WARC: file the --warc help under Log/index/cache, not Build (#679)

WARC is a transaction-level archive of what was fetched (a sibling of the
hts-cache), not a browsable-mirror build format like MHTML, so it belongs in
the Log/index/cache group next to the cache options. Help text only; the
webhttrack GUI already places it on the Log/Index/Cache tab (option9).

Signed-off-by: Xavier Roche <xroche@gmail.com>
Signed-off-by: Xavier Roche <roche@httrack.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.github/workflows/windows-build.yml

@@ -202,7 +202,8 @@ jobs:
 
           # 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.
-          expected_skips=" 48_local-crange-memresume.test 71_local-crange-repaircache.test"  # pending #581
+          # footer-overflow skips on Windows (needs a path past MAX_PATH); crange pending #581.
+          expected_skips=" 01_engine-footer-overflow.test 48_local-crange-memresume.test 71_local-crange-repaircache.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; }

html/abuse.html

@@ -217,7 +217,7 @@ school or
 shows. They might do that because they are connected through expensive modem connection,
 or because they would like to consult pages while travelling, or archive sites that may be
 removed
-one day, make some data mining, comiling information ("if only I could find this
+one day, make some data mining, compiling information ("if only I could find this
 website I saw one day..&quot;). <br>
 There are many good reasons to mirror websites, and this helps many good people.<br>
 As a webmaster, you might be interested to use such tools, too: test broken links, move a
@@ -229,7 +229,7 @@ test the webserver response and performances, index it..<br>
 Anyway, bandwidth abuse can be a problem. If your site is regularly &quot;clobbered&quot;
 by evil downloaders, you have <br>
 various solutions. You have radical solutions, and intermediate solutions. I strongly
-recomment not to use<br>
+recommend not to use<br>
 radical solutions, because of the previous remarks (good people often mirror websites).<br>
 <br>
 In general, for all solutions,<br>
@@ -244,7 +244,7 @@ or, to be extreme: if you unplug the wire, there will be no bandwidth abuse<br>
 Good: Will work with good people. Many good people just don't KNOW that they can slow down
 a network.<br>
 Bad: Will **only** work with good people<br>
-How to do: Obvious - place a note, a warning, an article, a draw, a poeme or whatever you
+How to do: Obvious - place a note, a warning, an article, a draw, a poem or whatever you
 want<br>
 <br>
 </li><li>Use &quot;robots.txt&quot; file<br>
@@ -266,7 +266,7 @@ Good: Efficient<br>
 Bad: Multiple users behind proxies will be slow down, not really easy to setup<br>
 How to do: Depends on webserver. Might be done with low-level IP rules (QoS)<br>
 <br>
-</li><li>Priorize small files, against large files<br>
+</li><li>Prioritize small files, against large files<br>
 Good: Efficient if large files are the cause of abuse<br>
 Bad: Not always efficient<br>
 How to do: Depends on the webserver<br>
@@ -283,7 +283,7 @@ How to do: Use routine QoS (fair queuing), or webserver options<br>
 <br>
 </li><li>Use technical tricks (like javascript) to hide URLs<br>
 Good: Efficient<br>
-Bad: The most efficient tricks will also cause your website to he heavy, and not
+Bad: The most efficient tricks will also cause your website to be heavy, and not
 user-friendly (and therefore less attractive, even for surfing users). Remember: clients
 or visitors might want to consult offline your website. Advanced users will also be still
 able to note the URLs and catch them. Will not work on non-javascript browsers. It will
@@ -335,7 +335,7 @@ Example: Use things like
 </li><li>Use technical tricks to temporarily ban IPs<br>
 Good: Efficient<br>
 Bad: Radical (your site will only be available online for all users), not easy to setup<br>
-How to to: Create fake links with &quot;killing&quot; targets<br>
+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>
@@ -417,7 +417,7 @@ Example:<br>
 </li><li>Another one is to create images of emails<br>
 Good: Efficient, does not require javascript<br>
 Bad: There is still the problem of the link (mailto:), images are bigger than text, and it can cause problems for blind people (a good solution is use an ALT attribute with the email written like "smith at mycompany dot com")<br>
-How to do: Not so obvious of you do not want to create images by yourself<br>
+How to do: Not so obvious if you do not want to create images by yourself<br>
 Example: (php, Unix)<br>
 
