td id="footer"><small>&copy; 1998-2026 Xavier Roche & other contributors - Web Design: Leto Kauler.</small></td>
-	</tr>
-</table>
+<dialog id="zoom" aria-label="Enlarged image"><img src="" alt=""></dialog>
+
+<footer>&copy; 1998-2026 Xavier Roche &amp; other contributors - Web Design: Leto Kauler.</footer>
+<!-- /doc-chrome:bottom -->
 
 </body>
-
 </html>
-
-

html/cmddoc.html

@@ -0,0 +1,10 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<title>Moved to the command-line guide</title>
+<link rel="canonical" href="cmdguide.html">
+<meta http-equiv="refresh" content="0; url=cmdguide.html">
+</head>
+<body><p>This page is now part of <a href="cmdguide.html">the HTTrack command-line guide</a>.</p></body>
+</html>

html/cmdguide.html

@@ -1,102 +1,75 @@
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
-
+<!DOCTYPE html>
+<html lang="en">
 <head>
-	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
-	<meta name="description" content="HTTrack is an easy-to-use website mirror utility. It allows you to download a World Wide website from the Internet to a local directory,building recursively all structures, getting html, images, and other files from the server to your computer. Links are rebuiltrelatively so that you can freely browse to the local site (works with any browser). You can mirror several sites together so that you can jump from one toanother. You can, also, update an existing mirror site, or resume an interrupted download. The robot is fully configurable, with an integrated help" />
-	<meta name="keywords" content="httrack, HTTRACK, HTTrack, winhttrack, WINHTTRACK, WinHTTrack, offline browser, web mirror utility, aspirateur web, surf offline, web capture, www mirror utility, browse offline, local  site builder, website mirroring, aspirateur www, internet grabber, capture de site web, internet tool, hors connexion, unix, dos, windows 95, windows 98, solaris, ibm580, AIX 4.0, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
-	<title>HTTrack Website Copier - Offline Browser</title>
-
-	<style type="text/css">
-	<!--
-
-body {
-	margin: 0;  padding: 0;  margin-bottom: 15px;  margin-top: 8px;
-	background: #77b;
-}
-body, td {
-	font: 14px "Trebuchet MS", Verdana, Arial, Helvetica, sans-serif;
-	}
-
-#subTitle {
-	background: #000;  color: #fff;  padding: 4px;  font-weight: bold; 
-	}
-
-#siteNavigation a, #siteNavigation .current {
-	font-weight: bold;  color: #448;
-	}
-#siteNavigation a:link    { text-decoration: none; }
-#siteNavigation a:visited { text-decoration: none; }
-
-#siteNavigation .current { background-color: #ccd; }
-
-#siteNavigation a:hover   { text-decoration: none;  background-color: #fff;  color: #000; }
-#siteNavigation a:active  { text-decoration: none;  background-color: #ccc; }
-
-a:link    { text-decoration: underline;  color: #00f; }
-a:visited { text-decoration: underline;  color: #000; }
-a:hover   { text-decoration: underline;  color: #c00; }
-a:active  { text-decoration: underline; }
-
-#pageContent {
-	clear: both;
-	border-bottom: 6px solid #000;
-	padding: 10px;  padding-top: 20px;
-	line-height: 1.65em;
-	background-image: url(images/bg_rings.gif);
-	background-repeat: no-repeat;
-	background-position: top right;
-	}
-
-#pageContent, #siteNavigation {
-	background-color: #ccd;
-	}
-
-.imgLeft  { float: left;   margin-right: 10px;  margin-bottom: 10px; }
-.imgRight { float: right;  margin-left: 10px;   margin-bottom: 10px; }
-
-hr { height: 1px;  color: #000;  background-color: #000;  margin-bottom: 15px; }
-
-h1 { margin: 0;  font-weight: bold;  font-size: 2em; }
-h2 { margin: 0;  font-weight: bold;  font-size: 1.6em; }
-h3 { margin: 0;  font-weight: bold;  font-size: 1.3em; }
-h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
-
-.blak { background-color: #000; }
-.hide { display: none; }
-.tableWidth { min-width: 400px; }
-
-.tblRegular       { border-collapse: collapse; }
-.tblRegular td    { padding: 6px;  background-image: url(fade.gif);  border: 2px solid #99c; }
-.tblHeaderColor, .tblHeaderColor td { background: #99c; }
-.tblNoBorder td   { border: 0; }
-
-// -->
-</style>
-
+<!-- doc-chrome:head -->
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<meta name="description" content="A task-oriented guide to the httrack command line: scope, filters, limits, logins, proxies, updates and recipes.">
+<link rel="stylesheet" href="doc.css">
+<script src="doc.js" defer></script>
+<!-- /doc-chrome:head -->
+<title>HTTrack command-line guide</title>
 </head>
+<body>
 
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-	<tr>
-	<td><img src="images/header_title_4.gif" width="400" height="34" alt="HTTrack Website Copier" title="" border="0" id="title" /></td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="3" class="tableWidth">
-	<tr>
-	<td id="subTitle">Open Source offline browser</td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-<tr class="blak">
-<td>
-	<table width="100%" border="0" align="center" cellspacing="1" cellpadding="0">
-	<tr>
-	<td colspan="6"> 
-		<table width="100%" border="0" align="center" cellspacing="0" cellpadding="10">
-		<tr> 
-		<td id="pageContent"> 
-<!-- ==================== End prologue ==================== -->
+<!-- doc-chrome:top -->
+<a class="skip" href="#main">Skip to content</a>
 
-<h2 align="center"><em>Command-Line Guide</em></h2>
+<header class="masthead">
+	<img src="images/wordmark.svg" width="400" height="36" alt="HTTrack Website Copier">
+	<div class="tagline">Open Source offline browser</div>
+</header>
+
+<div class="wrap">
+
+<nav class="toc" aria-label="Documentation">
+	<h2>On this page</h2>
+	<ul>
+		<li><a href="#quickstart">1. Quick start</a></li>
+		<li><a href="#scope">2. Scope: how far the crawl reaches</a></li>
+		<li><a href="#filters">3. Filters and scan rules</a></li>
+		<li><a href="#limits">4. Limits and politeness</a></li>
+		<li><a href="#names">5. File names and types</a></li>
+		<li><a href="#links">6. Links and page building</a></li>
+		<li><a href="#identity">7. Identity, cookies and login</a></li>
+		<li><a href="#proxy">8. Proxy and network</a></li>
+		<li><a href="#update">9. Update and cache</a></li>
+		<li><a href="#experts">10. Experts and scripting</a></li>
+		<li><a href="#recipes">11. Recipes</a></li>
+	</ul>
+	<h2>Start here</h2>
+	<ul>
+		<li><a href="guide.html">Interface guide</a></li>
+		<li><a href="faq.html">FAQ and troubleshooting</a></li>
+		<li><a href="abuse.html">Using HTTrack responsibly</a></li>
+	</ul>
+	<h2>Command line</h2>
+	<ul>
+		<li><a href="cmdguide.html" aria-current="page" class="here">Command-line guide</a></li>
+		<li><a href="httrack.man.html">Option reference</a></li>
+		<li><a href="filters.html">Filter syntax</a></li>
+	</ul>
+	<h2>Developers</h2>
+	<ul>
+		<li><a href="dev.html">Programming</a></li>
+		<li><a href="library.html">libhttrack API</a></li>
+		<li><a href="plug.html">Callbacks</a></li>
+		<li><a href="scripting.html">Scripting</a></li>
+		<li><a href="cache.html">Cache format</a></li>
+		<li><a href="changes.html">Change report format</a></li>
+	</ul>
+	<h2>More</h2>
+	<ul>
+		<li><a href="fcguide.html">Users Guide (3.10)</a></li>
+		<li><a href="contact.html">Contact and credits</a></li>
+		<li><a href="index.html">All documentation</a></li>
+	</ul>
+</nav>
+
+<main id="main">
+<!-- /doc-chrome:top -->
+
+<h1>Command-Line Guide</h1>
 
 <p>This is a task-oriented guide to the <tt>httrack</tt> command line: how to do the
 things people actually ask for, and the handful of defaults that surprise
@@ -112,21 +85,6 @@ the log. Every project writes <tt>hts-log.txt</tt> (and <tt>hts-err.txt</tt>) in
 its output directory, and those files name every URL that was refused, redirected,
 or filtered out. Read them first.</p>
 
-<h4>On this page</h4>
-<ul class="tblNoBorder">
-  <li><a href="#quickstart">1. Quick start</a></li>
-  <li><a href="#scope">2. Scope: how far the crawl reaches</a></li>
-  <li><a href="#filters">3. Filters and scan rules</a></li>
-  <li><a href="#limits">4. Limits and politeness</a></li>
-  <li><a href="#names">5. File names and types</a></li>
-  <li><a href="#links">6. Links and page building</a></li>
-  <li><a href="#identity">7. Identity, cookies and login</a></li>
-  <li><a href="#proxy">8. Proxy and network</a></li>
-  <li><a href="#update">9. Update and cache</a></li>
-  <li><a href="#experts">10. Experts and scripting</a></li>
-  <li><a href="#recipes">11. Recipes</a></li>
-</ul>
-
 <h3 id="quickstart">1. Quick start</h3>
 
 <p>A mirror is one command: a start URL and an output directory.</p>
@@ -156,7 +114,7 @@ you write. Get this right and most "it downloaded too much" or "it only grabbed
 the index" problems disappear.</p>
 
 <table class="tblRegular tableWidth" border="0">
-  <tr class="tblHeaderColor"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
+  <tr class="head"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
   <tr><td><tt>--depth (-r)</tt></td><td>Maximum link depth. <b>The start page is level 1</b>, so one level of links out is <tt>-r2</tt>, not <tt>-r1</tt>.</td></tr>
   <tr><td><tt>--stay-on-same-address (-a), --stay-on-same-domain (-d), --stay-on-same-tld (-l), --go-everywhere (-e)</tt></td><td>How far off the starting host the crawl may travel: same address (host), same principal domain, same top-level domain (for example .com), or everywhere. The default keeps you on the starting host.</td></tr>
   <tr><td><tt>--can-go-down (-D), --can-go-up (-U), --stay-on-same-dir (-S), --can-go-up-and-down (-B)</tt></td><td>Directory travel: down into subdirectories only, up to parent directories only, stay in the same directory, or both up and down.</td></tr>
@@ -242,7 +200,7 @@ options will not help there. That is an
 bracket forms match narrower sets. The full table, with size and mime rules, is on
 <a href="filters.html">the filters page</a>.</p>
 <table class="tblRegular tableWidth" border="0">
-  <tr class="tblHeaderColor"><td><b>Wildcard</b></td><td><b>Matches</b></td><td><b>Example</b></td></tr>
+  <tr class="head"><td><b>Wildcard</b></td><td><b>Matches</b></td><td><b>Example</b></td></tr>
   <tr><td><tt>*</tt></td><td>any run of characters</td><td><tt>+*.pdf</tt> &mdash; any URL ending <tt>.pdf</tt></td></tr>
   <tr><td><tt>*[file]</tt>, <tt>*[name]</tt></td><td>one path segment (any char but <tt>/</tt> and <tt>?</tt>)</td><td><tt>example.com/*[file]/</tt> &mdash; a directory-index page</td></tr>
   <tr><td><tt>*[path]</tt></td><td>a path, slashes allowed (any char but <tt>?</tt>)</td><td><tt>example.com/*[path].zip</tt></td></tr>
@@ -261,7 +219,7 @@ accident, and the <a href="abuse.html">abuse page</a> is worth a read. The limit
 below let you go faster when you own the target, and slower when you do not.</p>
 
 <table class="tblRegular tableWidth" border="0">
-  <tr class="tblHeaderColor"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
+  <tr class="head"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
   <tr><td><tt>--max-rate (-A)</tt></td><td>Maximum transfer rate in bytes/sec. <b>The default is about 100 KB/s even without this flag.</b> Raise it to go faster.</td></tr>
   <tr><td><tt>--sockets (-c)</tt></td><td>Number of parallel connections (default 4). <tt>--tiny</tt>, <tt>--wide</tt> and <tt>--ultrawide</tt> are presets.</td></tr>
   <tr><td><tt>--connection-per-second (-%c)</tt></td><td>New connections opened per second (default 5).</td></tr>
@@ -288,7 +246,7 @@ usually about a URL like <tt>/article?id=42</tt> or a <tt>.php</tt> page that is
 really HTML.</p>
 
 <table class="tblRegular tableWidth" border="0">
-  <tr class="tblHeaderColor"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
+  <tr class="head"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
   <tr><td><tt>--structure (-N)</tt></td><td>The local path and name layout. Presets are numeric, and you can also give a template such as <tt>--structure "%h%p/%n%q.%t"</tt>.</td></tr>
   <tr><td><tt>--long-names (-L)</tt></td><td>Long names, 8.3 names, or ISO9660 for CD masters.</td></tr>
   <tr><td><tt>--assume (-%A)</tt></td><td>Assume a MIME type for an extension, for example <tt>--assume php=text/html</tt>. This also skips the extra HEAD probe HTTrack would otherwise send to learn the type.</td></tr>
@@ -312,7 +270,7 @@ naming.</p>
 ones it kept so the local copy browses offline. These options tune both halves.</p>
 
 <table class="tblRegular tableWidth" border="0">
-  <tr class="tblHeaderColor"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
+  <tr class="head"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
   <tr><td><tt>--keep-links (-K)</tt></td><td>How links are rewritten in saved pages. The numbering is inverted from what you might guess: bare <tt>-K</tt> keeps <b>absolute</b> URLs, and <tt>-K0</tt> is the <b>relative</b> default. <tt>-K3</tt> keeps absolute URIs, <tt>-K4</tt> keeps the original links.</td></tr>
   <tr><td><tt>--replace-external (-x), --generate-errors (-o)</tt></td><td>Replace external links with an error page, and generate an error page for links that failed.</td></tr>
   <tr><td><tt>--preserve (-%p), --disable-passwords (-%x)</tt></td><td>Leave HTML untouched (no rewriting), and strip passwords out of saved links.</td></tr>
@@ -338,7 +296,7 @@ server), and obeys robots. Plenty of sites filter exactly that profile. These
 options control what HTTrack says about itself.</p>
 
 <table class="tblRegular tableWidth" border="0">
-  <tr class="tblHeaderColor"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
+  <tr class="head"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
   <tr><td><tt>--user-agent (-F)</tt></td><td>The <tt>User-Agent</tt>. Set a browser string to get past crawler blocks; <tt>--user-agent ""</tt> sends none.</td></tr>
   <tr><td><tt>--referer (-%R), --from (-%E), --language (-%l), --accept (-%a)</tt></td><td>Referer, From, Accept-Language and Accept headers.</td></tr>
   <tr><td><tt>--headers (-%X)</tt></td><td>Add raw header lines to every request.</td></tr>
@@ -369,7 +327,7 @@ across links at the same time.</p>
 <h3 id="proxy">8. Proxy and network</h3>
 
 <table class="tblRegular tableWidth" border="0">
-  <tr class="tblHeaderColor"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
+  <tr class="head"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
   <tr><td><tt>--proxy (-P)</tt></td><td>Route through a proxy. HTTP, SOCKS5 and CONNECT are supported: <tt>-P host:8080</tt>, <tt>-P socks5://host:1080</tt>, <tt>-P connect://host:443</tt>, with optional <tt>user:pass@</tt>.</td></tr>
   <tr><td><tt>--httpproxy-ftp (-%f)</tt></td><td>Send FTP requests through the HTTP proxy.</td></tr>
   <tr><td><tt>--protocol (-@i)</tt></td><td>Prefer IPv4 or IPv6.</td></tr>
@@ -392,7 +350,7 @@ updating possible. It is not a size-limited scratch area you can delete: throw i
 away and you lose the ability to continue or update the mirror.</p>
 
 <table class="tblRegular tableWidth" border="0">
-  <tr class="tblHeaderColor"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
+  <tr class="head"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
   <tr><td><tt>--continue</tt></td><td>Carry on an interrupted mirror, trusting the cache: it does not re-check pages already stored.</td></tr>
   <tr><td><tt>--update</tt></td><td>Re-run the mirror, revalidating each page with the server (If-Modified-Since / If-None-Match) and downloading only what changed.</td></tr>
   <tr><td><tt>--purge-old=0 (-X0)</tt></td><td>Do not purge. By default an update deletes local files that are no longer part of the mirror; <tt>--purge-old=0</tt> keeps them.</td></tr>
@@ -415,7 +373,7 @@ dynamic pages to look "changed" on every run. See the
 mirror behavior and expose the engine.</p>
 
 <table class="tblRegular tableWidth" border="0">
-  <tr class="tblHeaderColor"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
+  <tr class="head"><td><b>Option</b></td><td><b>What it controls</b></td></tr>
   <tr><td><tt>--get URL</tt></td><td>Fetch a single file and stop. Cache, index, depth, cookies and robots are all off for this mode.</td></tr>
   <tr><td><tt>--spider --testlinks --skeleton</tt></td><td>Scan without saving, test links at depth 1, or keep HTML only. Handy for checking a site before a real crawl.</td></tr>
   <tr><td><tt>--userdef-cmd (-V)</tt></td><td>Run a shell command on each downloaded file; <tt>$0</tt> is the file path. Good for on-the-fly processing.</td></tr>
@@ -540,24 +498,14 @@ all disabled.</small></p>
 <a href="cache.html">cache</a>; for the change report, see
 <a href="changes.html">changes</a>.</p>
 
-<!-- ==================== Start epilogue ==================== -->
-		</td>
-		</tr>
-		</table>
-	</td>
-	</tr>
-	</table>
-</td>
-</tr>
-</table>
+<!-- doc-chrome:bottom -->
+</main>
+</div>
 
