Follow <source>/<track> as embedded near-links (#451)

src/srcset are already extracted from any element via hts_detect[], so
<source>/<track> URLs were captured. But hts_detect_embed only listed
<img src>, so at the recursion-depth boundary under --near these media
were treated as plain links and dropped, unlike <img>. Add a separate
HTML5 media table (keeping the legacy one clang-format-stable) and chain
the embed lookup through both.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

src/htsglobal.h

@@ -229,6 +229,10 @@ Please visit our Website: http://www.httrack.com
 #define HTS_DEFAULT_FOOTER                                                     \
   "<!-- Mirrored from %s%s by HTTrack Website Copier/" HTTRACK_AFF_VERSION     \
   " " HTTRACK_AFF_AUTHORS ", %s -->"
+/* Honest crawler User-Agent; no fake OS/browser to go stale. */
+#define HTS_DEFAULT_USER_AGENT                                                 \
+  "Mozilla/5.0 (compatible; HTTrack/" HTTRACK_AFF_VERSION                      \
+  "; +https://www.httrack.com/)"
 #define HTTRACK_WEB "http://www.httrack.com"
 #define HTS_UPDATE_WEBSITE                                                     \
   "http://www.httrack.com/"                                                    \

src/htslib.c

@@ -563,6 +563,39 @@ const char *hts_mime[][2] = {
   {"", ""}
 };
 
+/* Modern web formats (post-2010), kept in their own table: appending to the
+   legacy hts_mime[] above makes clang-format reflow its whole initializer.
+   Scanned after hts_mime[], so it never shadows a legacy mapping. */
+static const char *hts_mime_modern[][2] = {
+    {"image/webp", "webp"},
+    {"image/avif", "avif"},
+    {"image/heic", "heic"},
+    {"font/woff", "woff"},
+    {"font/woff2", "woff2"},
+    {"font/ttf", "ttf"},
+    {"font/otf", "otf"},
+    {"application/json", "json"},
+    {"application/ld+json", "jsonld"},
+    {"application/manifest+json", "webmanifest"},
+    {"application/wasm", "wasm"},
+    {"text/javascript", "js"},
+    {"text/javascript", "mjs"},
+    {"text/markdown", "md"},
+    {"video/mp4", "mp4"},
+    {"video/webm", "webm"},
+    {"video/ogg", "ogv"},
+    {"video/mp2t", "ts"},
+    {"audio/mp4", "m4a"},
+    {"audio/aac", "aac"},
+    {"audio/ogg", "oga"},
+    {"audio/opus", "opus"},
+    {"audio/flac", "flac"},
+    {"audio/webm", "weba"},
+    {"application/x-7z-compressed", "7z"},
+    {"application/x-rar-compressed", "rar"},
+    {"application/zstd", "zst"},
+    {"", ""}};
+
 // Reserved (RFC2396)
 #define CIS(c,ch) ( ((unsigned char)(c)) == (ch) )
 #define CHAR_RESERVED(c)  ( CIS(c,';') \
@@ -4308,6 +4341,20 @@ void guess_httptype(httrackp * opt, char *s, const char *fil) {
   (void) get_httptype_sized(opt, s, HTS_MIMETYPE_SIZE, fil, 1);
 }
 
+// first match in a NUL-terminated {mime,ext} table. key selects the lookup
+// column (0=mime, 1=ext); returns the other column, or NULL if no row matches
+// (a "*" partner means the row carries no value).
+static const char *hts_mime_lookup(const char *(*table)[2], int key,
+                                   const char *needle) {
+  int j;
+
+  for (j = 0; strnotempty(table[j][1]); j++) {
+    if (strfield2(table[j][key], needle) && table[j][!key][0] != '*')
+      return table[j][!key];
+  }
+  return NULL;
+}
+
 // write the mime type for fil into s (capacity ssize)
 // flag: 1 to always return a type (the "application/..." / octet-stream
 // fallback) returns 1 if a type was written to s, 0 otherwise
@@ -4331,17 +4378,15 @@ HTSEXT_API hts_boolean get_httptype_sized(httrackp *opt, char *s, size_t ssize,
     while ((a > fil) && (*a != '.') && (*a != '/'))
       a--;
     if (a >= fil && *a == '.' && strlen(a) < 32) {
-      int j = 0;
+      const char *mime;
 
       a++;
-      while(strnotempty(hts_mime[j][1])) {
-        if (strfield2(hts_mime[j][1], a)) {
-          if (hts_mime[j][0][0] != '*') { // a match exists
-            strlcpybuff(s, hts_mime[j][0], ssize);
-            return 1;
-          }
-        }
-        j++;
+      mime = hts_mime_lookup(hts_mime, 1, a);
+      if (mime == NULL)
+        mime = hts_mime_lookup(hts_mime_modern, 1, a);
+      if (mime != NULL) {
+        strlcpybuff(s, mime, ssize);
+        return 1;
       }
 
       if (flag) {
@@ -4476,18 +4521,16 @@ int get_userhttptype(httrackp * opt, char *s, const char *fil) {
 // returns 1 if an extension was found (and written to s), 0 otherwise
 int give_mimext(char *s, size_t ssize, const char *st) {
   int ok = 0;
-  int j = 0;
+  const char *ext;
 