 <tt>
@@ -491,7 +491,7 @@ echo <br>
 </li><li>You can also create temporary email aliases, each week, for all users<br>
 Good: Efficient, and you can give your real email in your reply-to address<br>
 Bad: Temporary emails<br>
-How to do: Not so hard todo<br>
+How to do: Not so hard to do<br>
 Example: (script &amp; php, Unix)<br>
 
 <tt>

html/cmddoc.html

@@ -1,157 +0,0 @@
-<html xmlns="http://www.w3.org/1999/xhtml" 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>
-
-</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>Command-Line Documentation</em></h2>
-
-<br>
-
-The command-line version
-
-<ul>
-  <li><a href="cmdguide.html">Command-line Guide</a></li>
-  <br>A task-oriented guide: how to do the common things, and the defaults that surprise newcomers<br><br>
-  <li><a href="options.html">Command line Options</a></li>
-  <br>List of all powerful command line options<br><br>
-  <li>How to use httrack command-line version:</li>
-  <ul>
-    <li>Open a shell window</li>
-      <br>
-      <br>
-    <li>Type in <tt>httrack</tt> (or the complete path to the httrack executable)</li>
-      <br><small><tt>httrack</tt></small>
-      <br>
-      <br>
-    <li>Add the URLs, separated by a blank space</li>
-      <br><small><tt>httrack www.example.com/foo/</tt></small>
-      <br>
-      <br>
-    <li>If you need, add some options (see the <a href="options.html">option list</a>)</li>
-      <br><small><tt>httrack www.example.com/foo/ -O "/webs" -N4 -P proxy.myhost.com:3128</tt></small>
-      <br>
-      <br>
-    <li>Launch the command line, and wait until the mirror is finishing</li>
-      <br><small>You can (especially on the Unix release) press ^C to stop the mirror or put httrack in background</small>
-      <br>
-      <br>
-  </ul>
-</ul>
-
-<!-- ==================== 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>
-
-</html>
-

html/cmdguide.html

@@ -323,10 +323,18 @@ options control what HTTrack says about itself.</p>
   <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>
-  <tr><td><tt>--footer (-%F)</tt></td><td>A footer written into saved pages (on disk, not a network header).</td></tr>
+  <tr><td><tt>--footer (-%F)</tt></td><td>A footer written into saved pages (on disk, not a network header). See <b>Footer fields</b> below.</td></tr>
   <tr><td><tt>--cookies (-b), --cookies-file (-%K)</tt></td><td>Accept cookies, and preload a Netscape <tt>cookies.txt</tt>.</td></tr>
 </table>
 
+<p><b>Footer fields.</b> A footer with no <tt>%s</tt> may reference named fields:
+<tt>{addr}</tt>, <tt>{path}</tt>, <tt>{url}</tt>, <tt>{date}</tt> (mirror time),
+<tt>{lastmodified}</tt> (the page's Last-Modified), <tt>{version}</tt>,
+<tt>{mime}</tt>, <tt>{charset}</tt>, <tt>{status}</tt> and <tt>{size}</tt>; write
+<tt>{{</tt> or <tt>}}</tt> for a literal brace. A footer that contains <tt>%s</tt>
+keeps the older positional form (host, path, date in that order). Example:
+<tt>-%F "&lt;!-- Mirrored from {url} on {date} --&gt;"</tt>.</p>
+
 <p><b>Login.</b> For HTTP Basic auth, put the credentials in the URL:
 <tt>http://user:pass@host/</tt>. An <tt>@</tt> inside the username must be written
 <tt>%40</tt>. Only Basic is supported, not Digest.</p>

html/faq.html

@@ -3,7 +3,7 @@
 <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 vista, windows seven, windows 8, solaris, ibm580, AIX 4.0, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
+	<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">
@@ -135,9 +135,7 @@ clear language!
 