-<table width="76%" border="0" align="center" valign="bottom" cellspacing="0" cellpadding="0">
-	<tr>
-	<td id="footer"><small>&copy; 1998-2026 Xavier Roche & other contributors - Web Design: Leto Kauler.</small></td>
-	</tr>
-</table>
+<dialog id="zoom" aria-label="Enlarged image"><img src="" alt=""></dialog>
+
+<footer>&copy; 1998-2026 Xavier Roche &amp; other contributors - Web Design: Leto Kauler.</footer>
+<!-- /doc-chrome:bottom -->
 
 </body>
-
 </html>
-

html/contact.html

@@ -1,120 +1,75 @@
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
-
+<!DOCTYPE html>
+<html lang="en">
 <head>
-	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
-	<meta name="description" content="HTTrack is an easy-to-use website mirror utility. It allows you to download a World Wide website from the Internet to a local directory,building recursively all structures, getting html, images, and other files from the server to your computer. Links are rebuiltrelatively so that you can freely browse to the local site (works with any browser). You can mirror several sites together so that you can jump from one toanother. You can, also, update an existing mirror site, or resume an interrupted download. The robot is fully configurable, with an integrated help" />
-	<meta name="keywords" content="httrack, HTTRACK, HTTrack, winhttrack, WINHTTRACK, WinHTTrack, offline browser, web mirror utility, aspirateur web, surf offline, web capture, www mirror utility, browse offline, local  site builder, website mirroring, aspirateur www, internet grabber, capture de site web, internet tool, hors connexion, unix, dos, windows 95, windows 98, solaris, ibm580, AIX 4.0, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
-	<title>HTTrack Website Copier - Offline Browser</title>
-
-    <script language="javascript">
-    <!--
-    function FOS(host,nom,info) {
-      var s;
-      if (info == "") info=nom+"@"+host;
-      s="mail";
-      document.write("<a href='"+s+"to:"+nom+"@"+host+"'>"+info+"</a>");
-    }
-    // -->
-    </script>
-
-	<style type="text/css">
-	<!--
-
-body {
-	margin: 0;  padding: 0;  margin-bottom: 15px;  margin-top: 8px;
-	background: #77b;
-}
-body, td {
-	font: 14px "Trebuchet MS", Verdana, Arial, Helvetica, sans-serif;
-	}
-
-#subTitle {
-	background: #000;  color: #fff;  padding: 4px;  font-weight: bold; 
-	}
-
-#siteNavigation a, #siteNavigation .current {
-	font-weight: bold;  color: #448;
-	}
-#siteNavigation a:link    { text-decoration: none; }
-#siteNavigation a:visited { text-decoration: none; }
-
-#siteNavigation .current { background-color: #ccd; }
-
-#siteNavigation a:hover   { text-decoration: none;  background-color: #fff;  color: #000; }
-#siteNavigation a:active  { text-decoration: none;  background-color: #ccc; }
-
-
-a:link    { text-decoration: underline;  color: #00f; }
-a:visited { text-decoration: underline;  color: #000; }
-a:hover   { text-decoration: underline;  color: #c00; }
-a:active  { text-decoration: underline; }
-
-#pageContent {
-	clear: both;
-	border-bottom: 6px solid #000;
-	padding: 10px;  padding-top: 20px;
-	line-height: 1.65em;
-	background-image: url(images/bg_rings.gif);
-	background-repeat: no-repeat;
-	background-position: top right;
-	}
-
-#pageContent, #siteNavigation {
-	background-color: #ccd;
-	}
-
-
-.imgLeft  { float: left;   margin-right: 10px;  margin-bottom: 10px; }
-.imgRight { float: right;  margin-left: 10px;   margin-bottom: 10px; }
-
-hr { height: 1px;  color: #000;  background-color: #000;  margin-bottom: 15px; }
-
-h1 { margin: 0;  font-weight: bold;  font-size: 2em; }
-h2 { margin: 0;  font-weight: bold;  font-size: 1.6em; }
-h3 { margin: 0;  font-weight: bold;  font-size: 1.3em; }
-h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
-
-.blak { background-color: #000; }
-.hide { display: none; }
-.tableWidth { min-width: 400px; }
-
-.tblRegular       { border-collapse: collapse; }
-.tblRegular td    { padding: 6px;  background-image: url(fade.gif);  border: 2px solid #99c; }
-.tblHeaderColor, .tblHeaderColor td { background: #99c; }
-.tblNoBorder td   { border: 0; }
-
-
-// -->
-</style>
-
+<!-- doc-chrome:head -->
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<meta name="description" content="How to reach the HTTrack project, and who contributed to it.">
+<link rel="stylesheet" href="doc.css">
+<script src="doc.js" defer></script>
+<!-- /doc-chrome:head -->
+<title>Contact and credits</title>
+<script language="javascript">
+    <!--
+    function FOS(host,nom,info) {
+      var s;
+      if (info == "") info=nom+"@"+host;
+      s="mail";
+      document.write("<a href='"+s+"to:"+nom+"@"+host+"'>"+info+"</a>");
+    }
+    // -->
+    </script>
 </head>
+<body>
 
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-	<tr>
-	<td><img src="images/header_title_4.gif" width="400" height="34" alt="HTTrack Website Copier" title="" border="0" id="title" /></td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="3" class="tableWidth">
-	<tr>
-	<td id="subTitle">Open Source offline browser</td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-<tr class="blak">
-<td>
-	<table width="100%" border="0" align="center" cellspacing="1" cellpadding="0">
-	<tr>
-	<td colspan="6"> 
-		<table width="100%" border="0" align="center" cellspacing="0" cellpadding="10">
-		<tr> 
-		<td id="pageContent"> 
-<!-- ==================== End prologue ==================== -->
+<!-- doc-chrome:top -->
+<a class="skip" href="#main">Skip to content</a>
 
-<h2 align="center"><em>Contact Us!</em></h2>
+<header class="masthead">
+	<img src="images/wordmark.svg" width="400" height="36" alt="HTTrack Website Copier">
+	<div class="tagline">Open Source offline browser</div>
+</header>
+
+<div class="wrap">
+
+<nav class="toc" aria-label="Documentation">
+	<h2>Start here</h2>
+	<ul>
+		<li><a href="guide.html">Interface guide</a></li>
+		<li><a href="faq.html">FAQ and troubleshooting</a></li>
+		<li><a href="abuse.html">Using HTTrack responsibly</a></li>
+	</ul>
+	<h2>Command line</h2>
+	<ul>
+		<li><a href="cmdguide.html">Command-line guide</a></li>
+		<li><a href="httrack.man.html">Option reference</a></li>
+		<li><a href="filters.html">Filter syntax</a></li>
+	</ul>
+	<h2>Developers</h2>
+	<ul>
+		<li><a href="dev.html">Programming</a></li>
+		<li><a href="library.html">libhttrack API</a></li>
+		<li><a href="plug.html">Callbacks</a></li>
+		<li><a href="scripting.html">Scripting</a></li>
+		<li><a href="cache.html">Cache format</a></li>
+		<li><a href="changes.html">Change report format</a></li>
+	</ul>
+	<h2>More</h2>
+	<ul>
+		<li><a href="fcguide.html">Users Guide (3.10)</a></li>
+		<li><a href="contact.html" aria-current="page" class="here">Contact and credits</a></li>
+		<li><a href="index.html">All documentation</a></li>
+	</ul>
+</nav>
+
+<main id="main">
+<!-- /doc-chrome:top -->
+
+<h1>Contact Us!</h1>
 
 <br>
 
-<h3>
+<h3 id="please-visit-our-website">
 <center>
 <a href="http://www.httrack.com/" target="_blank">Please visit our website!</a>
 <br>
@@ -127,94 +82,94 @@ h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
 <pre>
 Informations on this project:
 
-This project has been developed by:
-Xavier Roche (xroche at httrack dot com)
-  for the main engine and Windows interface
-  and maintainer for v2.0 and v3.0
-Yann Philippot (yphilippot at lemel dot fr)
-  past contributor (java binary .class parser)
-David Lawrie (dalawrie at lineone dot net)
-Robert Lagadec (rlagadec at yahoo dot fr)
-  for checking both English & French translations
-Juan Pablo Barrio Lera (University of León)
-  for Spanish translations
-Rainer Klueting (rainer at klueting dot de)
-Bastian Gorke (bastiang at yahoo dot com)
-Rudi Ferrari (Wyando at netcologne dot de)
-Marcus Gaza (MarcusGaza at t-online dot de)
-  for German translations
-Rudi Ferrari (Wyando at netcologne dot de)
-  for Dutch translations
-Lukasz Jokiel (Opole University of Technology, Lukasz dot Jokiel at po dot opole dot pl)
-  for Polish translations
-Rui Fernandes (CANTIC, ruiefe at mail dot malhatlantica dot pt)
-Pedro T dot  Pinheiro (Universidade Nova de Lisboa-FCT, ptiago at mail dot iupi dot pt)
-  for Portuguese translations
-Andrei Iliev (iliev at vitaplus dot ru)
-  for Russian translations
-Witold Krakowski (wtkrak at netscape dot net )
-  for Italian translations
-Jozsef Tamas Herczeg (hdodi at freemail dot hu)
-  for Hungarian translation
-Paulo Neto (company at layout dot com dot br)
-  for Brazilian translation
-Brook Qin (brookqwr at sina dot com) 
-   for simplified Chinese translation
-David Hing Cheong Hung (DAVEHUNG at mtr dot com dot hk)
-Addy Lin (addy1975 at pchome dot com dot tw)
-   for traditional Chinese translation
-Jesper Bramm (bramm at get2net dot dk)
-   for Danish translation
-Tõnu Virma
-   for Estonian translation
-Staffan Ström (staffan at fam-strom dot org)
-   for Swedish translation
-Mehmet Akif Köeoðlu (mak at ttnet dot net dot tr)
-  for Turkish translation
-Aleksandar Savic (aleks at macedonia dot eu dot org)
-  for Macedonian translation
-Takayoshi Nakasikiryo
-  for Japanese translation
-Martin Sereday (sereday at slovanet dot sk)
-  for Slovak translation
-Antonín Matìjèík (matejcik at volny dot cz)
-  for Czech translation
-Andrij Shevchuk (http://programy dot com dot ua)
-  for Ukrainian translation
-Tobias "Spug" Langhoff (spug_enigma at hotmail dot com)
-  for Norwegian translation
-Jadran Rudeciur (jrudec at email dot si)
-  for Slovenian translation
-Alin Gheorghe Miron (miron dot alin at personal dot ro)
-  for Romanian translation
-Michael Papadakis (mikepap at freemail dot gr)
-  for Greek translation
-
-Thanks to:
-Leto Kauler (molotov at tasmail dot com)
-  for the site/logos design
-
-Special Thanks to:
-Patrick Ducrot & Daniel Carré (ENSI of Caen)
-  for their initial support
-Fred Cohen (fc at all dot net)
-  for HTTrack user's guide
-
-Greetings to:
-Christian Marillat (marillat dot christian at wanadoo dot fr)
-  for autoconf compliance and  .deb package
-Jean-loup Gailly from gzip dot org
-  for the help provided with Zlib
-Eric A dot  Young (eay at cryptsoft dot com)
-  for SSL cryptographic material (OpenSSL)
-
-Russ Freeman from gipsymedia
-  for hints on DLL dynamic load
-Paul DiLascia
-  for helping to fix problems with CHtmlView
-ISMRA/Ensi of Caen 
-  for their initial support
- .. and all users that are using and supporting HTTrack!
+This project has been developed by:
+Xavier Roche (xroche at httrack dot com)
+  for the main engine and Windows interface
+  and maintainer for v2.0 and v3.0
+Yann Philippot (yphilippot at lemel dot fr)
+  past contributor (java binary .class parser)
+David Lawrie (dalawrie at lineone dot net)
+Robert Lagadec (rlagadec at yahoo dot fr)
+  for checking both English & French translations
+Juan Pablo Barrio Lera (University of León)
+  for Spanish translations
+Rainer Klueting (rainer at klueting dot de)
+Bastian Gorke (bastiang at yahoo dot com)
+Rudi Ferrari (Wyando at netcologne dot de)
+Marcus Gaza (MarcusGaza at t-online dot de)
+  for German translations
+Rudi Ferrari (Wyando at netcologne dot de)
+  for Dutch translations
+Lukasz Jokiel (Opole University of Technology, Lukasz dot Jokiel at po dot opole dot pl)
+  for Polish translations
+Rui Fernandes (CANTIC, ruiefe at mail dot malhatlantica dot pt)
+Pedro T dot  Pinheiro (Universidade Nova de Lisboa-FCT, ptiago at mail dot iupi dot pt)
+  for Portuguese translations
+Andrei Iliev (iliev at vitaplus dot ru)
+  for Russian translations
+Witold Krakowski (wtkrak at netscape dot net )
+  for Italian translations
+Jozsef Tamas Herczeg (hdodi at freemail dot hu)
+  for Hungarian translation
+Paulo Neto (company at layout dot com dot br)
+  for Brazilian translation
+Brook Qin (brookqwr at sina dot com) 
+   for simplified Chinese translation
+David Hing Cheong Hung (DAVEHUNG at mtr dot com dot hk)
+Addy Lin (addy1975 at pchome dot com dot tw)
+   for traditional Chinese translation
+Jesper Bramm (bramm at get2net dot dk)
+   for Danish translation
+Tõnu Virma
+   for Estonian translation
+Staffan Ström (staffan at fam-strom dot org)
+   for Swedish translation
+Mehmet Akif Köeoðlu (mak at ttnet dot net dot tr)
+  for Turkish translation
+Aleksandar Savic (aleks at macedonia dot eu dot org)
+  for Macedonian translation
+Takayoshi Nakasikiryo
+  for Japanese translation
+Martin Sereday (sereday at slovanet dot sk)
+  for Slovak translation
+Antonín Matìjèík (matejcik at volny dot cz)
+  for Czech translation
+Andrij Shevchuk (http://programy dot com dot ua)
+  for Ukrainian translation
+Tobias "Spug" Langhoff (spug_enigma at hotmail dot com)
+  for Norwegian translation
+Jadran Rudeciur (jrudec at email dot si)
+  for Slovenian translation
+Alin Gheorghe Miron (miron dot alin at personal dot ro)
+  for Romanian translation
+Michael Papadakis (mikepap at freemail dot gr)
+  for Greek translation
+
+Thanks to:
+Leto Kauler (molotov at tasmail dot com)
+  for the site/logos design
+
+Special Thanks to:
+Patrick Ducrot & Daniel Carré (ENSI of Caen)
+  for their initial support
+Fred Cohen (fc at all dot net)
+  for HTTrack user's guide
+
+Greetings to:
+Christian Marillat (marillat dot christian at wanadoo dot fr)
+  for autoconf compliance and  .deb package
+Jean-loup Gailly from gzip dot org
+  for the help provided with Zlib
+Eric A dot  Young (eay at cryptsoft dot com)
+  for SSL cryptographic material (OpenSSL)
+
+Russ Freeman from gipsymedia
+  for hints on DLL dynamic load
+Paul DiLascia
+  for helping to fix problems with CHtmlView
+ISMRA/Ensi of Caen 
+  for their initial support
+ .. and all users that are using and supporting HTTrack!
 
 </pre>
 <hr>
@@ -225,46 +180,35 @@ ISMRA/Ensi of Caen
       You can also contact by email, but due to the large volume of messages, it is impossible
       to always respond (especially for configuration help or other configuration-related
       questions).
-<br>
-
-<script language="javascript">
-<!--
-    FOS('httrack.com','httrack','httrack at httrack dot com (HTTrack project)');
-	document.write('<br>');
-    FOS('httrack.com','roche','roche at httrack dot com (Xavier ROCHE)');
-// -->
-</script>
-<noscript>
-httrack at httrack dot com (HTTrack project)<br>
-roche at httrack dot com (Xavier ROCHE)<br>
-</noscript>
-
-
+<br>
+
+<script language="javascript">
+<!--
+    FOS('httrack.com','httrack','httrack at httrack dot com (HTTrack project)');
+	document.write('<br>');
+    FOS('httrack.com','roche','roche at httrack dot com (Xavier ROCHE)');
+// -->
+</script>
+<noscript>
+httrack at httrack dot com (HTTrack project)<br>
+roche at httrack dot com (Xavier ROCHE)<br>
+</noscript>
+
+
 <br><hr><br>
 <br>
 	This program is covered by the GNU General Public License.<br>
      	HTTrack/HTTrack Website Copier is Copyright (C) 1998-2026 Xavier Roche and other contributors
 <br>
 
-<!-- ==================== Start epilogue ==================== -->
-		</td>
-		</tr>
-		</table>
-	</td>
-	</tr>
-	</table>
-</td>
-</tr>
-</table>
+<!-- doc-chrome:bottom -->
+</main>
+</div>
 
-<table width="76%" border="0" align="center" valign="bottom" cellspacing="0" cellpadding="0">
-	<tr>
-	<td id="footer"><small>&copy; 1998-2026 Xavier Roche & other contributors - Web Design: Leto Kauler.</small></td>
-	</tr>
-</table>
+<dialog id="zoom" aria-label="Enlarged image"><img src="" alt=""></dialog>
+
+<footer>&copy; 1998-2026 Xavier Roche &amp; other contributors - Web Design: Leto Kauler.</footer>
+<!-- /doc-chrome:bottom -->
 