   st = hts_effective_mime(st); /* no declared type: derive an html ext */
   s[0] = '\0';
-  while((!ok) && (strnotempty(hts_mime[j][1]))) {
-    if (strfield2(hts_mime[j][0], st)) {
-      if (hts_mime[j][1][0] != '*') { // a match exists
-        strlcpybuff(s, hts_mime[j][1], ssize);
-        ok = 1;
-      }
-    }
-    j++;
+  ext = hts_mime_lookup(hts_mime, 0, st);
+  if (ext == NULL)
+    ext = hts_mime_lookup(hts_mime_modern, 0, st);
+  if (ext != NULL) {
+    strlcpybuff(s, ext, ssize);
+    ok = 1;
   }
   // wrap "x" mimetypes, such as:
   // application/x-mp3
@@ -6005,8 +6048,7 @@ HTSEXT_API httrackp *hts_create_opt(void) {
   opt->shell = HTS_FALSE;
   opt->proxy.active = 0;        // pas de proxy
   opt->user_agent_send = HTS_TRUE;
-  StringCopy(opt->user_agent,
-             "Mozilla/4.5 (compatible; HTTrack 3.0x; Windows 98)");
+  StringCopy(opt->user_agent, HTS_DEFAULT_USER_AGENT);
   StringCopy(opt->referer, "");
   StringCopy(opt->from, "");
   opt->savename_83 = HTS_SAVENAME_83_LONG; // long names by default

src/htsselftest.c

@@ -239,6 +239,14 @@ static void basic_selftests(void) {
     assertf(strcmp(ext, "html") == 0);
     assertf(give_mimext(ext, sizeof(ext), "no/such-mime-type") == 0);
     assertf(ext[0] == '\0');
+    // modern web formats -> extension. Avoid MIME types the
+    // application/<=4-char-subtype fallback could fabricate without a row.
+    assertf(give_mimext(ext, sizeof(ext), "image/webp") == 1);
+    assertf(strcmp(ext, "webp") == 0);
+    assertf(give_mimext(ext, sizeof(ext), "application/manifest+json") == 1);
+    assertf(strcmp(ext, "webmanifest") == 0);
+    assertf(give_mimext(ext, sizeof(ext), "font/woff2") == 1);
+    assertf(strcmp(ext, "woff2") == 0);
   }
   // convtolower(): lower-cases into the caller buffer (bounded by its size).
   {
@@ -293,6 +301,16 @@ static void basic_selftests(void) {
     assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
                                "x.gif", 0) == 1);
     assertf(strcmp(r.contenttype, "image/gif") == 0);
+    // modern extensions map back to their MIME type
+    assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
+                               "x.webp", 0) == 1);
+    assertf(strcmp(r.contenttype, "image/webp") == 0);
+    assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
+                               "app.wasm", 0) == 1);
+    assertf(strcmp(r.contenttype, "application/wasm") == 0);
+    assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
+                               "mod.mjs", 0) == 1);
+    assertf(strcmp(r.contenttype, "text/javascript") == 0);
     // no extension and flag==0: nothing written, returns 0
     assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
                                "noextfile", 0) == 0);
@@ -1284,6 +1302,22 @@ static int st_urlhack(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
+/* Default User-Agent: honest HTTrack token, no resurrected Windows 98. */
+static int st_useragent(httrackp *opt, int argc, char **argv) {
+  const char *ua = StringBuff(opt->user_agent);
+  (void) argc;
+  (void) argv;
+  assertf(ua != NULL);
+  assertf(strcmp(ua, HTS_DEFAULT_USER_AGENT) == 0);
+  /* Teeth independent of the macro: honest token + self-identifier, and no
+     legacy Mozilla/4.x fake-browser string (rejects the whole relic family). */
+  assertf(strstr(ua, "HTTrack/") != NULL);
+  assertf(strstr(ua, "+https://www.httrack.com/") != NULL);
+  assertf(strstr(ua, "Mozilla/4.") == NULL);
+  printf("useragent self-test OK: %s\n", ua);
+  return 0;
+}
+
 /* ------------------------------------------------------------ */
 /* Registry: name -> handler, with a usage hint and a one-line description. */
 /* ------------------------------------------------------------ */
@@ -1330,6 +1364,7 @@ static const struct selftest_entry {
      st_cache_writefail},
     {"dns", "", "DNS resolver/cache self-test", st_dns},
     {"cookies", "", "cookie request-header self-test", st_cookies},
+    {"useragent", "", "default User-Agent self-test", st_useragent},
 };
 