 <li><a href="#QG2">Where can I find French/other languages documentation?</a><br></li>
 
-<li><a href="#QG3b">Is HTTrack working on Windows Vista/Windows Seven/Windows 8 ?</a><br></li>
-
-<li><a href="#QG3">Is HTTrack working on Windows 95/98 ?</a><br></li>
+<li><a href="#QG3">Which systems does HTTrack run on?</a><br></li>
 
 <li><a href="#QG4">What's the difference between HTTrack, WinHTTrack and WebHTTrack?</a><br></li>
 
@@ -320,10 +318,10 @@ This can easily done by using filters: go to the Option panel, select the 'Scan
 <tt>+www.example.com/gallery/trees/*<br>
 +www.example.com/photos/*</tt><br>
 <br>
-This means "accept all links begining with <tt>www.example.com/gallery/trees/</tt> and <tt>www.example.com/photos/</tt>" 
+This means "accept all links beginning with <tt>www.example.com/gallery/trees/</tt> and <tt>www.example.com/photos/</tt>" 
 - the <tt>+</tt> means "accept" and the final <tt>*</tt> means "any character will match after the previous ones".
 Remember the <tt>*.doc</tt> or <tt>*.zip</tt> encountered when you want to select all files from a certain type on your computer: 
-it is almost the same here, except the begining "+"<br>
+it is almost the same here, except the beginning "+"<br>
 <br>
 Now, we might want to exclude all links in <tt>www.example.com/gallery/trees/hugetrees/</tt>, because with the previous filter,
 we accepted too many files. Here again, you can add a filter rule to refuse these links. Modify the previous filters to:<br>
@@ -331,8 +329,8 @@ we accepted too many files. Here again, you can add a filter rule to refuse thes
 +www.example.com/photos/*<br>
 -www.example.com/gallery/trees/hugetrees/*</tt><br>
 <br>
-You have noticed the <tt>-</tt> in the begining of the third rule: this means "refuse links matching the rule" 
-; and the rule is "any files begining with <tt>www.example.com/gallery/trees/hugetrees/</tt><br>
+You have noticed the <tt>-</tt> in the beginning of the third rule: this means "refuse links matching the rule" 
+; and the rule is "any files beginning with <tt>www.example.com/gallery/trees/hugetrees/</tt><br>
 
 Voila! With these three rules, you have precisely defined what you wanted to capture.<br>
 <br>
@@ -361,12 +359,12 @@ You can freely download it, without paying any fees, copy it to your friends, an
 There are NO official/authorized resellers, because HTTrack is <b>NOT</b> a commercial product.
 But you can be charged for duplication fees, or any other services (example: software CDroms or shareware collections, or fees for maintenance), 
 but you should have been informed that the software was free software/GPL, and you <b><u>MUST</u></b> have received a copy of the GNU General Public License.
-Otherwise this is dishonnest and unfair (ie. selling httrack on ebay without telling that it was a free software is a scam).
+Otherwise this is dishonest and unfair (ie. selling httrack on ebay without telling that it was a free software is a scam).
 </em>
 
 <br><br><a NAME="QG0b">Q: <strong>Are there any risks of viruses with this software?</strong></a><br>
 A: <em>For the software itself: 
-All official releases (at httrack.com) are checked against all known viruses, and the packaging process is also checked. Archives are stored on Un*x servers, not really concerned by viruses. It has been reported, however, that some rogue freeware sites are embedding free softwares and freewares inside badware installers. Always download httrack from the main site (www.httrack.com), and never from an untrusted source!<br>
+All official releases (at httrack.com) are checked against all known viruses, and the packaging process is also checked. Archives are stored on Un*x servers, not really concerned by viruses. It has been reported, however, that some rogue freeware sites are embedding free software and freeware inside badware installers. Always download httrack from the main site (www.httrack.com), and never from an untrusted source!<br>
 For files you are downloading on the WWW using HTTrack: You may encounter websites which were corrupted by viruses, and downloading data on these websites might be dangerous if you execute downloaded executables, or if embedded pages contain infected material (as dangerous as if using a regular Browser). Always ensure that websites you are crawling are safe.
  (Note: remember that using an antivirus software is a good idea once you are connected to the Internet)</em>
 
@@ -376,11 +374,8 @@ A: <em>That's right. You can, however, install WinHTTrack on your own machine, a
 <br><br><a NAME="QG2">Q: <strong>Where can I find French/other languages documentation?</strong></a><br>
 A: <em>Windows interface is available on several languages, but not yet the documentation!</em>
 