 </body>
-
 </html>
-
-

html/dev.html

@@ -1,161 +1,111 @@
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
-
+<!DOCTYPE html>
+<html lang="en">
 <head>
-	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
-	<meta name="description" content="HTTrack is an easy-to-use website mirror utility. It allows you to download a World Wide website from the Internet to a local directory,building recursively all structures, getting html, images, and other files from the server to your computer. Links are rebuiltrelatively so that you can freely browse to the local site (works with any browser). You can mirror several sites together so that you can jump from one toanother. You can, also, update an existing mirror site, or resume an interrupted download. The robot is fully configurable, with an integrated help" />
-	<meta name="keywords" content="httrack, HTTRACK, HTTrack, winhttrack, WINHTTRACK, WinHTTrack, offline browser, web mirror utility, aspirateur web, surf offline, web capture, www mirror utility, browse offline, local  site builder, website mirroring, aspirateur www, internet grabber, capture de site web, internet tool, hors connexion, unix, dos, windows 95, windows 98, solaris, ibm580, AIX 4.0, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
-	<title>HTTrack Website Copier - Offline Browser</title>
-
-	<style type="text/css">
-	<!--
-
-body {
-	margin: 0;  padding: 0;  margin-bottom: 15px;  margin-top: 8px;
-	background: #77b;
-}
-body, td {
-	font: 14px "Trebuchet MS", Verdana, Arial, Helvetica, sans-serif;
-	}
-
-#subTitle {
-	background: #000;  color: #fff;  padding: 4px;  font-weight: bold; 
-	}
-
-#siteNavigation a, #siteNavigation .current {
-	font-weight: bold;  color: #448;
-	}
-#siteNavigation a:link    { text-decoration: none; }
-#siteNavigation a:visited { text-decoration: none; }
-
-#siteNavigation .current { background-color: #ccd; }
-
-#siteNavigation a:hover   { text-decoration: none;  background-color: #fff;  color: #000; }
-#siteNavigation a:active  { text-decoration: none;  background-color: #ccc; }
-
-
-a:link    { text-decoration: underline;  color: #00f; }
-a:visited { text-decoration: underline;  color: #000; }
-a:hover   { text-decoration: underline;  color: #c00; }
-a:active  { text-decoration: underline; }
-
-#pageContent {
-	clear: both;
-	border-bottom: 6px solid #000;
-	padding: 10px;  padding-top: 20px;
-	line-height: 1.65em;
-	background-image: url(images/bg_rings.gif);
-	background-repeat: no-repeat;
-	background-position: top right;
-	}
-
-#pageContent, #siteNavigation {
-	background-color: #ccd;
-	}
-
-
-.imgLeft  { float: left;   margin-right: 10px;  margin-bottom: 10px; }
-.imgRight { float: right;  margin-left: 10px;   margin-bottom: 10px; }
-
-hr { height: 1px;  color: #000;  background-color: #000;  margin-bottom: 15px; }
-
-h1 { margin: 0;  font-weight: bold;  font-size: 2em; }
-h2 { margin: 0;  font-weight: bold;  font-size: 1.6em; }
-h3 { margin: 0;  font-weight: bold;  font-size: 1.3em; }
-h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
-
-.blak { background-color: #000; }
-.hide { display: none; }
-.tableWidth { min-width: 400px; }
-
-.tblRegular       { border-collapse: collapse; }
-.tblRegular td    { padding: 6px;  background-image: url(fade.gif);  border: 2px solid #99c; }
-.tblHeaderColor, .tblHeaderColor td { background: #99c; }
-.tblNoBorder td   { border: 0; }
-
-
-// -->
-</style>
-
+<!-- doc-chrome:head -->
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<meta name="description" content="Using HTTrack from a script, from the callbacks, or through the libhttrack library.">
+<link rel="stylesheet" href="doc.css">
+<script src="doc.js" defer></script>
+<!-- /doc-chrome:head -->
+<title>Programming with HTTrack</title>
 </head>
+<body>
 
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-	<tr>
-	<td><img src="images/header_title_4.gif" width="400" height="34" alt="HTTrack Website Copier" title="" border="0" id="title" /></td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="3" class="tableWidth">
-	<tr>
-	<td id="subTitle">Open Source offline browser</td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-<tr class="blak">
-<td>
-	<table width="100%" border="0" align="center" cellspacing="1" cellpadding="0">
-	<tr>
-	<td colspan="6"> 
-		<table width="100%" border="0" align="center" cellspacing="0" cellpadding="10">
-		<tr> 
-		<td id="pageContent"> 
-<!-- ==================== End prologue ==================== -->
+<!-- doc-chrome:top -->
+<a class="skip" href="#main">Skip to content</a>
 
-<h2 align="center"><em>HTTrack Programming page</em></h2>
+<header class="masthead">
+	<img src="images/wordmark.svg" width="400" height="36" alt="HTTrack Website Copier">
+	<div class="tagline">Open Source offline browser</div>
+</header>
+
+<div class="wrap">
+
+<nav class="toc" aria-label="Documentation">
+	<h2>On this page</h2>
+	<ul>
+		<li><a href="#programming">Programming</a></li>
+		<li><a href="#technical-references">Technical references</a></li>
+	</ul>
+	<h2>Start here</h2>
+	<ul>
+		<li><a href="guide.html">Interface guide</a></li>
+		<li><a href="faq.html">FAQ and troubleshooting</a></li>
+		<li><a href="abuse.html">Using HTTrack responsibly</a></li>
+	</ul>
+	<h2>Command line</h2>
+	<ul>
+		<li><a href="cmdguide.html">Command-line guide</a></li>
+		<li><a href="httrack.man.html">Option reference</a></li>
+		<li><a href="filters.html">Filter syntax</a></li>
+	</ul>
+	<h2>Developers</h2>
+	<ul>
+		<li><a href="dev.html" aria-current="page" class="here">Programming</a></li>
+		<li><a href="library.html">libhttrack API</a></li>
+		<li><a href="plug.html">Callbacks</a></li>
+		<li><a href="scripting.html">Scripting</a></li>
+		<li><a href="cache.html">Cache format</a></li>
+		<li><a href="changes.html">Change report format</a></li>
+	</ul>
+	<h2>More</h2>
+	<ul>
+		<li><a href="fcguide.html">Users Guide (3.10)</a></li>
+		<li><a href="contact.html">Contact and credits</a></li>
+		<li><a href="index.html">All documentation</a></li>
+	</ul>
+</nav>
+
+<main id="main">
+<!-- /doc-chrome:top -->
+
+<h1>HTTrack Programming page</h1>
 
 <br>
 
-HTTrack can be used as a third-party program in batch files, or as library. 
+HTTrack can be used as a third-party program in batch files, or as library. 
 Depending on your needs, you may look:
 
 <br><br>
-
-<h3>Programming</h3>
 
-<ul>
+<h3 id="programming">Programming</h3>
+
+<ul>
 <li><a href="scripting.html">Simple use: scripting examples using the httrack commandline program</a></li><br>
-You can use tens of options (see <tt>httrack --help</tt>) to control precisely the mirror, and used embedded commands in httrack.
-<br><br>
-<li><a href="plug.html">More complex use: plugging external C functions to the httrack library</a></li><br>
-For advanced functions, you may have to use external C wrappers ; for example when adding advanced crawl features, such as "tuned" filestructure type
-<br><i>Important note: please read the license information of httrack before developing add-ons</i><br />
-See also the page <a href="plug_330.html">for versions prior to 3.41</a>
-<br><br>
-<li><a href="library.html">Advanced use: using the library</a></li><br>
-The library can be used to write graphical GUIs for httrack, or to run mirrors from a program.
-<br><i>Important note: please read the license information of httrack before developing add-ons</i>
-</ul>
-
-<h3>Technical references</h3>
-<ul>
-<li><a href="cache.html">Cache format</a></li><br>
-HTTrack stores original HTML data and references to downloaded files in a cache, located in the hts-cache directory.
-This page describes the HTTrack cache format.
-<li><a href="changes.html">Change report format</a></li><br>
-With --changes, HTTrack writes hts-changes.json describing what the crawl left new, changed, unchanged and gone
-compared to the previous mirror. This page describes that file.
-</ul>
-
+You can use tens of options (see <tt>httrack --help</tt>) to control precisely the mirror, and used embedded commands in httrack.
+<br><br>
+<li><a href="plug.html">More complex use: plugging external C functions to the httrack library</a></li><br>
+For advanced functions, you may have to use external C wrappers ; for example when adding advanced crawl features, such as "tuned" filestructure type
+<br><i>Important note: please read the license information of httrack before developing add-ons</i><br />
+See also the page <a href="plug_330.html">for versions prior to 3.41</a>
+<br><br>
+<li><a href="library.html">Advanced use: using the library</a></li><br>
+The library can be used to write graphical GUIs for httrack, or to run mirrors from a program.
+<br><i>Important note: please read the license information of httrack before developing add-ons</i>
+</ul>
+
+<h3 id="technical-references">Technical references</h3>
+<ul>
+<li><a href="cache.html">Cache format</a></li><br>
+HTTrack stores original HTML data and references to downloaded files in a cache, located in the hts-cache directory.
+This page describes the HTTrack cache format.
+<li><a href="changes.html">Change report format</a></li><br>
+With --changes, HTTrack writes hts-changes.json describing what the crawl left new, changed, unchanged and gone
+compared to the previous mirror. This page describes that file.
+</ul>
+
 
 <br><br>
 
-<!-- ==================== Start epilogue ==================== -->
-		</td>
-		</tr>
-		</table>
-	</td>
-	</tr>
-	</table>
-</td>
-</tr>
-</table>
+<!-- doc-chrome:bottom -->
+</main>
+</div>
 
-<table width="76%" border="0" align="center" valign="bottom" cellspacing="0" cellpadding="0">
-	<tr>
-	<td id="footer"><small>&copy; 1998-2026 Xavier Roche & other contributors - Web Design: Leto Kauler.</small></td>
-	</tr>
-</table>
+<dialog id="zoom" aria-label="Enlarged image"><img src="" alt=""></dialog>
+
+<footer>&copy; 1998-2026 Xavier Roche &amp; other contributors - Web Design: Leto Kauler.</footer>
+<!-- /doc-chrome:bottom -->
 
 </body>
-
 </html>
-
-

html/doc.css

@@ -0,0 +1,349 @@
+/* Shared chrome for the HTTrack documentation pages. Page-specific rules live
+   beside the page (guide.css). Read from disk as often as over http, so
+   everything here has to work from a file:// URL. */
+
+:root {
+	--field: #77b;
+	--panel: #ccd;
+	--accent: #99c;
+	--ink: #111;
+	--ink-soft: #444;
+	--rule: #aab;
+	--link: #00c;
+	--link-hover: #c00;
+	--code-bg: #e8e8f2;
+	--chip: #dde;
+	--shadow: rgba(0, 0, 0, .25);
+}
+
+@media (prefers-color-scheme: dark) {
+	:root {
+		--field: #171a2b;
+		--panel: #22263a;
+		--accent: #3b4066;
+		--ink: #e6e6ee;
+		--ink-soft: #a9adc4;
+		--rule: #3b4066;
+		--link: #9db4ff;
+		--link-hover: #ff9d9d;
+		--code-bg: #14172a;
+		--chip: #2e3350;
+		--shadow: rgba(0, 0, 0, .6);
+	}
+}
+
+* { box-sizing: border-box; }
+
+/* The plain declaration before each var() is what IE11 gets: it drops the
+   custom-property line it cannot parse and keeps the literal above it. */
+body {
+	margin: 0;
+	padding: 0 1rem 3rem;
+	background: #77b;
+	background: var(--field);
+	color: #111;
+	color: var(--ink);
+	font: 1em/1.6 "Trebuchet MS", Verdana, system-ui, -apple-system, "Segoe UI", sans-serif;
+}
+
+/* ---- page frame ---- */
+
+.masthead, .wrap {
+	max-width: 68rem;
+	margin: 0 auto;
+}
+
+.masthead {
+	padding: .6rem 0 0;
+}
+
+/* Take back the whitespace the SVG carries around the letters, restoring the old bitmap's spacing. */
+.masthead img {
+	display: block;
+	max-width: 100%;
+	height: auto;
+	margin: -1.7px 0 -1.1px;
+}
+
+.masthead .tagline {
+	background: #000;
+	color: #fff;
+	font-weight: bold;
+	/* A one-line label has no use for the body's prose leading. */
+	line-height: 1;
+	padding: .3rem .4rem;
+	margin-top: .4rem;
+}
+
+.wrap {
+	background: #ccd;
+	background: var(--panel);
+	border-bottom: 6px solid #000;
+	padding: 1.5rem;
+	/* The rings the 2007 pages carried. Transparent, so it rides on --panel. */
+	background-image: url(images/bg_rings.svg);
+	background-repeat: no-repeat;
+	background-position: top right;
+}
+
+@media (prefers-color-scheme: dark) {
+	/* Rings dropped, not inverted: their lavender is a light-panel tone. */
+	.wrap { background-image: none; }
+
+	/* The wordmark is black on transparent, and all but vanishes on the dark field. */
+	.masthead img { filter: invert(1); }
+}
+
+@media (min-width: 62rem) {
+	.wrap {
+		display: grid;
+		grid-template-columns: 14rem minmax(0, 1fr);
+		gap: 2.5rem;
+		align-items: start;
+	}
+
+	/* The hub is its own navigation, so it spans the full width. */
+	.wrap.solo { display: block; }
+}
+
+footer {
+	max-width: 68rem;
+	margin: .5rem auto 0;
+	color: #eef;
+	font-size: .8em;
+}
+
+@media (prefers-color-scheme: dark) {
+	footer { color: var(--ink-soft); }
+}
+
+/* ---- typography ---- */
+
+h2, h3 { scroll-margin-top: 1rem; }
+
+h1 { font-size: 1.9em; margin: 0 0 .3em; line-height: 1.2; }
+h2 { font-size: 1.45em; margin: 2.5em 0 .5em; padding-bottom: .2em; border-bottom: 2px solid var(--rule); }
+h3 { font-size: 1.15em; margin: 2em 0 .4em; }
+h2:first-child, h1 + h2 { margin-top: 1em; }
+
+p { margin: 0 0 1em; }
+
+a { color: #00c; color: var(--link); }
+a:hover { color: #c00; color: var(--link-hover); }
+
+code, kbd, pre {
+	font-family: ui-monospace, "Cascadia Mono", Consolas, "DejaVu Sans Mono", monospace;
+	font-size: .9em;
+}
+
+code, kbd { background: var(--code-bg); padding: .1em .35em; border-radius: 3px; }
+
+/* Legacy pages carry wide code samples: scroll them, never the page. */
+pre {
+	overflow-x: auto;
+	max-width: 100%;
+	padding: .7rem;
+	background: var(--code-bg);
+	border-left: 3px solid var(--accent);
+}
+
+.lede { font-size: 1.08em; color: var(--ink-soft); }
+
+hr { height: 1px; border: 0; background: var(--rule); margin: 2em 0; }
+
+img { max-width: 100%; height: auto; }
+
+/* Legacy prose carries bare URLs long enough to push a phone sideways. */
+body { overflow-wrap: break-word; }
+
+/* The reference pages carry tables wider than any column: scroll the table, not
+   the page. The guide's own MIME table is narrow and reads better left alone. */
+main table:not(.mime) { display: block; overflow-x: auto; }
+
+/* ---- table of contents ---- */
+
+.toc { font-size: .92em; }
+
+@media (min-width: 62rem) {
+	.toc { position: sticky; top: 1rem; max-height: calc(100vh - 2rem); overflow-y: auto; }
+}
+
+.toc h2 {
+	font-size: .8em;
+	text-transform: uppercase;
+	letter-spacing: .08em;
+	margin: 0 0 .5em;
+	border: 0;
+	color: var(--ink-soft);
+}
+
+.toc ol, .toc ul { list-style: none; margin: 0 0 1.5em; padding: 0; }
+.toc li { margin: 0; }
+
+.toc a {
+	display: block;
+	padding: .2rem .5rem;
+	text-decoration: none;
+	border-left: 3px solid transparent;
+	color: var(--ink);
+}
+
+.toc a:hover { background: var(--accent); }
+.toc a[aria-current="true"] { border-left-color: var(--link); font-weight: bold; }
+.toc .here { font-weight: bold; }
+
+/* ---- callouts ---- */
+
+.note {
+	margin: 0 0 1em;
+	padding: .7rem 1rem;
+	border-left: 4px solid var(--accent);
+	background: var(--chip);
+	font-size: .95em;
+}
+
+.note > :last-child { margin-bottom: 0; }
+
+/* ---- the hub ---- */
+
+.hub {
+	display: grid;
+	gap: 1.5rem;
+	margin: 2rem 0 0;
+	padding: 0;
+	list-style: none;
+}
+
+@media (min-width: 46rem) {
+	.hub { grid-template-columns: repeat(2, minmax(0, 1fr)); }
+}
+
+.hub > li {
+	padding: 1.2rem;
+	background: var(--chip);
+	border-radius: .5rem;
+}
+
+.hub h2 {
+	margin: 0 0 .8em;
+	font-size: 1.1em;
+	text-transform: uppercase;
+	letter-spacing: .06em;
+	border: 0;
+	color: var(--ink-soft);
+}
+
+.hub dl { margin: 0; }
+.hub dt { margin: 0 0 .1em; font-weight: bold; }
+.hub dd { margin: 0 0 1em; font-size: .93em; color: var(--ink-soft); }
+.hub dd:last-child { margin-bottom: 0; }
+
+/* Option names in the glosses are short; without this a browser breaks
+   "--changes" after its hyphens. */
+.hub code { white-space: nowrap; }
+
+.dated { font-weight: normal; font-size: .85em; color: var(--ink-soft); }
+
+/* ---- content tables ---- */
+
+/* The reference pages use bare <table> for their content tables. The guide's MIME
+   table is styled beside the guide and opts out. */
+main table:not(.mime) {
+	border-collapse: collapse;
+	margin: 0 0 1em;
+	font-size: .92em;
+}
+
+main table:not(.mime) td, main table:not(.mime) th {
+	border: 1px solid var(--rule);
+	padding: .3em .6em;
+	text-align: left;
+	vertical-align: top;
+}
+
+main table:not(.mime) th, main table:not(.mime) tr.head td {
+	background: var(--accent);
+	font-weight: bold;
+}
+
+/* ---- screenshots ---- */
+
+figure {
+	margin: 0 0 1.5em;
+	text-align: center;
+}
+
+figure img {
+	border: 1px solid var(--rule);
+	background: #fff;
+	box-shadow: 0 2px 8px var(--shadow);
+	cursor: zoom-in;
+}
+
+figcaption {
+	margin-top: .5em;
+	font-size: .88em;
+	color: var(--ink-soft);
+}
+
+/* Zoom overlay. Closed <dialog> is hidden by the UA, so nothing shows without JS. */
+dialog#zoom {
+	max-width: 96vw;
+	max-height: 96vh;
+	padding: 0;
+	border: 0;
+	background: transparent;
+}
+
+dialog#zoom img {
+	display: block;
+	max-width: 96vw;
+	max-height: 96vh;
+	width: auto;
+	height: auto;
+	cursor: zoom-out;
+}
+
+dialog#zoom::backdrop { background: rgba(0, 0, 0, .8); }
+
+/* ---- filter box (guide options, and the FAQ) ---- */
+
+.filter {
+	display: flex;
+	gap: .5rem;
+	align-items: center;
+	margin: 0 0 1.5rem;
+}
+
+.filter input {
+	flex: 1 1 auto;
+	padding: .5rem .7rem;
+	border: 1px solid var(--rule);
+	border-radius: .3rem;
+	background: var(--panel);
+	color: var(--ink);
+	font: inherit;
+}
+
+.filter output { font-size: .88em; color: var(--ink-soft); white-space: nowrap; }
+
+/* ---- misc ---- */
+
+.skip {
+	position: absolute;
+	left: -9999px;
+}
+
+.skip:focus {
+	left: 1rem;
+	top: 1rem;
+	background: var(--panel);
+	padding: .5rem;
+	z-index: 10;
+}
+
+@media print {
+	body { background: #fff; }
+	.toc, .filter { display: none; }
+	.wrap { display: block; border: 0; }
+}