 static void list_selftests(void) {

src/htsserver.c

@@ -358,12 +358,12 @@ int smallserver(T_SOC soc, char *url, char *method, char *data, char *path) {
       {NULL, 0}
     };
     initStrElt initStr[] = {
-      {"user", "Mozilla/4.5 (compatible; HTTrack 3.0x; Windows 98)"},
-      {"footer",
-       "<!-- Mirrored from %s%s by HTTrack Website Copier/3.x [XR&CO'2014], %s -->"},
-      {"url2", "+*.png +*.gif +*.jpg +*.jpeg +*.css +*.js -ad.doubleclick.net/*"},
-      {NULL, NULL}
-    };
+        {"user", HTS_DEFAULT_USER_AGENT},
+        {"footer", "<!-- Mirrored from %s%s by HTTrack Website Copier/3.x "
+                   "[XR&CO'2014], %s -->"},
+        {"url2",
+         "+*.png +*.gif +*.jpg +*.jpeg +*.css +*.js -ad.doubleclick.net/*"},
+        {NULL, NULL}};
     int i = 0;
 
     for(i = 0; initInt[i].name; i++) {

src/htswizard.c

@@ -80,6 +80,10 @@ htspair_t hts_detect_embed[] = {
   {NULL, NULL}
 };
 
+/* HTML5 media siblings of <img src>: same near-link treatment (#451) */
+static const htspair_t hts_detect_embed_html5[] = {
+    {"source", "src"}, {"source", "srcset"}, {"track", "src"}, {NULL, NULL}};
+
 /* Internal */
 static int hts_acceptlink_(httrackp * opt, int ptr, const char *adr,
                            const char *fil, const char *tag,
@@ -136,6 +140,17 @@ static int cmp_token(const char *tag, const char *cmp) {
           && !isalnum((unsigned char) tag[p]));
 }
 
+/* TRUE if (tag, attribute) matches an embedded-asset pair in the table */
+static hts_boolean is_embed_pair(const htspair_t *table, const char *tag,
+                                 const char *attribute) {
+  int i;
+  for (i = 0; table[i].tag != NULL; i++) {
+    if (cmp_token(tag, table[i].tag) && cmp_token(attribute, table[i].attr))
+      return HTS_TRUE;
+  }
+  return HTS_FALSE;
+}
+
 static int hts_acceptlink_(httrackp * opt, int ptr,
                            const char *adr, const char *fil, const char *tag,
                            const char *attribute, int *set_prio_to,
@@ -163,15 +178,9 @@ static int hts_acceptlink_(httrackp * opt, int ptr,
 
   /* Built-in known tags (<img src=..>, ..) */
   if (forbidden_url != 0 && opt->nearlink && tag != NULL && attribute != NULL) {
-    int i;
-
-    for(i = 0; hts_detect_embed[i].tag != NULL; i++) {
-      if (cmp_token(tag, hts_detect_embed[i].tag)
-          && cmp_token(attribute, hts_detect_embed[i].attr)
-        ) {
-        embedded_triggered = 1;
-        break;
-      }
+    if (is_embed_pair(hts_detect_embed, tag, attribute) ||
+        is_embed_pair(hts_detect_embed_html5, tag, attribute)) {
+      embedded_triggered = 1;
     }
   }
 

tests/01_engine-parse.test

@@ -323,4 +323,33 @@ grep -Fq 'href="ahref%20(4).gif"' "$saved9" ||
 ! grep -Eq '(src|href)="[^"]*%28' "$saved9" ||
     ! echo "FAIL #163: gate over-fired onto a non-url() attribute link" || exit 1
 
+# HTML5 <source>/<track> follow as embedded near-links past the -r2 depth boundary (#451).
+# img.gif positive control; plain.gif (bare <a href>) negative control proves the gate is selective.
+site10="$tmp/html5media"
+mkdir -p "$site10"
+for f in img ss plain; do gif "$site10/$f.gif"; done
+printf 'x' >"$site10/v.webm"
+printf 'x' >"$site10/subs.vtt"
+cat >"$site10/index.html" <<EOF
+<html><body><a href="leaf.html">leaf</a></body></html>
+EOF
+cat >"$site10/leaf.html" <<EOF
+<html><body>
+<img src="img.gif">
+<picture><source srcset="ss.gif 2x"></picture>
+<video><source src="v.webm"></video>
+<video><track src="subs.vtt"></video>
+<a href="plain.gif">plain link past the boundary</a>
+</body></html>
+EOF
+out10="$tmp/html5media-out"
+rm -rf "$out10"
+mkdir -p "$out10"
+httrack "file://$site10/index.html" -O "$out10" --quiet --near -r2 >"$out10/.log" 2>&1 || true
+found "img.gif" "$out10"
+found "ss.gif" "$out10"
+found "v.webm" "$out10"
+found "subs.vtt" "$out10"
+notfound "plain.gif" "$out10"
+
 exit 0

tests/01_engine-useragent.test

@@ -0,0 +1,7 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# Default User-Agent (#449): honest HTTrack token, no Windows 98 relic.
+httrack -O /dev/null -#test=useragent run | grep -q "useragent self-test OK"

tests/Makefile.am

@@ -50,6 +50,7 @@ TESTS = \
 	01_engine-stripquery.test \
 	01_engine-strsafe.test \
 	01_engine-urlhack.test \
+	01_engine-useragent.test \
 	02_manpage-regen.test \
 	02_update-cache.test \
 	10_crawl-simple.test \