-<br><br><a NAME="QG3b">Q: <strong>Is HTTrack working on Windows Vista/Windows Seven/Windows 8 ?</strong></a><br>
-A: <em>Yes, it does</em>
-
-<br><br><a NAME="QG3">Q: <strong>Is HTTrack working on Windows 95/98 ?</strong></a><br>
-A: <em>No, not anymore. You may try to pick an older release (such as 3.33)</em>
+<br><br><a NAME="QG3">Q: <strong>Which systems does HTTrack run on?</strong></a><br>
+A: <em>HTTrack runs on current Windows, Linux and other Unix-like systems, and macOS. Very old platforms such as Windows 95/98 are no longer supported; you may try an older release (such as 3.33) on those.</em>
 
 <br><br><a NAME="QG4">Q: <strong>What's the difference between HTTrack, WinHTTrack and WebHTTrack?</strong></a><br>
 A: <em>WinHTTrack is the Windows GUI release of HTTrack (with a native graphic shell) and WebHTTrack is the Linux/Posix release of HTTrack (with an html graphic shell)</em>
@@ -394,7 +389,7 @@ A: <em>It should. The <tt>configure.ac</tt> may be modified in some cases, howev
 <br><br><a NAME="QG7">Q: <strong>I use HTTrack for professional purpose. What about restrictions/license fee?</strong></a><br>
 A: <em>HTTrack is covered by the GNU General Public License (GPL). There is no restrictions using HTTrack for professional purpose, 
 except if you develop a software which uses HTTrack components (parts of the source, or any other component).
-See the <tt>license.txt</tt> file for more information</em>. See also the next question regarding copyright issues when reditributing downloaded material.
+See the <tt>license.txt</tt> file for more information</em>. See also the next question regarding copyright issues when redistributing downloaded material.
 
 <br><br><a NAME="QG7b">Q: <strong>Is there any license royalties for distributing a mirror made with HTTrack?</strong></a><br>
 A: <em>On the HTTrack side, no. However, sharing, publishing or reusing copyrighted material downloaded from a site requires the authorization of the copyright holders, and possibly paying royalty fees. Always ask the authorization before creating a mirror of a site, even if the site appears to be royalty-free and/or without copyright notice.</em>
@@ -415,7 +410,7 @@ There are several reasons (and solutions) for a mirror to fail. Reading the log
 
 <ul>
  <li>Links within the site refers to external links, or links located in another (or upper) directories, not captured by default - the use of filters is generally THE solution, as this is one of the powerful option in HTTrack. <u>See the above questions/answers</u>.</li>
- <li>Website <a href="#Q1b1">'robots.txt' rules</a> forbide access to several website parts - you can disable them, but only with great care!</li>
+ <li>Website <a href="#Q1b1">'robots.txt' rules</a> forbid access to several website parts - you can disable them, but only with great care!</li>
  <li>HTTrack is filtered (by its default User-agent IDentity) - you can change the Browser User-Agent identity to an anonymous one (MSIE, Netscape..) - here again, use this option with care, as this measure might have been put to avoid some bandwidth abuse (see also the <a href="abuse.html">abuse faq</a>!)</li>
 </ul>
 
@@ -457,14 +452,14 @@ A: <em>Yes, HTTrack does support (since 3.20 release) ipv6 sites, using A/AAAA e
 A: <em>Check the build options (you may have selected user-defined structure with wrong parameters!)</em>
 
 <br><br><a NAME="QT5">Q: <strong>When capturing real audio/video links (.ram), I only get a shortcut!</a></strong></a></br>
-A: <em>Yes, but .ra/.rm associated file should be captured together - except if rtsp:// protocol is used (not supported by HTTrack yet), or if proper filters are needed</em>
+A: <em>The .ra/.rm associated file can be captured together with the shortcut, if proper filters are set. Streaming protocols such as rtsp:// are out of scope: HTTrack is an HTTP/FTP mirror and does not capture rtsp streams.</em>
 