html/doc.js

@@ -0,0 +1,104 @@
+/* Shared behaviour for the documentation pages: click an image to enlarge it, and
+   mark the section being read in the sidebar. Both are optional, and both are
+   written to fail quietly on an old browser rather than break the page: a Windows 7
+   machine may still open these files in Internet Explorer. */
+
+(function () {
+	"use strict";
+
+	function each(list, fn) {
+		Array.prototype.forEach.call(list, fn);
+	}
+
+	/* ---- click to enlarge ---- */
+
+	function zoomable(node) {
+		while (node && node !== document.body) {
+			if (node.tagName === "IMG" && node.parentNode &&
+				node.parentNode.tagName === "FIGURE") {
+				return node;
+			}
+			node = node.parentNode;
+		}
+		return null;
+	}
+
+	function enlarge() {
+		var zoom = document.getElementById("zoom");
+		if (!zoom || typeof zoom.showModal !== "function") {
+			return;
+		}
+		var target = zoom.getElementsByTagName("img")[0];
+		document.addEventListener("click", function (event) {
+			var img = zoomable(event.target);
+			if (!img) {
+				return;
+			}
+			event.preventDefault();
+			target.src = img.src;
+			target.alt = img.alt;
+			zoom.showModal();
+		});
+		zoom.addEventListener("click", function () {
+			zoom.close();
+		});
+	}
+
+	/* ---- highlight the section being read ---- */
+
+	function highlight() {
+		var marks = [];
+		each(document.querySelectorAll(".toc a, .tabstrip a"), function (a) {
+			if (a.hash && a.hash.length > 1) {
+				marks.push(a);
+			}
+		});
+		if (!marks.length || !window.IntersectionObserver) {
+			return;
+		}
+
+		var byId = {};
+		each(marks, function (a) {
+			var id = a.hash.slice(1);
+			(byId[id] = byId[id] || []).push(a);
+		});
+
+		var visible = {};
+		var observer = new IntersectionObserver(function (entries) {
+			each(entries, function (entry) {
+				visible[entry.target.id] = entry.isIntersecting;
+			});
+			var top = Object.keys(byId).filter(function (id) {
+				return visible[id];
+			})[0];
+			each(marks, function (a) {
+				if (a.getAttribute("aria-current") === "true") {
+					a.removeAttribute("aria-current");
+				}
+			});
+			if (top) {
+				each(byId[top], function (a) {
+					a.setAttribute("aria-current", "true");
+				});
+			}
+		}, { rootMargin: "-10% 0px -70% 0px" });
+
+		Object.keys(byId).forEach(function (id) {
+			var el = document.getElementById(id);
+			if (el) {
+				observer.observe(el);
+			}
+		});
+	}
+
+	function start() {
+		enlarge();
+		highlight();
+	}
+
+	if (document.readyState === "loading") {
+		document.addEventListener("DOMContentLoaded", start);
+	} else {
+		start();
+	}
+})();

html/faq.html

@@ -1,112 +1,76 @@
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
-
+<!DOCTYPE html>
+<html lang="en">
 <head>
-	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
-	<meta name="description" content="HTTrack is an easy-to-use website mirror utility. It allows you to download a World Wide website from the Internet to a local directory,building recursively all structures, getting html, images, and other files from the server to your computer. Links are rebuiltrelatively so that you can freely browse to the local site (works with any browser). You can mirror several sites together so that you can jump from one toanother. You can, also, update an existing mirror site, or resume an interrupted download. The robot is fully configurable, with an integrated help" />
-	<meta name="keywords" content="httrack, HTTRACK, HTTrack, winhttrack, WINHTTRACK, WinHTTrack, offline browser, web mirror utility, aspirateur web, surf offline, web capture, www mirror utility, browse offline, local  site builder, website mirroring, aspirateur www, internet grabber, capture de site web, internet tool, hors connexion, unix, linux, windows, macos, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
-	<title>HTTrack Website Copier - Offline Browser</title>
-
-	<style type="text/css">
-	<!--
-
-body {
-	margin: 0;  padding: 0;  margin-bottom: 15px;  margin-top: 8px;
-	background: #77b;
-}
-body, td {
-	font: 14px "Trebuchet MS", Verdana, Arial, Helvetica, sans-serif;
-	}
-
-#subTitle {
-	background: #000;  color: #fff;  padding: 4px;  font-weight: bold; 
-	}
-
-#siteNavigation a, #siteNavigation .current {
-	font-weight: bold;  color: #448;
-	}
-#siteNavigation a:link    { text-decoration: none; }
-#siteNavigation a:visited { text-decoration: none; }
-
-#siteNavigation .current { background-color: #ccd; }
-
-#siteNavigation a:hover   { text-decoration: none;  background-color: #fff;  color: #000; }
-#siteNavigation a:active  { text-decoration: none;  background-color: #ccc; }
-
-
-a:link    { text-decoration: underline;  color: #00f; }
-a:visited { text-decoration: underline;  color: #000; }
-a:hover   { text-decoration: underline;  color: #c00; }
-a:active  { text-decoration: underline; }
-
-#pageContent {
-	clear: both;
-	border-bottom: 6px solid #000;
-	padding: 10px;  padding-top: 20px;
-	line-height: 1.65em;
-	background-image: url(images/bg_rings.gif);
-	background-repeat: no-repeat;
-	background-position: top right;
-	}
-
-#pageContent, #siteNavigation {
-	background-color: #ccd;
-	}
-
-
-.imgLeft  { float: left;   margin-right: 10px;  margin-bottom: 10px; }
-.imgRight { float: right;  margin-left: 10px;   margin-bottom: 10px; }
-
-hr { height: 1px;  color: #000;  background-color: #000;  margin-bottom: 15px; }
-
-h1 { margin: 0;  font-weight: bold;  font-size: 2em; }
-h2 { margin: 0;  font-weight: bold;  font-size: 1.6em; }
-h3 { margin: 0;  font-weight: bold;  font-size: 1.3em; }
-h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
-
-.blak { background-color: #000; }
-.hide { display: none; }
-.tableWidth { min-width: 400px; }
-
-.tblRegular       { border-collapse: collapse; }
-.tblRegular td    { padding: 6px;  background-image: url(fade.gif);  border: 2px solid #99c; }
-.tblHeaderColor, .tblHeaderColor td { background: #99c; }
-.tblNoBorder td   { border: 0; }
-
-
-// -->
-</style>
-
+<!-- doc-chrome:head -->
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<meta name="description" content="Frequently asked questions about HTTrack, and what to do when a site does not mirror the way you expected.">
+<link rel="stylesheet" href="doc.css">
+<script src="doc.js" defer></script>
+<!-- /doc-chrome:head -->
+<title>HTTrack FAQ and troubleshooting</title>
 </head>
+<body>
 
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-	<tr>
-	<td><img src="images/header_title_4.gif" width="400" height="34" alt="HTTrack Website Copier" title="" border="0" id="title" /></td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="3" class="tableWidth">
-	<tr>
-	<td id="subTitle">Open Source offline browser</td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-<tr class="blak">
-<td>
-	<table width="100%" border="0" align="center" cellspacing="1" cellpadding="0">
-	<tr>
-	<td colspan="6"> 
-		<table width="100%" border="0" align="center" cellspacing="0" cellpadding="10">
-		<tr> 
-		<td id="pageContent"> 
-<!-- ==================== End prologue ==================== -->
+<!-- doc-chrome:top -->
+<a class="skip" href="#main">Skip to content</a>
 
-<h2 align="center"><em>F A Q</em></h2>
+<header class="masthead">
+	<img src="images/wordmark.svg" width="400" height="36" alt="HTTrack Website Copier">
+	<div class="tagline">Open Source offline browser</div>
+</header>
+
+<div class="wrap">
+
+<nav class="toc" aria-label="Documentation">
+	<h2>On this page</h2>
+	<ul>
+		<li><a href="#very-frequently-asked-questions">Very Frequently Asked Questions</a></li>
+		<li><a href="#general-questions">General questions</a></li>
+		<li><a href="#troubleshooting">Troubleshooting</a></li>
+		<li><a href="#questions-concerning-a-mirror">Questions concerning a mirror</a></li>
+		<li><a href="#other-problems">Other problems</a></li>
+	</ul>
+	<h2>Start here</h2>
+	<ul>
+		<li><a href="guide.html">Interface guide</a></li>
+		<li><a href="faq.html" aria-current="page" class="here">FAQ and troubleshooting</a></li>
+		<li><a href="abuse.html">Using HTTrack responsibly</a></li>
+	</ul>
+	<h2>Command line</h2>
+	<ul>
+		<li><a href="cmdguide.html">Command-line guide</a></li>
+		<li><a href="httrack.man.html">Option reference</a></li>
+		<li><a href="filters.html">Filter syntax</a></li>
+	</ul>
+	<h2>Developers</h2>
+	<ul>
+		<li><a href="dev.html">Programming</a></li>
+		<li><a href="library.html">libhttrack API</a></li>
+		<li><a href="plug.html">Callbacks</a></li>
+		<li><a href="scripting.html">Scripting</a></li>
+		<li><a href="cache.html">Cache format</a></li>
+		<li><a href="changes.html">Change report format</a></li>
+	</ul>
+	<h2>More</h2>
+	<ul>
+		<li><a href="fcguide.html">Users Guide (3.10)</a></li>
+		<li><a href="contact.html">Contact and credits</a></li>
+		<li><a href="index.html">All documentation</a></li>
+	</ul>
+</nav>
+
+<main id="main">
+<!-- /doc-chrome:top -->
+
+<h1>F A Q</h1>
 
 <br>
 
 <p><em><br>
 <ul>
 <strong>Tips:</strong>
-<li>In case of troubles/problems during transfer, <b><u><font color="red">first check the hts-log.txt (and hts-err.txt) files to figure out what happened</b></u></font>. These log files report all
+<li>In case of troubles/problems during transfer, <b><u>first check the hts-log.txt (and hts-err.txt) files to figure out what happened</b></u>. These log files report all
 events that may be useful to detect a problem. You can also ajust the debug level of the log files in the option
 </li><li>
 The tutorial written by Fred Cohen is a very good document to read, to understand how to use the engine,
@@ -118,12 +82,12 @@ clear language!
 
 <ul><br>
 
-<h3><b>Very</b> Frequently Asked Questions:<br></h3>
+<h3 id="very-frequently-asked-questions"><b>Very</b> Frequently Asked Questions:<br></h3>
 
 <li><a href="#VF1">HTTrack does not capture all files I want to capture!</a><br></li>
 
 <br>
-<h3>General questions:<br></h3>
+<h3 id="general-questions">General questions:<br></h3>
 
 <li><a href="#QG0">Is there any 'spyware' or 'adware' in this program? Can you prove that there isn't any?</a><br></li>
 
@@ -152,7 +116,7 @@ clear language!
 <li><a href="#QG9">Is there a GUI version available for Linux and Un*x?</a><br></li>
 
 
-<br><h3>Troubleshooting:<br></h3>
+<br><h3 id="troubleshooting">Troubleshooting:<br></h3>
 
 <li><a href="#Q0">Some sites are captured very well, other aren't. Why?</a><br></li>
 
@@ -217,7 +181,7 @@ clear language!
 <li><a href="#QT2">With WinHTTrack, sometimes the minimize in system tray causes a crash!</a><br></li>
 
 
-<h3><br>Questions concerning a mirror:<br></h3></li>
+<h3 id="questions-concerning-a-mirror"><br>Questions concerning a mirror:<br></h3></li>
 
 <li><a href="#Q5">I want to mirror a Web site, but there are some files outside the domain, too. How to retrieve them?</a><br></li>
 
@@ -277,7 +241,7 @@ clear language!
 
 <li><a href="#QM13">How can I grab email addresses in web pages?</a><br></li>
 
-<br><h3>Other problems:<br></h3></a>
+<br><h3 id="other-problems">Other problems:<br></h3></a>
 
 <li><a href="#Q300">My problerm is not listed!</a><br></li>
 
@@ -912,25 +876,14 @@ A: <em>Feel free to <a href="contact.html">contact us</a>!
 
 </em></p><h3><br>
 
-<!-- ==================== Start epilogue ==================== -->
-		</td>
-		</tr>
-		</table>
-	</td>
-	</tr>
-	</table>
-</td>
-</tr>
-</table>
+<!-- doc-chrome:bottom -->
+</main>
+</div>
 
-<table width="76%" border="0" align="center" valign="bottom" cellspacing="0" cellpadding="0">
-	<tr>
-	<td id="footer"><small>&copy; 1998-2026 Xavier Roche & other contributors - Web Design: Leto Kauler.</small></td>
-	</tr>
-</table>
+<dialog id="zoom" aria-label="Enlarged image"><img src="" alt=""></dialog>
+
+<footer>&copy; 1998-2026 Xavier Roche &amp; other contributors - Web Design: Leto Kauler.</footer>
+<!-- /doc-chrome:bottom -->
 
 </body>
-
 </html>
-
-

html/fcguide.html

@@ -1,110 +1,81 @@
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
-
+<!DOCTYPE html>
+<html lang="en">
 <head>
-	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
-	<meta name="description" content="HTTrack is an easy-to-use website mirror utility. It allows you to download a World Wide website from the Internet to a local directory,building recursively all structures, getting html, images, and other files from the server to your computer. Links are rebuiltrelatively so that you can freely browse to the local site (works with any browser). You can mirror several sites together so that you can jump from one toanother. You can, also, update an existing mirror site, or resume an interrupted download. The robot is fully configurable, with an integrated help" />
-	<meta name="keywords" content="httrack, HTTRACK, HTTrack, winhttrack, WINHTTRACK, WinHTTrack, offline browser, web mirror utility, aspirateur web, surf offline, web capture, www mirror utility, browse offline, local  site builder, website mirroring, aspirateur www, internet grabber, capture de site web, internet tool, hors connexion, unix, dos, windows 95, windows 98, solaris, ibm580, AIX 4.0, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
-	<title>HTTrack Website Copier - Offline Browser</title>
-
-	<style type="text/css">
-	<!--
-
-body {
-	margin: 0;  padding: 0;  margin-bottom: 15px;  margin-top: 8px;
-	background: #77b;
-}
-body, td {
-	font: 14px "Trebuchet MS", Verdana, Arial, Helvetica, sans-serif;
-	}
-
-#subTitle {
-	background: #000;  color: #fff;  padding: 4px;  font-weight: bold; 
-	}
-
-#siteNavigation a, #siteNavigation .current {
-	font-weight: bold;  color: #448;
-	}
-#siteNavigation a:link    { text-decoration: none; }
-#siteNavigation a:visited { text-decoration: none; }
-
-#siteNavigation .current { background-color: #ccd; }
-
-#siteNavigation a:hover   { text-decoration: none;  background-color: #fff;  color: #000; }
-#siteNavigation a:active  { text-decoration: none;  background-color: #ccc; }
-
-
-a:link    { text-decoration: underline;  color: #00f; }
-a:visited { text-decoration: underline;  color: #000; }
-a:hover   { text-decoration: underline;  color: #c00; }
-a:active  { text-decoration: underline; }
-
-#pageContent {
-	clear: both;
-	border-bottom: 6px solid #000;
-	padding: 10px;  padding-top: 20px;
-	line-height: 1.65em;
-	background-image: url(images/bg_rings.gif);
-	background-repeat: no-repeat;
-	background-position: top right;
-	}
-
-#pageContent, #siteNavigation {
-	background-color: #ccd;
-	}
-
-
-.imgLeft  { float: left;   margin-right: 10px;  margin-bottom: 10px; }
-.imgRight { float: right;  margin-left: 10px;   margin-bottom: 10px; }
-
-hr { height: 1px;  color: #000;  background-color: #000;  margin-bottom: 15px; }
-
-h1 { margin: 0;  font-weight: bold;  font-size: 2em; }
-h2 { margin: 0;  font-weight: bold;  font-size: 1.6em; }
-h3 { margin: 0;  font-weight: bold;  font-size: 1.3em; }
-h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
-
-.blak { background-color: #000; }
-.hide { display: none; }
-.tableWidth { min-width: 400px; }
-
-.tblRegular       { border-collapse: collapse; }
-.tblRegular td    { padding: 6px;  background-image: url(fade.gif);  border: 2px solid #99c; }
-.tblHeaderColor, .tblHeaderColor td { background: #99c; }
-.tblNoBorder td   { border: 0; }
-
-
-// -->
-</style>
-
+<!-- doc-chrome:head -->
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<meta name="description" content="Fred Cohen's HTTrack Users Guide, written for release 3.10.">
+<link rel="stylesheet" href="doc.css">
+<script src="doc.js" defer></script>
+<!-- /doc-chrome:head -->
+<title>HTTrack Users Guide, by Fred Cohen (3.10)</title>
 </head>
+<body>
 