 <br><br><a NAME="QT6">Q: <strong>Using user:password@address is not working!</a></strong></a></br>
 A: <em>Again, first check the <tt>hts-log.txt</tt> and <tt>hts-err.txt</tt> error log files - this can give you precious information<br>
 The site may have a different authentication scheme - form based authentication, for example.
 In this case, use the URL capture features of HTTrack, it might work.
 <br>Note: If your username and/or password contains a '<tt>@</tt>' character, you may have to replace all '<tt>@</tt>' 
-occurences by '<tt>%40</tt>' so that it can work, such as in <tt>user%40domain.com:foobar@www.foo.com/auth/. 
+occurrences by '<tt>%40</tt>' so that it can work, such as in <tt>user%40domain.com:foobar@www.foo.com/auth/. 
 You may have to do the same for all "special" characters like spaces (%20), quotes (%22)..</tt>
 </em>
 <br><br>
@@ -520,7 +515,7 @@ These rules, stored in a file called robots.txt, are given by the website, to sp
 - for example, /cgi-bin or large images files.
 They are followed by default by HTTrack, as it is advised. Therefore, you may miss some files that would have been downloaded without
 these rules - check in your logs if it is the case:<br>
-<tt>Info: Note: due to www.foobar.com remote robots.txt rules, links begining with these path will be forbidden: /cgi-bin/,/images/ (see in the options to disable this)
+<tt>Info: Note: due to www.foobar.com remote robots.txt rules, links beginning with these path will be forbidden: /cgi-bin/,/images/ (see in the options to disable this)
 </tt>
 <br>
 If you want to disable them, just change the corresponding option in the option list! (but only disable this option with great care, 
@@ -540,7 +535,7 @@ HTTrack must find one. Therefore, two index.html will be produced, one with the
 <br>
 It might be a good idea to consider that http://www.foobar.com/ and http://www.foobar.com/index.html are the same links, to avoid
 duplicate files, isn't it?
-NO, because the top index (/) can refer to ANY filename, and if index.html is generally the default name, index.htm can be choosen,
+NO, because the top index (/) can refer to ANY filename, and if index.html is generally the default name, index.htm can be chosen,
 or index.php3, mydog.jpg, or anything you may imagine. (some webmasters are really crazy)
 <br>
 <br>
@@ -595,8 +590,7 @@ A: <em>Simply use the <tt>--assume dat=application/x-zip</tt> option
 A: <em>You may need cookies! Cookies are specific data (for example, your username or password) that are sent to your browser once
 you have logged in certain sites so that you only have to log-in once. For example, after having entered your username in a website, you can
 view pages and articles, and the next time you will go to this site, you will not have to re-enter your username/password.<br>
-To "merge" your personnal cookies to an HTTrack project, just copy the cookies.txt file from your Netscape folder (or the cookies located into the Temporary Internet Files folder for IE)
-into your project folder (or even the HTTrack folder)
+To supply your own cookies to an HTTrack project, put a Netscape-format <tt>cookies.txt</tt> file in your project folder, or point HTTrack at one with the <tt>--cookies-file</tt> option. You can export your browser's session cookies to that format with a browser extension.
 </em>
 <br>
 <br>
@@ -661,7 +655,7 @@ Shell version, skip some slow files, too.</em><br>
 
 </a><a NAME="Q3b">Q: <strong>I want to update a site, but it's taking too much time! What's happening?</strong><br>
 A: <em>First, HTTrack always tries to minimize the download flow by interrogating the server about the
-file changes. But, because HTTrack has to rescan all files from the begining to rebuild the local site structure, 
+file changes. But, because HTTrack has to rescan all files from the beginning to rebuild the local site structure, 
 it can take some time. 
 Besides, some servers are not very smart and always consider that they get newer files, forcing HTTrack to reload them,
 even if no changes have been made!
@@ -740,7 +734,7 @@ retransferred.</em><br>
 </a><a NAME="Q7">Q: <strong>I just want to retrieve all ZIP files or other files in a web
 site/in a page. How do I do it?</strong><br>
 A: <em>You can use different methods. You can use the 'get files near a link' option if
-files are in a foreign domain. You can use, too, a filter adress: adding <tt>+*.zip</tt>
+files are in a foreign domain. You can use, too, a filter address: adding <tt>+*.zip</tt>
 in the URL list (or in the filter list) will accept all ZIP files, even if these files are
 outside the address. <br>
 Example : <tt>httrack www.example.com/someaddress.html +*.zip</tt> will allow

html/filters.html

@@ -111,7 +111,7 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
     starts links, the default mode is to mirror these links - i.e. if one of your start page is
     www.example.com/test/index.html, all links starting with www.example.com/test/ will be
     accepted. But links directly in www.example.com/.. will not be accepted, however, because
-    they are in a higher strcuture. This prevent HTTrack from mirroring the whole site. (All
+    they are in a higher structure. This prevent HTTrack from mirroring the whole site. (All
     files in structure levels equal or lower than the primary links will be retrieved.)<br>
     </i>
     <br>
@@ -127,13 +127,15 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
     an authorization filter, like <b><tt>+*.gif</tt></b>. The pattern is a plus (this one: <b><tt>+</tt></b>),
     followed by a pattern composed of letters and wildcards (this one: <b><tt>*</tt></b>). 
     <br><br>
-    To forbide a family of links, define
+    To forbid a family of links, define
     an authorization filter, like <b><tt>-*.gif</tt></b>. The pattern is a dash (this one: <b><tt>-</tt></b>),
     followed by a the same kind of pattern as for the authorization filter.
     <br><br>
     Example: +*.gif will accept all files finished by .gif<br>
     Example: -*.gif will refuse all files finished by .gif<br>
     <br>
+    To see which rule accepted or blocked a given URL, run HTTrack with the <b><tt>--why</tt></b> (<b><tt>-%Y</tt></b>) option, described in <a href="httrack.man.html#OPTIONS">the manual page</a>.<br>
+    <br>
     
 <p>    
     <h4>Scan rules based on size (e.g. accept or refuse files bigger/smaller than a certain size)</h4>
@@ -143,7 +145,7 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
     size to ensure that you won't reach a defined limit.
     
     Example: You may want to accept all files on the domain www.example.com, using '+www.example.com/*', 
-    including gif files inside this domain and outside (eternal images), but not take to large images, 
+    including gif files inside this domain and outside (external images), but not take to large images, 
     or too small ones (thumbnails)<br>
     Excluding gif images smaller than 5KB and images larger than 100KB is therefore a good option;
     +www.example.com +*.gif -*.gif*[<5] -*.gif*[>100] 

html/httrack.man.html

@@ -100,16 +100,17 @@ offline browser : copy websites to a local directory</p>
 ] [ <b>-%Y, --why</b> ] [ <b>-u, --check-type[=N]</b> ] [
 <b>-j, --parse-java[=N]</b> ] [ <b>-sN, --robots[=N]</b> ] [
 <b>-%h, --http-10</b> ] [ <b>-%k, --keep-alive</b> ] [
-<b>-%B, --tolerant</b> ] [ <b>-%s, --updatehack</b> ] [
-<b>-%u, --urlhack</b> ] [ <b>-%A, --assume</b> ] [ <b>-@iN,
---protocol[=N]</b> ] [ <b>-%w, --disable-module</b> ] [
-<b>-F, --user-agent</b> ] [ <b>-%R, --referer</b> ] [
-<b>-%E, --from</b> ] [ <b>-%F, --footer</b> ] [ <b>-%l,
---language</b> ] [ <b>-%a, --accept</b> ] [ <b>-%X,
---headers</b> ] [ <b>-C, --cache[=N]</b> ] [ <b>-k,
---store-all-in-cache</b> ] [ <b>-%n, --do-not-recatch</b> ]
-[ <b>-%v, --display</b> ] [ <b>-Q, --do-not-log</b> ] [
-<b>-q, --quiet</b> ] [ <b>-z, --extra-log</b> ] [ <b>-Z,
+<b>-%z, --disable-compression</b> ] [ <b>-%B, --tolerant</b>
+] [ <b>-%s, --updatehack</b> ] [ <b>-%u, --urlhack</b> ] [
+<b>-%A, --assume</b> ] [ <b>-@iN, --protocol[=N]</b> ] [
+<b>-%w, --disable-module</b> ] [ <b>-F, --user-agent</b> ] [
+<b>-%R, --referer</b> ] [ <b>-%E, --from</b> ] [ <b>-%F,
+--footer</b> ] [ <b>-%l, --language</b> ] [ <b>-%a,
+--accept</b> ] [ <b>-%X, --headers</b> ] [ <b>-C,
+--cache[=N]</b> ] [ <b>-k, --store-all-in-cache</b> ] [
+<b>-%r, --warc</b> ] [ <b>-%n, --do-not-recatch</b> ] [
+<b>-%v, --display</b> ] [ <b>-Q, --do-not-log</b> ] [ <b>-q,
+--quiet</b> ] [ <b>-z, --extra-log</b> ] [ <b>-Z,
 --debug-log</b> ] [ <b>-v, --verbose</b> ] [ <b>-f,
 --file-log</b> ] [ <b>-f2, --single-log</b> ] [ <b>-I,
 --index</b> ] [ <b>-%i, --build-top-index</b> ] [ <b>-%I,
@@ -121,7 +122,8 @@ offline browser : copy websites to a local directory</p>
 ] [ <b>-e, --go-everywhere</b> ] [ <b>-%H,
 --debug-headers</b> ] [ <b>-%!,
 --disable-security-limits</b> ] [ <b>-V, --userdef-cmd</b> ]
-[ <b>-%W, --callback</b> ] [ <b>-K, --keep-links[=N]</b>
+[ <b>-%W, --callback</b> ] [ <b>-y,
+--background-on-suspend</b> ] [ <b>-K, --keep-links[=N]</b>
 ]</p>
 