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-	<tr>
-	<td><img src="images/header_title_4.gif" width="400" height="34" alt="HTTrack Website Copier" title="" border="0" id="title" /></td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="3" class="tableWidth">
-	<tr>
-	<td id="subTitle">Open Source offline browser</td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-<tr class="blak">
-<td>
-	<table width="100%" border="0" align="center" cellspacing="1" cellpadding="0">
-	<tr>
-	<td colspan="6"> 
-		<table width="100%" border="0" align="center" cellspacing="0" cellpadding="10">
-		<tr> 
-		<td id="pageContent"> 
-<!-- ==================== End prologue ==================== -->
+<!-- doc-chrome:top -->
+<a class="skip" href="#main">Skip to content</a>
+
+<header class="masthead">
+	<img src="images/wordmark.svg" width="400" height="36" alt="HTTrack Website Copier">
+	<div class="tagline">Open Source offline browser</div>
+</header>
+
+<div class="wrap">
+
+<nav class="toc" aria-label="Documentation">
+	<h2>On this page</h2>
+	<ul>
+		<li><a href="#background-and-introduction">Background and Introduction</a></li>
+		<li><a href="#basics">Basics</a></li>
+		<li><a href="#syntax">Syntax</a></li>
+		<li><a href="#a-thorough-going-over">A Thorough Going Over</a></li>
+		<li><a href="#filters">Filters</a></li>
+		<li><a href="#user-authentication-protocols">User Authentication Protocols</a></li>
+		<li><a href="#httrackrc">.httrackrc</a></li>
+		<li><a href="#release-notes">Release Notes</a></li>
+		<li><a href="#some-more-examples">Some More Examples</a></li>
+		<li><a href="#general-questions">General questions</a></li>
+		<li><a href="#troubleshooting">Troubleshooting</a></li>
+		<li><a href="#questions-concerning-a-mirror">Questions concerning a mirror</a></li>
+	</ul>
+	<h2>Start here</h2>
+	<ul>
+		<li><a href="guide.html">Interface guide</a></li>
+		<li><a href="faq.html">FAQ and troubleshooting</a></li>
+		<li><a href="abuse.html">Using HTTrack responsibly</a></li>
+	</ul>
+	<h2>Command line</h2>
+	<ul>
+		<li><a href="cmdguide.html">Command-line guide</a></li>
+		<li><a href="httrack.man.html">Option reference</a></li>
+		<li><a href="filters.html">Filter syntax</a></li>
+	</ul>
+	<h2>Developers</h2>
+	<ul>
+		<li><a href="dev.html">Programming</a></li>
+		<li><a href="library.html">libhttrack API</a></li>
+		<li><a href="plug.html">Callbacks</a></li>
+		<li><a href="scripting.html">Scripting</a></li>
+		<li><a href="cache.html">Cache format</a></li>
+		<li><a href="changes.html">Change report format</a></li>
+	</ul>
+	<h2>More</h2>
+	<ul>
+		<li><a href="fcguide.html" aria-current="page" class="here">Users Guide (3.10)</a></li>
+		<li><a href="contact.html">Contact and credits</a></li>
+		<li><a href="index.html">All documentation</a></li>
+	</ul>
+</nav>
+
+<main id="main">
+<!-- /doc-chrome:top -->
 
 <center><h1> Httrack Users Guide (3.10)</h1>
 By Fred Cohen </center>
 
 <hr>
 
-<h2> Background and Introduction </h2>
+<h2 id="background-and-introduction"> Background and Introduction </h2>
 
 <p align=justify> I started using httrack in mid-2000 and found it to be
 an excellent tool for imaging web sites.  Various words are used to
@@ -125,7 +96,7 @@ assistance from the authors I volunteered to write a users manual for
 httrack - and here it is.  I hope it gets the job done.
 
 <hr>
-<h2> Basics </h2>
+<h2 id="basics"> Basics </h2>
 
 <p align=justify> Httrack is a program that gets information from the
 Internet, looks for pointers to other information, gets that
@@ -237,7 +208,7 @@ Build options:
   x  replace external html links by error pages (--replace-external)
  %x  do not include any password for external password protected websites (%x0 include) (--no-passwords)
  %q *include query string for local files (useless, for information purpose only) (%q0 don't include) (--include-query-string)
-  o *generate output html file in case of error (404..) (o0 don't generate) (--generate-errors)
+  o *save the server's error pages (404..) (o0 discard them) (--generate-errors)
   X *purge old files after update (X0 keep delete) (--purge-old[=N])
 
 Spider options:
@@ -385,7 +356,7 @@ the rest of us, I will now go through this listing one item at a time
 with examples... I will be here a while...
 
 <hr>
-<h2> Syntax </h2>
+<h2 id="syntax"> Syntax </h2>
 
 <pre><b><i>httrack &lt;URLs&gt; [-option] [+&lt;FILTERs&gt;] [-&lt;FILTERs&gt;] </i></b></pre>
 
@@ -413,7 +384,7 @@ site. Specifically, the defauls are:
   NN  name conversion type (0 *original structure, 1+: see below)
   LN  long names (L1 *long names / L0 8-3 conversion)
   K   keep original links (e.g. http://www.adr/link) (K0 *relative link)
-  o *generate output html file in case of error (404..) (o0 don't generate)
+  o *save the server's error pages (404..) (o0 discard them)
   X *purge old files after update (X0 keep delete)
   bN  accept cookies in cookies.txt (0=do not accept,* 1=accept)
   u check document type if unknown (cgi,asp..) (u0 don't check, * u1 check but /, u2 check always)
@@ -473,11 +444,11 @@ store them with the same names used on the web site.
 URLs within this web site are adjusted to point to the files in the
 mirror.
 
-<pre><b><i>  o *generate output html file in case of error (404..) (o0 don't generate) </i></b></pre>
+<pre><b><i>  o *save the server's error pages (404..) (o0 discard them) </i></b></pre>
 
-<p align=justify> IF there are errors in downloading, create a file that
-indicates that the URL was not found.  This makes browsing go a lot
-smoother.
+<p align=justify> IF a page cannot be downloaded, the error page the
+server sent is saved in its place, so a broken link still lands on the
+site's own 'not found' page.  This makes browsing go a lot smoother.
 
 <pre><b><i>  X *purge old files after update (X0 keep delete) </i></b></pre>
 
@@ -571,7 +542,7 @@ www.all.net/bob/deeper/).
 
 <hr>
 
-<h2> A Thorough Going Over </h2>
+<h2 id="a-thorough-going-over"> A Thorough Going Over </h2>
 
 <p align=justify> Now that you have an introduction, it's time for a
 more though coverage.  This is where I go through each of the options
@@ -1011,7 +982,7 @@ Build options:
   LN  long names (L1 *long names / L0 8-3 conversion)
   K   keep original links (e.g. http://www.adr/link) (K0 *relative link)
   x   replace external html links by error pages
-  o *generate output html file in case of error (404..) (o0 don't generate)
+  o *save the server's error pages (404..) (o0 discard them)
   X *purge old files after update (X0 keep delete)
   %x  do not include any password for external password protected websites (%x0 include) (--no-passwords)
   %q *include query string for local files (information only) (%q0 don't include) (--include-query-string)
@@ -1118,9 +1089,9 @@ deactivated byt his process.
 httrack http://www.shoesizes.com -O /tmp/shoesizes -x
 </i></b></pre>
 
-<p align=justify> This option prevents the generation of '404' error
-files to replace files that were not found even though there were URLs
-pointing to them.  It is useful for saving space as well as eliminating
+<p align=justify> This option keeps the server's '404' error pages out
+of the mirror, even though there were URLs pointing to the missing
+files.  It is useful for saving space as well as eliminating
 unnecessary files in operations where a working web site is not the
 desired result. 
 
@@ -1930,7 +1901,7 @@ as -%h).
 
 <hr>
 
-<h2> Filters </h2>
+<h2 id="filters"> Filters </h2>
 
 <p align=justify> Filters are normally placed at the end of the command
 line, but can be intermixed with other command line options if desired,
@@ -2079,7 +2050,7 @@ generated automatically using the interface)
 
 <hr>
 
-<h2> User Authentication Protocols </h2>
+<h2 id="user-authentication-protocols"> User Authentication Protocols </h2>
 
 <p align=justify> Smoe servers require user ID and password information
 in order to gain access.  In this example, the user ID smith with
@@ -2096,7 +2067,7 @@ capability is being provided through th URL capture features
 
 <hr>
 
-<h2> .httrackrc </h2>
+<h2 id="httrackrc"> .httrackrc </h2>
 
 <p align=justify> A file called '.httrackrc' can be placed in the
 current directory, or if not found there, in the home directory, to
@@ -2185,7 +2156,7 @@ added by the .httrackrc
 
 <hr>
 
-<h2> Release Notes </h2>
+<h2 id="release-notes"> Release Notes </h2>
 
 <p align=justify> Some things change between releases.  Here are some
 recent changes in httrack that may affect some of these options:
@@ -2223,7 +2194,7 @@ collision for large numbers of files.
 
 <hr>
 
-<h2> Some More Examples </h2>
+<h2 id="some-more-examples"> Some More Examples </h2>
 
 <p align=justify> Here are some examples of special purpose httrack
 command lines that might be useful for your situation.
@@ -2275,7 +2246,7 @@ httrack "http://www.somesite.com/~library/thing/thingmain.htm" -O /tmp/thing -R5
 
 <hr>
 
-<h2>General questions:</h2>
+<h2 id="general-questions">General questions:</h2>
 
 <p align=justify><b>Q:  The install is not working on NT without administrator rights! </b>
 
@@ -2327,7 +2298,7 @@ Un*x? </b>
 <p align=justify> A: No.  Unfortunately, we do not have enough time for
 that - if you want to help us, please write one!
 
-<hr><h2> Troubleshooting:</h2>
+<hr><h2 id="troubleshooting"> Troubleshooting:</h2>
 
 <p align=justify><b>Q: Only the first page is caught.  What's wrong?</b>
 </br> A: First, check the <b>hts-err.txt</b> error log file - this can
@@ -2509,7 +2480,7 @@ considered as "newer" than the local ones..  even if there are
 identical! Unfortunately, there is no possibility to avoid this problem,
 which is strongly linked with the server abilities. 
 
-<p align=justify> <hr><h2> Questions concerning a mirror: </h2>
+<p align=justify> <hr><h2 id="questions-concerning-a-mirror"> Questions concerning a mirror: </h2>
 
 <p align=justify> <p align=justify><b>Q: I want to mirror a Web site,
 but there are some files outside the domain, too.  How to retrieve them?
@@ -2693,25 +2664,14 @@ too many sessions, or your system may be unable to provide the necessary
 resources.  Try redusing this number - for example using the -c2 options
 for only 2 simultaneous sesions.
 
-<!-- ==================== Start epilogue ==================== -->
-		</td>
-		</tr>
-		</table>
-	</td>
-	</tr>
-	</table>
-</td>
-</tr>
-</table>
+<!-- doc-chrome:bottom -->
+</main>
+</div>
 
-<table width="76%" border="0" align="center" valign="bottom" cellspacing="0" cellpadding="0">
-	<tr>
-	<td id="footer"><small>&copy; 2007 Xavier Roche & other contributors - Web Design: Leto Kauler.</small></td>
-	</tr>
-</table>
+<dialog id="zoom" aria-label="Enlarged image"><img src="" alt=""></dialog>
+
+<footer>&copy; 1998-2026 Xavier Roche &amp; other contributors - Web Design: Leto Kauler.</footer>
+<!-- /doc-chrome:bottom -->
 
 </body>
-
 </html>
-
-

html/filters.html

@@ -1,105 +1,61 @@
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
-
+<!DOCTYPE html>
+<html lang="en">
 <head>
-	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
-	<meta name="description" content="HTTrack is an easy-to-use website mirror utility. It allows you to download a World Wide website from the Internet to a local directory,building recursively all structures, getting html, images, and other files from the server to your computer. Links are rebuiltrelatively so that you can freely browse to the local site (works with any browser). You can mirror several sites together so that you can jump from one toanother. You can, also, update an existing mirror site, or resume an interrupted download. The robot is fully configurable, with an integrated help" />
-	<meta name="keywords" content="httrack, HTTRACK, HTTrack, winhttrack, WINHTTRACK, WinHTTrack, offline browser, web mirror utility, aspirateur web, surf offline, web capture, www mirror utility, browse offline, local  site builder, website mirroring, aspirateur www, internet grabber, capture de site web, internet tool, hors connexion, unix, dos, windows 95, windows 98, solaris, ibm580, AIX 4.0, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
-	<title>HTTrack Website Copier - Offline Browser</title>
-
-	<style type="text/css">
-	<!--
-
-body {
-	margin: 0;  padding: 0;  margin-bottom: 15px;  margin-top: 8px;
-	background: #77b;
-}
-body, td {
-	font: 14px "Trebuchet MS", Verdana, Arial, Helvetica, sans-serif;
-	}
-
-#subTitle {
-	background: #000;  color: #fff;  padding: 4px;  font-weight: bold; 
-	}
-
-#siteNavigation a, #siteNavigation .current {
-	font-weight: bold;  color: #448;
-	}
-#siteNavigation a:link    { text-decoration: none; }
-#siteNavigation a:visited { text-decoration: none; }
-
-#siteNavigation .current { background-color: #ccd; }
-
-#siteNavigation a:hover   { text-decoration: none;  background-color: #fff;  color: #000; }
-#siteNavigation a:active  { text-decoration: none;  background-color: #ccc; }
-
-
-a:link    { text-decoration: underline;  color: #00f; }
-a:visited { text-decoration: underline;  color: #000; }
-a:hover   { text-decoration: underline;  color: #c00; }
-a:active  { text-decoration: underline; }
-
-#pageContent {
-	clear: both;
-	border-bottom: 6px solid #000;
-	padding: 10px;  padding-top: 20px;
-	line-height: 1.65em;
-	background-image: url(images/bg_rings.gif);
-	background-repeat: no-repeat;
-	background-position: top right;
-	}
-
-#pageContent, #siteNavigation {
-	background-color: #ccd;
-	}
-
-
-.imgLeft  { float: left;   margin-right: 10px;  margin-bottom: 10px; }
-.imgRight { float: right;  margin-left: 10px;   margin-bottom: 10px; }
-
-hr { height: 1px;  color: #000;  background-color: #000;  margin-bottom: 15px; }
-
-h1 { margin: 0;  font-weight: bold;  font-size: 2em; }
-h2 { margin: 0;  font-weight: bold;  font-size: 1.6em; }
-h3 { margin: 0;  font-weight: bold;  font-size: 1.3em; }
-h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
-
-.blak { background-color: #000; }
-.hide { display: none; }
-.tableWidth { min-width: 400px; }
-
-.tblRegular       { border-collapse: collapse; }
-.tblRegular td    { padding: 6px;  background-image: url(fade.gif);  border: 2px solid #99c; }
-.tblHeaderColor, .tblHeaderColor td { background: #99c; }
-.tblNoBorder td   { border: 0; }
-
-
-// -->
-</style>
-
+<!-- doc-chrome:head -->
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<meta name="description" content="HTTrack filter syntax: wildcards, and the size and MIME-type forms of a scan rule.">
+<link rel="stylesheet" href="doc.css">
+<script src="doc.js" defer></script>
+<!-- /doc-chrome:head -->
+<title>HTTrack filter syntax</title>
 </head>
+<body>
 
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-	<tr>
-	<td><img src="images/header_title_4.gif" width="400" height="34" alt="HTTrack Website Copier" title="" border="0" id="title" /></td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="3" class="tableWidth">
-	<tr>
-	<td id="subTitle">Open Source offline browser</td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-<tr class="blak">
-<td>
-	<table width="100%" border="0" align="center" cellspacing="1" cellpadding="0">
-	<tr>
-	<td colspan="6"> 
-		<table width="100%" border="0" align="center" cellspacing="0" cellpadding="10">
-		<tr> 
-		<td id="pageContent"> 
-<!-- ==================== End prologue ==================== -->
+<!-- doc-chrome:top -->
+<a class="skip" href="#main">Skip to content</a>
 
-<h2 align="center"><em>Filters: Advanced</em></h2>
+<header class="masthead">
+	<img src="images/wordmark.svg" width="400" height="36" alt="HTTrack Website Copier">
+	<div class="tagline">Open Source offline browser</div>
+</header>
+
+<div class="wrap">
+
+<nav class="toc" aria-label="Documentation">
+	<h2>Start here</h2>
+	<ul>
+		<li><a href="guide.html">Interface guide</a></li>
+		<li><a href="faq.html">FAQ and troubleshooting</a></li>
+		<li><a href="abuse.html">Using HTTrack responsibly</a></li>
+	</ul>
+	<h2>Command line</h2>
+	<ul>
+		<li><a href="cmdguide.html">Command-line guide</a></li>
+		<li><a href="httrack.man.html">Option reference</a></li>
+		<li><a href="filters.html" aria-current="page" class="here">Filter syntax</a></li>
+	</ul>
+	<h2>Developers</h2>
+	<ul>
+		<li><a href="dev.html">Programming</a></li>
+		<li><a href="library.html">libhttrack API</a></li>
+		<li><a href="plug.html">Callbacks</a></li>
+		<li><a href="scripting.html">Scripting</a></li>
+		<li><a href="cache.html">Cache format</a></li>
+		<li><a href="changes.html">Change report format</a></li>
+	</ul>
+	<h2>More</h2>
+	<ul>
+		<li><a href="fcguide.html">Users Guide (3.10)</a></li>
+		<li><a href="contact.html">Contact and credits</a></li>
+		<li><a href="index.html">All documentation</a></li>
+	</ul>
+</nav>
+
+<main id="main">
+<!-- /doc-chrome:top -->
+
+<h1>Filters: Advanced</h1>
 
 <br>
 
@@ -152,7 +108,7 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
     
     <br>
     
-    Important notice: size scan rules are checked <font color=red><b>after</b></font> the link was scheduled for download, 
+    Important notice: size scan rules are checked <b>after</b> the link was scheduled for download, 
     allowing to abort the connection. 
 
 
@@ -174,7 +130,7 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
     -mime:image/gif
     <br>
     
-    Important notice: MIME types scan rules are <font color=red><b>only</b></font> checked against links that were
+    Important notice: MIME types scan rules are <b>only</b> checked against links that were
     scheduled for download, i.e. links <b>already authorized</b> by url scan rules. 
     Hence, using '+mime:image/gif' will only be a hint to accept images that were already authorized, 
     if previous MIME scan rules excluded them - such as in '-mime:*/* +mime:text/html +mime:image/gif'
@@ -182,7 +138,7 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
     <br>
 
     <br>
-    <h3>Scan rules patterns:</h3>
+    <h3 id="scan-rules-patterns">Scan rules patterns:</h3>
 
 <p>    
     <h4>1.a. Scan rules based on URL or extension</h4>
@@ -455,25 +411,14 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
 
 <br>
 
-<!-- ==================== Start epilogue ==================== -->
-		</td>
-		</tr>
-		</table>
-	</td>
-	</tr>
-	</table>
-</td>
-</tr>
-</table>
+<!-- doc-chrome:bottom -->
+</main>
+</div>
 
-<table width="76%" border="0" align="center" valign="bottom" cellspacing="0" cellpadding="0">
-	<tr>
-	<td id="footer"><small>&copy; 1998-2026 Xavier Roche & other contributors - Web Design: Leto Kauler.</small></td>
-	</tr>
-</table>
+<dialog id="zoom" aria-label="Enlarged image"><img src="" alt=""></dialog>
+
+<footer>&copy; 1998-2026 Xavier Roche &amp; other contributors - Web Design: Leto Kauler.</footer>
+<!-- /doc-chrome:bottom -->
 
 </body>
-
 </html>
-
-

html/guide.css

@@ -0,0 +1,149 @@
+/* Styles specific to guide.html: the platform switcher, the option tab strip and
+   the option entries. The shared page chrome is in doc.css, loaded first. */
+
+/* Anchor targets must clear the sticky tab strip. */
+h2, h3, section.tab { scroll-margin-top: 5.5rem; }
+
+.cli {
+	font-family: ui-monospace, "Cascadia Mono", Consolas, "DejaVu Sans Mono", monospace;
+	font-size: .9em;
+}
+
+/* ---- platform switcher ---- */
+
+.platforms {
+	display: flex;
+	flex-wrap: wrap;
+	gap: .3rem;
+	margin: 0 0 1.5rem;
+	padding: .3rem;
+	background: var(--chip);
+	border-radius: .5rem;
+}
+
+.platforms button {
+	flex: 1 1 8rem;
+	padding: .5rem .7rem;
+	border: 0;
+	border-radius: .35rem;
+	background: transparent;
+	color: var(--ink);
+	font: inherit;
+	font-size: .95em;
+	cursor: pointer;
+}
+
+.platforms button:hover { background: var(--accent); }
+
+.platforms button[aria-pressed="true"] {
+	background: var(--panel);
+	box-shadow: 0 1px 3px var(--shadow);
+	font-weight: bold;
+}
+
+.platforms button small { display: block; font-weight: normal; color: var(--ink-soft); font-size: .82em; }
+
+/* Hide only what the chosen platform excludes: an "unhide" rule would need to
+   outweigh the hiding one, and loses on specificity. Without scripting no
+   platform is set, so every variant stays visible. */
+html[data-platform="win"] [data-for]:not([data-for~="win"]),
+html[data-platform="web"] [data-for]:not([data-for~="web"]),
+html[data-platform="droid"] [data-for]:not([data-for~="droid"]) { display: none; }
+
+/* ---- platform badges ---- */
+
+.badge {
+	display: inline-block;
+	padding: .05em .5em;
+	border-radius: 1em;
+	background: var(--accent);
+	color: var(--ink);
+	font-size: .78em;
+	font-weight: bold;
+	vertical-align: .1em;
+	white-space: nowrap;
+}
+
+/* ---- screenshots ---- */
+
+figure img[data-for~="droid"] { max-width: 18rem; }
+
+/* ---- option tab strip ---- */
+
+.tabstrip {
+	position: sticky;
+	top: 0;
+	z-index: 2;
+	display: flex;
+	flex-wrap: wrap;
+	gap: .2rem;
+	margin: 0 0 1.5rem;
+	padding: .4rem;
+	background: var(--chip);
+	border-radius: .4rem;
+	box-shadow: 0 2px 6px var(--shadow);
+}
+
+.tabstrip a {
+	padding: .3rem .6rem;
+	border-radius: .25rem;
+	text-decoration: none;
+	color: var(--ink);
+	font-size: .9em;
+	white-space: nowrap;
+}
+
+.tabstrip a:hover { background: var(--accent); }
+.tabstrip a[aria-current="true"] { background: var(--panel); font-weight: bold; box-shadow: 0 1px 3px var(--shadow); }
+
+/* ---- option entries ---- */
+
+.opt {
+	margin: 0 0 1.2em;
+	padding-bottom: 1.2em;
+	border-bottom: 1px solid var(--rule);
+}
+
+.opt:last-child { border-bottom: 0; }
+
+.opt-head {
+	display: flex;
+	flex-wrap: wrap;
+	gap: .5rem;
+	align-items: baseline;
+	justify-content: space-between;
+	margin-bottom: .3em;
+}
+
+.opt-name { font-weight: bold; }
+
+.opt .cli {
+	background: var(--code-bg);
+	padding: .1em .45em;
+	border-radius: 3px;
+	color: var(--ink-soft);
+	white-space: nowrap;
+}
+
+.opt p { margin: 0 0 .5em; font-size: .95em; }
+.opt p:last-child { margin-bottom: 0; }
+
+.opt[hidden] { display: none; }
+
+/* ---- misc ---- */
+
+table.mime {
+	border-collapse: collapse;
+	margin: 0 0 1em;
+	font-size: .92em;
+}
+
+table.mime td {
+	border: 1px solid var(--rule);
+	padding: .3em .6em;
+}
+
+@media print {
+	.tabstrip, .platforms { display: none; }
+	html[data-platform] [data-for] { display: revert !important; }
+}