 <h2>DESCRIPTION
@@ -646,6 +648,18 @@ don&rsquo;t wait) (--cached-delayed-type-check)</p></td></tr>
 <td width="4%">
 
 
+<p>-%t</p></td>
+<td width="5%"></td>
+<td width="82%">
+
+
+<p>keep the original file extension, don&rsquo;t rewrite it
+from the MIME type (%t0 rewrite)</p></td></tr>
+<tr valign="top" align="left">
+<td width="9%"></td>
+<td width="4%">
+
+
 <p>-LN</p></td>
 <td width="5%"></td>
 <td width="82%">
@@ -878,6 +892,18 @@ for small files and test requests (%k0 don&rsquo;t use)
 <td width="4%">
 
 
+<p>-%z</p></td>
+<td width="5%"></td>
+<td width="82%">
+
+
+<p>do not request compressed content (%z0 request)
+(--disable-compression)</p> </td></tr>
+<tr valign="top" align="left">
+<td width="9%"></td>
+<td width="4%">
+
+
 <p>-%B</p></td>
 <td width="5%"></td>
 <td width="82%">
@@ -1023,9 +1049,10 @@ headers (-F &quot;user-agent name&quot;) (--user-agent
 <td width="82%">
 
 
-<p>footer string in Html code (-%F &quot;Mirrored [from
-host %s [file %s [at %s]]]&quot; (--footer
-&lt;param&gt;)</p> </td></tr>
+<p>footer string in Html code (-%F &quot;Mirrored from
+{url} on {date}&quot;; fields {addr} {path} {url} {date}
+{lastmodified} {version} {mime} {charset} {status} {size},
+or legacy %s) (--footer &lt;param&gt;)</p></td></tr>
 <tr valign="top" align="left">
 <td width="9%"></td>
 <td width="4%">
@@ -1102,6 +1129,20 @@ update before) (--cache[=N])</p></td></tr>
 <td width="4%">
 
 
+<p>-%r</p></td>
+<td width="5%"></td>
+<td width="82%">
+
+
+<p>write an ISO-28500 WARC/1.1 archive; --warc-file NAME
+sets the output name, --warc-max-size N rotates segments
+past N bytes, --warc-cdx also writes a sorted CDXJ index,
+--wacz packages it all as a WACZ file (--warc)</p></td></tr>
+<tr valign="top" align="left">
+<td width="9%"></td>
+<td width="4%">
+
+
 <p>-%n</p></td>
 <td width="5%"></td>
 <td width="82%">
@@ -1383,25 +1424,13 @@ p7 get html files before, then treat other files</p>
 <td width="8%">
 
 
-<p style="margin-top: 1em">-#X</p></td>
+<p style="margin-top: 1em">-#test</p></td>
 <td width="1%"></td>
 <td width="82%">
 
 
-<p style="margin-top: 1em">*use optimized engine (limited
-memory boundary checks) (--fast-engine)</p></td></tr>
-<tr valign="top" align="left">
-<td width="9%"></td>
-<td width="8%">
-
-
-<p>-#test</p></td>
-<td width="1%"></td>
-<td width="82%">
-
-
-<p>list engine self-tests (run one with -#test=NAME
-[args])</p> </td></tr>
+<p style="margin-top: 1em">list engine self-tests (run one
+with -#test=NAME [args])</p></td></tr>
 <tr valign="top" align="left">
 <td width="9%"></td>
 <td width="8%">
@@ -1532,17 +1561,6 @@ memory boundary checks) (--fast-engine)</p></td></tr>
 <td width="8%">
 