html/guide.html

@@ -0,0 +1,916 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<meta name="description" content="How to mirror a website with the HTTrack graphical interface: a step-by-step walkthrough and a full option reference for WinHTTrack on Windows, WebHTTrack on Linux and Unix, and HTTrack for Android.">
+<meta name="keywords" content="httrack, WinHTTrack, WebHTTrack, HTTrack Android, offline browser, website mirroring, web mirror utility, options, scan rules, filters">
+<title>The HTTrack interface, step by step</title>
+<link rel="stylesheet" href="doc.css">
+<link rel="stylesheet" href="guide.css">
+<script src="doc.js" defer></script>
+<script src="guide.js"></script>
+</head>
+<body>
+
+<a class="skip" href="#main">Skip to content</a>
+
+<header class="masthead">
+	<img src="images/wordmark.svg" width="400" height="36" alt="HTTrack Website Copier">
+	<div class="tagline">Open Source offline browser</div>
+</header>
+
+<div class="wrap">
+
+<nav class="toc" aria-label="Contents">
+	<h2>Walkthrough</h2>
+	<ol>
+		<li><a href="#before">Before you start</a></li>
+		<li><a href="#step-start">1. Open HTTrack</a></li>
+		<li><a href="#step-project">2. Name the project</a></li>
+		<li><a href="#step-address">3. Enter the addresses</a></li>
+		<li><a href="#step-ready">4. Last checks</a></li>
+		<li><a href="#step-run">5. Watch it run</a></li>
+		<li><a href="#step-done">6. Read the result</a></li>
+	</ol>
+	<h2>Options</h2>
+	<ol>
+		<li><a href="#opt-scan-rules">Scan Rules</a></li>
+		<li><a href="#opt-limits">Limits</a></li>
+		<li><a href="#opt-flow-control">Flow Control</a></li>
+		<li><a href="#opt-links">Links</a></li>
+		<li><a href="#opt-build">Build</a></li>
+		<li><a href="#opt-browser-id">Browser ID</a></li>
+		<li><a href="#opt-spider">Spider</a></li>
+		<li><a href="#opt-proxy">Proxy</a></li>
+		<li><a href="#opt-log-index-cache">Log, Index, Cache</a></li>
+		<li><a href="#opt-mime-types">MIME Types</a></li>
+		<li><a href="#opt-experts-only">Experts Only</a></li>
+	</ol>
+	<h2>Elsewhere</h2>
+	<ol>
+		<li><a href="filters.html">Filter syntax</a></li>
+		<li><a href="cmdguide.html">Command-line guide</a></li>
+		<li><a href="faq.html">FAQ and troubleshooting</a></li>
+		<li><a href="index.html">All documentation</a></li>
+	</ol>
+</nav>
+
+<main id="main">
+
+<h1>The HTTrack interface, step by step</h1>
+
+<p class="lede">HTTrack copies a website to your disk so you can read it offline. The same
+engine ships behind three interfaces, and this page covers all three: pick yours below and
+the screenshots and notes follow along.</p>
+
+<div class="platforms" role="group" aria-label="Choose your version">
+	<button type="button" data-platform="win" aria-pressed="false">WinHTTrack <small>Windows</small></button>
+	<button type="button" data-platform="web" aria-pressed="false">WebHTTrack <small>Linux, macOS and Unix</small></button>
+	<button type="button" data-platform="droid" aria-pressed="false">HTTrack <small>Android</small></button>
+</div>
+
+<h2 id="before">Before you start</h2>
+
+<p>The three versions differ in their chrome, not in what they do. Every option below means
+the same thing in each of them, and all three write the same profile format. Where a version
+genuinely lacks something, it is marked <span class="badge">not on Android</span> or
+similar.</p>
+
+<p data-for="web">WebHTTrack runs as a small local web server and opens in your usual browser.
+Nothing is uploaded anywhere; the pages you see come from your own machine. Do leave the window
+open while a mirror runs: the interface pings the server every 30 seconds, and the server shuts
+itself down once those pings stop.</p>
+
+<p data-for="droid">The Android app needs Android 7.0 or later and is on
+<a href="https://play.google.com/store/apps/details?id=com.httrack.android">Google Play</a>.</p>
+
+<p>Each option also lists its command-line equivalent, so anything you set here can later be
+scripted. The <a href="cmdguide.html">command-line guide</a> covers that side.</p>
+
+<div class="note" data-for="droid">
+	<p><b>First launch.</b> Android asks for permission to store mirrors on your device. Without
+	it the app cannot save anything, so tap <b>Allow</b>.</p>
+	<figure>
+		<img data-for="droid" src="img/guide-droid-permission.png" alt="Android storage permission dialog" width="600" height="1300">
+	</figure>
+	<p>If an older release left mirrors behind, a second prompt offers to bring them in. Tap
+	<b>Import</b> to move them, or <b>Not now</b>.</p>
+	<figure>
+		<img data-for="droid" src="img/guide-droid-legacy-import.png" alt="Prompt offering to import mirrors from an older version" width="600" height="1300">
+	</figure>
+</div>
+
+<div class="note" data-for="win">
+	<p><b>First launch.</b> WinHTTrack opens on its About box, which carries a <b>Language
+	preference</b> dropdown at the foot. The choice is remembered, and
+	<b>Preferences &gt; Language preference...</b> changes it later.</p>
+	<figure>
+		<img data-for="win" src="img/guide-win-language.png" alt="WinHTTrack About box with the language preference dropdown" width="369" height="371">
+	</figure>
+</div>
+
+<h2 id="step-start">1. Open HTTrack</h2>
+
+<p>The welcome screen has nothing to fill in. <span data-for="win web">Click <b>Next</b></span><span
+data-for="droid">Tap <b>Next</b></span> to create a project, or open one you already made.</p>
+
+<figure>
+	<img data-for="win" src="img/guide-win-start.png" alt="WinHTTrack welcome pane" width="1040" height="744">
+	<img data-for="web" src="img/guide-web-start.png" alt="WebHTTrack welcome page" width="1024" height="388">
+	<img data-for="droid" src="img/guide-droid-start.png" alt="HTTrack for Android welcome screen" width="600" height="1300">
+	<figcaption>The welcome screen.</figcaption>
+</figure>
+
+<p class="note" data-for="web">The language dropdown starts blank on purpose: its first entry
+means "leave the interface as it is". Pick a language only if you want to change it.</p>
+
+<p class="note" data-for="web">On macOS, <code>brew install httrack</code> installs WebHTTrack
+alongside the command line tool. Open <b>HTTrack.app</b> if you have it, or run
+<code>webhttrack</code> in a terminal; either way the interface opens in your browser and
+behaves exactly as described here.</p>
+
+<h2 id="step-project">2. Name the project</h2>
+
+<p>A project is one mirror: its name becomes the folder your files land in, so give it something
+you will recognise in a year. The <b>category</b> is optional and only groups related projects
+together in the list.</p>
+
+<figure>
+	<img data-for="win" src="img/guide-win-project-name.png" alt="WinHTTrack project name, category and base path" width="1040" height="744">
+	<img data-for="web" src="img/guide-web-project-name.png" alt="WebHTTrack project name, category and base path" width="1024" height="346">
+	<img data-for="droid" src="img/guide-droid-project-name.png" alt="Android project name, category and base path" width="600" height="1300">
+	<figcaption>Project name, category, and where the files go.</figcaption>
+</figure>
+
+<p data-for="win web"><b>Base path</b> is the folder holding all your mirrors. Keeping every project
+under one folder is worth doing, if only so an update finds the previous copy. To reopen or update
+an existing project, pick its name from the list instead of typing a new one.</p>
+
+<p data-for="droid">The base path is fixed inside the app's storage and cannot be changed. To update
+an existing project, pick its name from the list instead of typing a new one.</p>
+
+<h2 id="step-address">3. Enter the addresses</h2>
+
+<p>Type the address you want to copy. Several addresses, one per line, are mirrored together and
+keep their links to each other.</p>
+
+<figure>
+	<img data-for="win" src="img/guide-win-project-setup.png" alt="WinHTTrack action and web addresses" width="1040" height="744">
+	<img data-for="web" src="img/guide-web-project-setup.png" alt="WebHTTrack action and web addresses" width="1024" height="496">
+	<img data-for="droid" src="img/guide-droid-project-setup.png" alt="Android web address and action" width="600" height="1300">
+	<figcaption>The addresses to copy, and what to do with them.</figcaption>
+</figure>
+
+<p><b>Action</b> decides what the engine does with them:</p>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Download web site(s)</span><span class="cli">-w, --mirror</span></div>
+	<p>The normal choice. Copies the sites with the current options.</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">Download web site(s) + questions</span><span class="cli">-W, --mirror-wizard</span></div>
+	<p>The same, but asks before following anything it is unsure about.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Get individual files</span><span class="cli">-g, --get-files</span></div>
+	<p>Downloads exactly the addresses you listed and follows nothing. Use it to grab a handful of
+	files rather than a site.</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">Download all sites in pages</span><span class="cli">-Y, --mirrorlinks</span></div>
+	<p>Mirrors every site linked from the pages you listed. Pointed at a bookmarks file, it copies
+	everything you bookmarked.</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">Test links in pages</span><span class="cli">--testlinks</span></div>
+	<p>Checks that the links resolve without saving anything. Useful against a bookmarks file.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Continue interrupted download</span><span class="cli">--continue</span></div>
+	<p>Picks a crashed or cancelled mirror back up where it stopped. Offered only when the project
+	already exists.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Update existing download</span><span class="cli">--update</span></div>
+	<p>Re-checks the whole site and fetches only what changed. Offered only when the project already
+	exists, and it needs the cache from the previous run, which is why
+	<a href="#opt-experts-only">Use a cache for updates</a> should stay on.</p>
+</div>
+
+<p data-for="win web">The <b>Add a URL</b> button takes one address at a time, and does two
+things the address box cannot. It attaches a login and password to that one address, for a
+page behind basic authentication. And it captures an address out of your browser, for a page
+you can only reach by submitting a form or following a script: HTTrack listens on a local
+port, you point your browser at it as a proxy and click the link or the submit button as
+usual, and the address the browser asks for is added to the project.</p>
+
+<figure data-for="web">
+	<img data-for="web" src="img/guide-web-add-url.png" alt="WebHTTrack add-a-URL dialog" width="1024" height="634">
+	<figcaption>Adding a single address, with an optional login.</figcaption>
+</figure>
+
+<p>Everything else lives behind <b>Set options</b>, described in
+<a href="#options">the option panel</a> below. The defaults are sane; a first mirror needs nothing
+from there except, quite often, a <a href="#opt-scan-rules">scan rule</a>.</p>
+
+<figure data-for="droid">
+	<img data-for="droid" src="img/guide-droid-options-menu.png" alt="Android options tab list" width="600" height="1300">
+	<figcaption>On Android the option tabs are a list.</figcaption>
+</figure>
+
+<h2 id="step-ready">4. Last checks</h2>
+
+<p data-for="win">One pane stands between you and the mirror. It can dial a connection first,
+hang up when the mirror ends, shut the machine down afterwards, or hold the whole thing for up to
+24 hours. Leave it alone if you are already online and want to start now, and click
+<b>Finish</b>.</p>
+
+<p data-for="web">One page stands between you and the mirror. <b>Start</b> begins it;
+the save-only choice writes the project settings and stops, which is handy when you are preparing
+a mirror to run later.</p>
+
+<p data-for="droid">Android has no such screen: <b>Start</b> on the address screen begins the
+mirror straight away.</p>
+
+<figure data-for="win web">
+	<img data-for="win" src="img/guide-win-ready.png" alt="WinHTTrack connection settings before starting" width="1040" height="744">
+	<img data-for="web" src="img/guide-web-ready.png" alt="WebHTTrack ready to start" width="1024" height="508">
+	<figcaption>The last screen before the mirror runs.</figcaption>
+</figure>
+
+<h2 id="step-run">5. Watch it run</h2>
+
+<p>The engine reports what it is doing: bytes written, links scanned, transfer rate, errors so
+far, and one line per transfer in flight. A mirror of any size takes a while. That is the
+server's pace as much as yours, and the <a href="#opt-limits">Limits</a> options exist to keep it
+polite.</p>
+
+<figure>
+	<img data-for="win" src="img/guide-win-progress.png" alt="WinHTTrack mirror in progress" width="1040" height="744">
+	<img data-for="web" src="img/guide-web-progress.png" alt="WebHTTrack mirror in progress" width="1024" height="742">
+	<img data-for="droid" src="img/guide-droid-progress.png" alt="Android mirror in progress" width="600" height="1300">
+	<figcaption>A crawl in flight.</figcaption>
+</figure>
+
+<p data-for="win web">You can stop at any point without losing what has been written, and a
+stopped mirror resumes later with <b>Continue interrupted download</b>. Individual transfers can
+be cancelled too, which is the quick way past one enormous file. Several options (the number of
+connections, the limits) can be changed while the mirror runs.</p>
+
+<p data-for="droid">Tap <b>Abort</b> to stop. Nothing already written is lost, and the mirror
+resumes later with <b>Continue interrupted download</b>.</p>
+
+<h2 id="step-done">6. Read the result</h2>
+
+<p>When the crawl ends, open the copy and read it as you would the real site. Links between
+mirrored pages are rewritten to point at each other, so it browses offline in any browser.</p>
+
+<figure>
+	<img data-for="win" src="img/guide-win-finished.png" alt="WinHTTrack mirror complete" width="1040" height="744">
+	<img data-for="web" src="img/guide-web-finished.png" alt="WebHTTrack mirror complete" width="1024" height="487">
+	<img data-for="droid" src="img/guide-droid-finished.png" alt="Android mirror complete" width="600" height="1300">
+	<figcaption>Done.</figcaption>
+</figure>
+
+<p>Read the log before you trust a mirror. It records every error, and a site that looks complete
+can still be missing images that a <a href="#opt-scan-rules">scan rule</a> would have caught. If
+something is missing, the <a href="faq.html">FAQ and troubleshooting</a> page starts with the
+usual causes.</p>
+
+<p data-for="win web">The files sit under the base path you chose, in a folder named after the
+project. Opening <code>index.html</code> there browses the mirror without HTTrack.</p>
+
+<p data-for="droid">Mirrors are written to
+<code>/storage/emulated/0/HTTrack/Websites</code>, in a folder named after the project. That is
+shared storage, so a file manager or a USB cable can reach it, and opening
+<code>index.html</code> there browses the mirror without the app.</p>
+
+<h2 id="options">The option panel</h2>
+
+<p>Eleven tabs, and you can ignore almost all of them. The defaults mirror a site correctly; the
+options are there for the sites that need persuading. Each entry below names the setting as the
+interface shows it, and the command-line option it corresponds to.</p>
+
+<nav class="tabstrip" aria-label="Option tabs">
+	<a href="#opt-scan-rules">Scan Rules</a>
+	<a href="#opt-limits">Limits</a>
+	<a href="#opt-flow-control">Flow Control</a>
+	<a href="#opt-links">Links</a>
+	<a href="#opt-build">Build</a>
+	<a href="#opt-browser-id">Browser ID</a>
+	<a href="#opt-spider">Spider</a>
+	<a href="#opt-proxy">Proxy</a>
+	<a href="#opt-log-index-cache">Log, Index, Cache</a>
+	<a href="#opt-mime-types">MIME Types</a>
+	<a href="#opt-experts-only">Experts Only</a>
+</nav>
+
+<div class="filter">
+	<label for="optfilter">Find an option</label>
+	<input type="search" id="optfilter" placeholder="cookies, depth, footer…" autocomplete="off">
+	<output id="optcount" for="optfilter"></output>
+</div>
+
+<section class="tab" id="opt-scan-rules">
+<h3>Scan Rules</h3>
+
+<figure>
+	<img data-for="win" src="img/guide-win-opt-scan-rules.png" alt="WinHTTrack Scan Rules tab" width="524" height="448">
+	<img data-for="web" src="img/guide-web-opt-scan-rules.png" alt="WebHTTrack Scan Rules tab" width="1024" height="995">
+	<img data-for="droid" src="img/guide-droid-opt-scan-rules.png" alt="Android Scan Rules tab" width="600" height="1300">
+</figure>
+
+<p>The most useful tab in the panel, and the answer to most "why is this missing?" questions. A
+scan rule accepts or refuses addresses by pattern: a whole directory, a domain, a file type. When
+a mirror comes back without its images because they live on another host, this is where you let
+them in.</p>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Include link(s)</span><span class="cli">+pattern</span></div>
+	<p>Accept addresses matching the pattern, even ones the engine would otherwise leave alone.
+	<code>+*.example.com/*.jpg</code> takes the JPEGs from a neighbouring host;
+	<code>+*/images/landscapes/*</code> takes one directory wherever it appears.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Exclude link(s)</span><span class="cli">-pattern</span></div>
+	<p>Refuse addresses matching the pattern. <code>-*.zip</code> skips the archives,
+	<code>-*/forum/*</code> skips a section you do not want.</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">Rule list from a file</span><span class="cli">-%S, --urllist &lt;file&gt;</span></div>
+	<p>Reads rules from a text file, one per line, instead of the box.</p>
+</div>
+
+<p>Rules are read in order and the last match wins, so a broad exclusion followed by a narrow
+inclusion does what it looks like. The full pattern syntax, including size and MIME conditions,
+is on the <a href="filters.html">filter page</a>.</p>
+</section>
+
+<section class="tab" id="opt-limits">
+<h3>Limits</h3>
+
+<figure>
+	<img data-for="win" src="img/guide-win-opt-limits.png" alt="WinHTTrack Limits tab" width="524" height="448">
+	<img data-for="web" src="img/guide-web-opt-limits.png" alt="WebHTTrack Limits tab" width="1024" height="1016">
+	<img data-for="droid" src="img/guide-droid-opt-limits.png" alt="Android Limits tab" width="600" height="1300">
+</figure>
+
+<p>Ceilings on how much the mirror may cost you, and cost the server. The two rate limits at the
+bottom are the ones that keep you welcome.</p>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Maximum mirroring depth</span><span class="cli">-rN, --depth N</span></div>
+	<p>How many clicks from your starting addresses the engine may travel. A depth of 3 means the
+	pages you listed, plus everything within two more clicks. Left empty it is effectively
+	unlimited, which is usually right: the engine already refuses to leave the site.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Maximum external depth</span><span class="cli">-%eN, --ext-depth N</span></div>
+	<p>How far to follow links off the site, past what the scan rules allow. It overrides the other
+	limits, so raise it with care. The default is zero.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Max size of any non-HTML file</span><span class="cli">-mN, --max-files N</span></div>
+	<p>Per-file ceiling in bytes: a larger image or archive is skipped.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Max size of any HTML file</span><span class="cli">-mN,N2, --max-files</span></div>
+	<p>The same for pages. One command-line option carries both ceilings, non-HTML first.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Site size limit</span><span class="cli">-MN, --max-size N</span></div>
+	<p>Total bytes the mirror may download before it stops.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Pause after downloading</span><span class="cli">-GN, --max-pause N</span></div>
+	<p>Pauses once that many bytes have arrived and waits for you to delete a lock file. The way to
+	mirror a site larger than your free space: back up and clear the files during the pause.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Pause between files</span><span class="cli">-%G, --pause MIN[:MAX]</span></div>
+	<p>Waits a random number of seconds between downloads. <code>2:8</code> picks a fresh delay in
+	that range each time. The gentlest way to crawl a small server, and less blunt than capping the
+	rate.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Max time overall</span><span class="cli">-EN, --max-time N</span></div>
+	<p>Seconds the whole mirror may take. 3600 is an hour.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Max transfer rate</span><span class="cli">-AN, --max-rate N</span></div>
+	<p>Bytes per second, across the whole mirror. Keeps HTTrack from taking the whole line.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Max connections / seconds</span><span class="cli">-%cN, --connection-per-second N</span></div>
+	<p>New connections per second, and the politest thing on this page. Fractions are allowed:
+	<code>0.1</code> is one connection every ten seconds. Setting it to zero removes the limit and
+	can flatten a small server; do not, unless the server is yours.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Maximum number of links</span><span class="cli">-#LN, --advanced-maxlinks N</span></div>
+	<p>How many addresses may be held in memory, downloaded or not. The engine stops dead on
+	reaching it, so do not set it low. The default of 100,000 suits most sites and costs memory to
+	raise.</p>
+</div>
+</section>
+
+<section class="tab" id="opt-flow-control">
+<h3>Flow Control</h3>
+
+<figure>
+	<img data-for="win" src="img/guide-win-opt-flow-control.png" alt="WinHTTrack Flow Control tab" width="524" height="448">
+	<img data-for="web" src="img/guide-web-opt-flow-control.png" alt="WebHTTrack Flow Control tab" width="1024" height="910">
+	<img data-for="droid" src="img/guide-droid-opt-flow-control.png" alt="Android Flow Control tab" width="600" height="1300">
+</figure>
+
+<p>How hard to push, and when to give up on a server that is not answering.</p>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Number of connections</span><span class="cli">-cN, --sockets N</span></div>
+	<p>Transfers running at once. Four is the default and eight is comfortable on an ordinary site;
+	drop to one or two when the files are large, since parallel transfers of big files help nobody.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Timeout</span><span class="cli">-TN, --timeout N</span></div>
+	<p>Seconds to wait on a silent server before abandoning the link. It also bounds host name
+	resolution. Around 120 suits most connections.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Retries</span><span class="cli">-RN, --retries N</span></div>
+	<p>How many times to retry after a timeout or another non-fatal error. It will not rescue a
+	404: nothing retries a definite answer.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Min transfer rate</span><span class="cli">-JN, --min-rate N</span></div>
+	<p>Bytes per second below which a transfer is treated as stalled and dropped.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Abandon host on timeout or slow transfer</span><span class="cli">-HN, --host-control N</span></div>
+	<p>Whether one bad transfer condemns the whole host: never (0), on timeout (1), on a slow
+	transfer (2), or either (3). The checkboxes beside the timeout and rate fields set this. Anything
+	but <em>never</em> can drop a lot of links over one slow moment, so leave it off unless a host is
+	actively wasting your time.</p>
+</div>
+</section>
+
+<section class="tab" id="opt-links">
+<h3>Links</h3>
+
+<figure>
+	<img data-for="win" src="img/guide-win-opt-links.png" alt="WinHTTrack Links tab" width="524" height="448">
+	<img data-for="web" src="img/guide-web-opt-links.png" alt="WebHTTrack Links tab" width="1024" height="781">
+	<img data-for="droid" src="img/guide-droid-opt-links.png" alt="Android Links tab" width="600" height="1300">
+</figure>
+
+<p>What counts as a link worth following.</p>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Attempt to detect all links</span><span class="cli">-%P, --extended-parsing</span></div>
+	<p>Looks for addresses everywhere, including unknown tags and JavaScript. On by default. It
+	earns its keep on script-heavy pages, at the price of the occasional request for something that
+	was never a link.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Get non-HTML files related to a link</span><span class="cli">-n, --near</span></div>
+	<p>Fetches the images and other files a page refers to even when they sit outside the mirror.
+	The usual fix for a page whose pictures live on another host.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Test validity of all links</span><span class="cli">-t, --test</span></div>
+	<p>Requests every link found, including ones the rules forbid, and logs the failures. A link
+	checker rather than a mirroring option.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Get HTML files first</span><span class="cli">-p7, --priority 7</span></div>
+	<p>Takes the pages before the images. The structure of the site is known sooner, which makes the
+	rest of the crawl better informed.</p>
+</div>
+</section>
+
+<section class="tab" id="opt-build">
+<h3>Build</h3>
+
+<figure>
+	<img data-for="win" src="img/guide-win-opt-build.png" alt="WinHTTrack Build tab" width="524" height="448">
+	<img data-for="web" src="img/guide-web-opt-build.png" alt="WebHTTrack Build tab" width="1024" height="986">
+	<img data-for="droid" src="img/guide-droid-opt-build.png" alt="Android Build tab" width="600" height="1300">
+</figure>
+
+<p>How the copy is laid out on disk.</p>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Local structure type</span><span class="cli">-NN, --structure N</span></div>
+	<p>The default reproduces the site's own folders and names. The alternatives sort files by kind
+	instead: all the pages here, all the images there. A custom pattern such as
+	<code>-N "%h%p/%n%q.%t"</code> builds names from the host, path, name, query and type.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">DOS names (8+3)</span><span class="cli">-L0, --long-names 0</span></div>
+	<p>Cuts every name to eight characters and a three-letter extension.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">ISO9660 names (CDROM)</span><span class="cli">-L2, --long-names 2</span></div>
+	<p>Names that survive being burned to a CD or DVD.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">No error pages</span><span class="cli">-o0, --do-not-generate-errors</span></div>
+	<p>By default a page that returned 404 is saved as a note saying so. This drops those, leaving
+	nothing at all where the page was.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">No external pages</span><span class="cli">-x, --replace-external</span></div>
+	<p>Replaces links that leave the mirror with a page saying you need to be online. Keeps the
+	offline copy from silently reaching for the network.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Hide passwords</span><span class="cli">-%x, --disable-passwords</span></div>
+	<p>Strips credentials out of the links written into the saved pages, so the copy cannot leak
+	them.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Hide query strings</span><span class="cli">-%q0, --include-query-string 0</span></div>
+	<p>Local files rarely need the <code>?a=1&amp;b=2</code> part, though it can carry a hint about
+	what a page was. Some limited browsers choke on it.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Do not purge old files</span><span class="cli">-X0, --purge-old 0</span></div>
+	<p>After an update HTTrack deletes local files that are gone from the site or now excluded. This
+	keeps them.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Inline assets as data: URIs</span><span class="cli">-%Z, --single-file</span></div>
+	<p>Rewrites each saved page with its stylesheets, scripts, images and fonts embedded, so a single
+	file opens anywhere on its own. Links between mirrored pages stay relative; audio and video stay
+	links. <code>--single-file-max-size</code> caps each embedded asset, 10 MB by default.</p>
+</div>
+</section>
+
+<section class="tab" id="opt-browser-id">
+<h3>Browser ID</h3>
+
+<figure>
+	<img data-for="win" src="img/guide-win-opt-browser-id.png" alt="WinHTTrack Browser ID tab" width="524" height="448">
+	<img data-for="web" src="img/guide-web-opt-browser-id.png" alt="WebHTTrack Browser ID tab" width="1024" height="706">
+	<img data-for="droid" src="img/guide-droid-opt-browser-id.png" alt="Android Browser ID tab" width="600" height="1300">
+</figure>
+
+<p>What HTTrack says about itself in its requests.</p>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Browser identity</span><span class="cli">-F, --user-agent</span></div>
+	<p>The <code>User-Agent</code> sent with every request. Some sites serve different pages, or
+	refuse to serve at all, depending on what they read here.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">HTML footer</span><span class="cli">-%F, --footer</span></div>
+	<p>A comment added to each saved page, recording where it came from. Named fields are
+	substituted: <code>{url}</code>, <code>{date}</code>, <code>{addr}</code>, <code>{path}</code>,
+	<code>{lastmodified}</code>, <code>{version}</code>, <code>{mime}</code>, <code>{charset}</code>,
+	<code>{status}</code> and <code>{size}</code>. For example
+	<code>&lt;!-- Mirrored from {url} on {date} --&gt;</code>. You can turn it off, but a page with no
+	record of its origin is worth less later.</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">Preferred language</span><span class="cli">-%l, --language</span></div>
+	<p>The <code>Accept-Language</code> header, as in <code>"fr, en, *"</code>. It decides which
+	translation a multilingual site hands over.</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">Default referer</span><span class="cli">-%R, --referer</span></div>
+	<p>The <code>Referer</code> sent with the first request. Occasionally needed by sites that refuse
+	traffic arriving from nowhere.</p>
+</div>
+</section>
+
+<section class="tab" id="opt-spider">
+<h3>Spider</h3>
+
+<figure>
+	<img data-for="win" src="img/guide-win-opt-spider.png" alt="WinHTTrack Spider tab" width="524" height="448">
+	<img data-for="web" src="img/guide-web-opt-spider.png" alt="WebHTTrack Spider tab" width="1024" height="1557">
+	<img data-for="droid" src="img/guide-droid-opt-spider.png" alt="Android Spider tab" width="600" height="1300">
+</figure>
+
+<p>How the engine behaves towards the server it is talking to.</p>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Accept cookies</span><span class="cli">-bN, --cookies N</span></div>
+	<p>On by default. Sites that hand out a session before showing anything need it.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Check document type</span><span class="cli">-uN, --check-type N</span></div>
+	<p>When the address does not reveal the file type, say a <code>.cgi</code> that returns an image,
+	the engine asks the server so the file gets a sensible name locally. Turning this off entirely
+	produces a mirror full of files no browser will open.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Parse scripts</span><span class="cli">-jN, --parse-java N</span></div>
+	<p>Reads scripts looking for addresses. On by default.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Follow robots.txt</span><span class="cli">-sN, --robots N</span></div>
+	<p>Whether to respect the site's crawling rules: never (0), sometimes (1), always (2, the
+	default), or always including the strict rules (3). Ignoring them on a site you do not own is
+	how mirroring gets people blocked.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Update hacks</span><span class="cli">-%s, --updatehack</span></div>
+	<p>Works around servers that misreport what changed, treating a file of identical size as
+	unchanged even when the timestamp moved. Saves a great deal of traffic on dynamic sites, at a
+	small risk of keeping a stale page.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Tolerant requests</span><span class="cli">-%B, --tolerant</span></div>
+	<p>Accepts responses that break the rules. Off by default, because a server that lies about a
+	file's length usually leaves you with a truncated one.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Force HTTP/1.0 requests</span><span class="cli">-%h, --http-10</span></div>
+	<p>For servers and proxies too old to cope with anything newer. It costs you most of the update
+	machinery, so use it only when a site genuinely fails without it.</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">URL hacks</span><span class="cli">-%u, --urlhack</span></div>
+	<p>Treats addresses that differ only cosmetically as the same page (<code>www.example.com</code>
+	and <code>example.com</code>, doubled slashes, reordered query keys), so the same page is not
+	downloaded twice.</p>
+	<p>Three checkboxes opt out of one part each when a site really does treat the difference as
+	meaningful: <b>Keep the www. prefix</b> (<code>--keep-www-prefix</code>), <b>Keep double
+	slashes</b> (<code>--keep-double-slashes</code>) and <b>Keep the original query-string order</b>
+	(<code>--keep-query-order</code>).</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">Seed the crawl from the site's sitemap</span><span class="cli">-%m, --sitemap</span></div>
+	<p>Reads the site's sitemap, the <code>Sitemap:</code> lines in <code>robots.txt</code> and then
+	<code>/sitemap.xml</code>, and adds every address it lists as a starting point. It reaches pages
+	no link on the site points to. <b>Sitemap address</b> (<code>--sitemap-url</code>) names one
+	directly instead of probing.</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">Load cookies from file</span><span class="cli">-%K, --cookies-file</span></div>
+	<p>Preloads cookies from a Netscape <code>cookies.txt</code> before the crawl starts. How you
+	mirror something that needs you logged in, by exporting the session from your browser.</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">Strip query keys</span><span class="cli">-%g, --strip-query</span></div>
+	<p>Comma-separated query keys to drop when naming saved files, such as
+	<code>sid,utm_source</code>. Keeps one page from being saved several times under tracking
+	parameters that change nothing.</p>
+</div>
+</section>
+
+<section class="tab" id="opt-proxy">
+<h3>Proxy</h3>
+
+<figure>
+	<img data-for="win" src="img/guide-win-opt-proxy.png" alt="WinHTTrack Proxy tab" width="524" height="448">
+	<img data-for="web" src="img/guide-web-opt-proxy.png" alt="WebHTTrack Proxy tab" width="1024" height="762">
+	<img data-for="droid" src="img/guide-droid-opt-proxy.png" alt="Android Proxy tab" width="600" height="1300">
+</figure>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Proxy type</span><span class="cli">-P scheme://…</span></div>
+	<p>The proxy protocol. <b>HTTP</b> is an ordinary proxy. <b>HTTP (CONNECT tunnel)</b> sends every
+	request through a CONNECT tunnel, which CONNECT-only proxies such as Tor's
+	<code>HTTPTunnelPort</code> require. <b>SOCKS5</b> defaults to port 1080.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Proxy address and port</span><span class="cli">-P, --proxy</span></div>
+	<p>The proxy to send requests through. On the command line one string carries the lot, including
+	a scheme and credentials where needed:
+	<code>--proxy socks5://user:pass@proxy.example.com:1080</code>.</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">Proxy login and password</span><span class="cli">-P user:pass@host:port</span></div>
+	<p>Filled in behind the <b>Configure</b> button, for a proxy that demands authentication.</p>
+	<p><span class="badge">not on Android</span> The Android app takes a host and a port only.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Use proxy for FTP transfers</span><span class="cli">-%f, --httpproxy-ftp</span></div>
+	<p>Sends <code>ftp://</code> transfers through the HTTP proxy as well. On by default, and worth
+	keeping: it gets FTP links through a firewall, and proxied FTP tends to be more reliable than the
+	engine's own client.</p>
+</div>
+</section>
+
+<section class="tab" id="opt-log-index-cache">
+<h3>Log, Index, Cache</h3>
+
+<figure>
+	<img data-for="win" src="img/guide-win-opt-log-index-cache.png" alt="WinHTTrack Log, Index, Cache tab" width="524" height="448">
+	<img data-for="web" src="img/guide-web-opt-log-index-cache.png" alt="WebHTTrack Log, Index, Cache tab" width="1024" height="1278">
+	<img data-for="droid" src="img/guide-droid-opt-log-index-cache.png" alt="Android Log, Index, Cache tab" width="600" height="1300">
+</figure>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Store all files in cache</span><span class="cli">-k, --store-all-in-cache</span></div>
+	<p>Normally only pages are cached, since that is all an update needs. This caches everything,
+	which lets you rebuild the mirror in a different layout later without downloading it again, and
+	makes the cache as large as the mirror.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Do not re-download locally erased files</span><span class="cli">-%n, --do-not-recatch</span></div>
+	<p>A file you deleted stays deleted through the next update, instead of coming straight back.
+	Useful while pruning something large by hand.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Create log files</span><span class="cli">-f, --file-log</span></div>
+	<p>On, and worth leaving on: without a log you have no way to find out what failed. The
+	debug level beside it controls how much detail lands there.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Make an index</span><span class="cli">-I, --index</span></div>
+	<p>Writes an <code>index.html</code> at the top of the project, listing the mirrored sites. The
+	front door to the copy.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Make a word database</span><span class="cli">-%I, --search-index</span></div>
+	<p>Builds a searchable word index of every mirrored page.</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">Write a WARC archive of the crawl</span><span class="cli">-%r, --warc</span></div>
+	<p>Saves every fetched response into an ISO-28500 WARC/1.1 archive alongside the mirror, headers
+	and all. The mirror is a browsable copy; the WARC is the archival record of what the server
+	actually sent, which is what replay tools and web archives want.</p>
+	<p><b>WARC archive name</b> (<code>--warc-file</code>) sets the base name, blank to auto-name it
+	under the output directory. <b>WARC segment size limit</b> (<code>--warc-max-size</code>) starts a
+	new segment past that many bytes; blank or 0 keeps one file.</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">Write a CDXJ index of the WARC archive</span><span class="cli">-%rc, --warc-cdx</span></div>
+	<p>Adds a sorted CDXJ index listing every record in the archive, which replay tools use to find a
+	capture without reading the whole file.</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">Package the crawl as a WACZ file</span><span class="cli">--wacz</span></div>
+	<p>Bundles the WARC, its CDXJ index and the mirrored pages into one WACZ file. It implies both of
+	the two above.</p>
+</div>
+
+<div class="opt" data-for="win web">
+	<div class="opt-head"><span class="opt-name">Report what changed since the previous mirror</span><span class="cli">-%d, --changes</span></div>
+	<p>Writes <code>hts-changes.json</code> listing what this crawl left new, changed, unchanged and
+	gone against the previous mirror. The quick way to see what an update actually did.</p>
+</div>
+</section>
+
+<section class="tab" id="opt-mime-types">
+<h3>MIME Types</h3>
+
+<figure>
+	<img data-for="win" src="img/guide-win-opt-mime-types.png" alt="WinHTTrack MIME types tab" width="524" height="448">
+	<img data-for="web" src="img/guide-web-opt-mime-types.png" alt="WebHTTrack MIME types tab" width="1024" height="1046">
+	<img data-for="droid" src="img/guide-droid-opt-mime-types.png" alt="Android MIME types tab" width="600" height="1300">
+</figure>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Type / MIME associations</span><span class="cli">-%A, --assume</span></div>
+	<p>Tells the engine what an extension always means, so it stops asking the server. On a site full
+	of <code>.asp</code> links this is a large speed-up: without it every unknown extension costs a
+	request before the engine knows what it has.</p>
+	<p>Enter a file type and the MIME type it maps to, <code>asp</code> to <code>text/html</code>,
+	and list several at once with commas: <code>asp,php,php3</code>. On the command line the same
+	thing reads <code>--assume asp,php,php3=text/html</code>, and
+	<code>--assume standard</code> covers the usual page extensions in one go.</p>
+	<p>It also renames on the way in. If you know the site's <code>.dat</code> files are really ZIPs,
+	map <code>dat</code> to <code>application/x-zip</code> and they land correctly named. Mapping an
+	unknown type to <code>application/octet-stream</code> simply stops the engine checking it.</p>
+	<table class="mime">
+		<tr><td><code>text/html</code></td><td>pages, which HTTrack parses for links</td></tr>
+		<tr><td><code>image/gif</code>, <code>image/jpeg</code>, <code>image/png</code></td><td>images</td></tr>
+		<tr><td><code>application/x-zip</code></td><td>ZIP archives</td></tr>
+		<tr><td><code>application/octet-stream</code></td><td>anything else, left alone</td></tr>
+	</table>
+	<p><span class="badge">Android</span> The table holds up to eight entries.</p>
+</div>
+</section>
+
+<section class="tab" id="opt-experts-only">
+<h3>Experts Only</h3>
+
+<figure>
+	<img data-for="win" src="img/guide-win-opt-experts-only.png" alt="WinHTTrack Experts Only tab" width="524" height="448">
+	<img data-for="web" src="img/guide-web-opt-experts-only.png" alt="WebHTTrack Experts Only tab" width="1024" height="1088">
+	<img data-for="droid" src="img/guide-droid-opt-experts-only.png" alt="Android Experts Only tab" width="600" height="1300">
+</figure>
+
+<p>The defaults here are right for almost every mirror. The travel modes are the exception: they
+are how you widen a crawl deliberately.</p>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Use a cache for updates</span><span class="cli">-CN, --cache N</span></div>
+	<p>Keep this on. The cache is what makes <b>Update existing download</b> and <b>Continue
+	interrupted download</b> possible at all; turning it off saves a little disk and costs you both.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Primary scan rule</span><span class="cli">-pN, --priority N</span></div>
+	<p>What gets saved: nothing (0, for checking links), pages only (1), everything but pages (2),
+	everything (3, the default), or pages first then the rest (7).</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Travel mode</span><span class="cli">-S -D -U -B</span></div>
+	<p>Which directories the crawl may enter relative to your starting address: this one only
+	(<code>-S</code>), it and below (<code>-D</code>, the default), it and above (<code>-U</code>), or
+	both directions (<code>-B</code>).</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Global travel mode</span><span class="cli">-a -d -l -e</span></div>
+	<p>How far the crawl may stray from the address you gave it: same address only (<code>-a</code>,
+	the default), same domain (<code>-d</code>), same top-level domain (<code>-l</code>), or anywhere
+	at all (<code>-e</code>). The last one will follow the web until a limit stops it.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Rewrite links</span><span class="cli">-KN, --keep-links N</span></div>
+	<p>What the links in the saved pages look like: relative, so the copy browses offline
+	(<code>K0</code>, the default), absolute, or the original online addresses (<code>K4</code>), which
+	gives you the pages as archived documents rather than a browsable mirror.</p>
+</div>
+
+<div class="opt">
+	<div class="opt-head"><span class="opt-name">Activate debug mode</span><span class="cli">-%H, --debug-headers</span></div>
+	<p>Writes the HTTP headers and other internals to the log. For diagnosing a site that behaves
+	strangely, not for normal use.</p>
+</div>
+</section>
+
+<h2 id="next">Where to go next</h2>
+
+<ul>
+	<li><a href="filters.html">Filter syntax</a>: the full pattern language behind Scan Rules.</li>
+	<li><a href="cmdguide.html">Command-line guide</a>: the same engine, scripted.</li>
+	<li><a href="httrack.man.html">Manual page</a>: every option, authoritative.</li>
+	<li><a href="faq.html">FAQ and troubleshooting</a>: when a mirror comes back wrong.</li>
+	<li><a href="abuse.html">How not to use HTTrack</a>: worth two minutes before pointing it at
+	someone else's server.</li>
+</ul>
+
+</main>
+</div>
+
+<dialog id="zoom" aria-label="Enlarged screenshot"><img src="" alt=""></dialog>
+
+<footer>&copy; 1998-2026 Xavier Roche &amp; other contributors - Web Design: Leto Kauler.</footer>
+
+</body>
+</html>

html/guide.js

@@ -0,0 +1,127 @@
+/* Progressive enhancement for guide.html: the platform switcher and the option
+   filter. Image zoom and sidebar highlighting are shared, in doc.js. Everything
+   here is optional: with scripting off the page still carries every platform's
+   text and screenshots. */
+
+(function () {
+	"use strict";
+
+	var PLATFORMS = ["win", "web", "droid"];
+	var STORE = "httrack-guide-platform";
+
+	/* Chrome denies storage to file:// origins, and the doc is read from disk. */
+	function remembered() {
+		try {
+			return localStorage.getItem(STORE);
+		} catch (e) {
+			return null;
+		}
+	}
+
+	function remember(platform) {
+		try {
+			localStorage.setItem(STORE, platform);
+		} catch (e) {
+			/* not fatal: the hash still carries the choice */
+		}
+	}
+
+	/* "#win/opt-limits" -> {platform: "win", target: "opt-limits"}, and a bare
+	   "#win" is a platform, not a target of that name. */
+	function parseHash() {
+		var hash = location.hash.replace(/^#/, "");
+		var slash = hash.indexOf("/");
+		if (slash < 0) {
+			return PLATFORMS.indexOf(hash) !== -1
+				? { platform: hash, target: "" }
+				: { platform: null, target: hash };
+		}
+		if (PLATFORMS.indexOf(hash.slice(0, slash)) !== -1) {
+			return { platform: hash.slice(0, slash), target: hash.slice(slash + 1) };
+		}
+		return { platform: null, target: hash };
+	}
+
+	function setPlatform(platform) {
+		document.documentElement.setAttribute("data-platform", platform);
+	}
+
+	/* Runs before first paint, so the page never flashes the other platforms. */
+	var initial = parseHash().platform || remembered() ||
+		(/Android/i.test(navigator.userAgent) ? "droid" :
+			/Windows/i.test(navigator.userAgent) ? "win" : "web");
+	setPlatform(initial);
+
+	document.addEventListener("DOMContentLoaded", function () {
+		var current = document.documentElement.getAttribute("data-platform");
+
+		/* ---- platform switcher ---- */
+
+		var buttons = [].slice.call(document.querySelectorAll(".platforms button"));
+
+		function select(platform, push) {
+			current = platform;
+			setPlatform(platform);
+			remember(platform);
+			buttons.forEach(function (b) {
+				b.setAttribute("aria-pressed", String(b.dataset.platform === platform));
+			});
+			if (push) {
+				var target = parseHash().target;
+				history.replaceState(null, "", "#" + platform + (target ? "/" + target : ""));
+			}
+		}
+
+		buttons.forEach(function (b) {
+			b.addEventListener("click", function () {
+				select(b.dataset.platform, true);
+			});
+		});
+		select(current, false);
+
+		/* A "#win/opt-limits" link has no element of that id: scroll it ourselves. */
+		function jumpToHash() {
+			var parsed = parseHash();
+			if (parsed.platform) {
+				select(parsed.platform, false);
+			}
+			if (parsed.target) {
+				var el = document.getElementById(parsed.target);
+				if (el) {
+					el.scrollIntoView();
+				}
+			}
+		}
+
+		window.addEventListener("hashchange", jumpToHash);
+		if (parseHash().platform) {
+			jumpToHash();
+		}
+
+		/* ---- option filter ---- */
+
+		var filter = document.getElementById("optfilter");
+		var count = document.getElementById("optcount");
+		if (filter) {
+			var options = [].slice.call(document.querySelectorAll(".opt"));
+			options.forEach(function (opt) {
+				opt.dataset.haystack = opt.textContent.toLowerCase();
+			});
+			filter.addEventListener("input", function () {
+				var needle = filter.value.trim().toLowerCase();
+				var shown = 0;
+				options.forEach(function (opt) {
+					var hit = !needle || opt.dataset.haystack.indexOf(needle) !== -1;
+					opt.hidden = !hit;
+					shown += hit ? 1 : 0;
+				});
+				/* Fold away a tab whose options all filtered out. */
+				[].slice.call(document.querySelectorAll("section.tab")).forEach(function (section) {
+					section.hidden = needle !== "" &&
+						!section.querySelector(".opt:not([hidden])");
+				});
+				count.textContent = needle ? shown + " of " + options.length : "";
+			});
+		}
+	});
+})();

html/httrack.css

@@ -37,7 +37,7 @@ a:active  { text-decoration: underline; }
 	border-bottom: 6px solid #000;
 	padding: 10px;  padding-top: 20px;
 	line-height: 1.65em;
-	background-image: url(images/bg_rings.gif);
+	background-image: url(images/bg_rings.svg);
 	background-repeat: no-repeat;
 	background-position: top right;
 	}

html/httrack.man.html

@@ -777,8 +777,8 @@ information purpose only) (%q0 don’t include)
 <td width="82%">
 
 
-<p>*generate output html file in case of error (404..) (o0
-don&rsquo;t generate) (--generate-errors)</p></td></tr>
+<p>*save the server&rsquo;s error pages (404..) (o0 discard
+them) (--generate-errors)</p></td></tr>
 <tr valign="top" align="left">
 <td width="9%"></td>
 <td width="4%">

html/images/bg_rings.svg

@@ -0,0 +1,8 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="501" height="456" viewBox="0 0 501 456">
+<title>HTTrack rings</title>
+<!-- Transparent, unlike the GIF this replaces: the panel's own #ccd shows through. -->
+<g fill="#b9b9d0" fill-rule="evenodd">
+<path d="M614.59 346.3A323.36 197.55 21.16 1 0 11.46 112.89A323.36 197.55 21.16 1 0 614.59 346.3 ZM590.57 315.66A262.58 160.99 22.18 1 0 104.26 117.43A262.58 160.99 22.18 1 0 590.57 315.66 Z"/>
+<path d="M578.08 292.16A185.6 113.57 21.23 1 0 232.08 157.73A185.6 113.57 21.23 1 0 578.08 292.16 ZM564.4 274.56A150.77 92.55 22.26 1 0 285.34 160.32A150.77 92.55 22.26 1 0 564.4 274.56 Z"/>
+</g>
+</svg>