 
-<p>-#R</p></td>
-<td width="1%"></td>
-<td width="82%">
-
-
-<p>old FTP routines (debug) (--repair-cache)</p></td></tr>
-<tr valign="top" align="left">
-<td width="9%"></td>
-<td width="8%">
-
-
 <p>-#T</p></td>
 <td width="1%"></td>
 <td width="82%">
@@ -1633,6 +1651,18 @@ each files ($0 is the filename: -V &quot;rm \$0&quot;)
 
 <p>use an external library function as a wrapper (-%W
 myfoo.so[,myparameters]) (--callback &lt;param&gt;)</p></td></tr>
+<tr valign="top" align="left">
+<td width="9%"></td>
+<td width="4%">
+
+
+<p>-y</p></td>
+<td width="5%"></td>
+<td width="82%">
+
+
+<p>go to background when suspended (y0 don&rsquo;t)
+(--background-on-suspend)</p> </td></tr>
 </table>
 
 <h3>Details: Option N

html/index.html

@@ -109,12 +109,12 @@ h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
   <li>How to Use</li>
   <ul>
     <li><a href="shelldoc.html">WinHTTrack/WebHTTrack (GUI version for Windows or Linux/Unix)</a></li>
-    <br>HTTrack GUI documentation, with step-by-step example, for the Windows release (WinHTTrack) and the Linux/Unix relese (WebHTTrack)<br>
+    <br>HTTrack GUI documentation, with step-by-step example, for the Windows release (WinHTTrack) and the Linux/Unix release (WebHTTrack)<br>
     <br>
     <li><a href="android.html">HTTrack on Android</a></li>
     <br>Step-by-step guide for the Android app<br>
     <br>
-    <li><a href="cmddoc.html">Command-line version</a></li>
+    <li><a href="httrack.man.html">Command-line version</a></li>
     <br>How to run HTTrack from the command line, and where to find every option<br>
     <br>
     <li><a href="cmdguide.html">Command-line Guide</a></li>
@@ -123,7 +123,7 @@ h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
     <li><a href="fcguide.html">HTTrack Users Guide By Fred Cohen</a></li>
     <br>A tutorial that describes all command-line options, for Linux and Windows users<br>
     <br>
-    <li><a href="dev.html">Developper/Programming</a></li>
+    <li><a href="dev.html">Developer/Programming</a></li>
     <br>How to use HTTrack in batch files, and how to use the library<br>
   </ul>
   <br>

html/options.html

@@ -101,6 +101,10 @@ h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
 
 <h2 align="center"><em>Options</em></h2>
 
+<p><strong>Note:</strong> this is a legacy option list and may be out of date.
+For the authoritative, always-current reference see <a href="httrack.man.html">the httrack manual page</a>,
+and for a task-oriented walkthrough see the <a href="cmdguide.html">Command-line Guide</a>.</p>
+
 <ul>
   <li>Filters: <a href="filters.html">how to use them</a></li>
   <br><small>Here you can find informations on filters: how to accept all gif files in a mirror, for example</small>

html/server/option9.html

@@ -103,6 +103,17 @@ ${do:end-if}
 > ${LANG_I61}
 <br><br>
 
+<input type="checkbox" name="warc" ${checked:warc}
+			title='${html:LANG_WARCTIP}' onMouseOver="info('${html:LANG_WARCTIP}'); return true" onMouseOut="info('&nbsp;'); return true"
+> ${LANG_WARC}
+<br><br>
+
+${LANG_WARCFILE}
+<input name="warcfile" value="${warcfile}" size="40"
+			title='${html:LANG_WARCFILETIP}' onMouseOver="info('${html:LANG_WARCFILETIP}'); return true" onMouseOut="info('&nbsp;'); return true"
+>
+<br><br>
+
 <input type="checkbox" name="norecatch" ${checked:norecatch}
 			title='${html:LANG_I5b}' onMouseOver="info('${html:LANG_I5b}'); return true" onMouseOut="info('&nbsp;'); return true"
 > ${LANG_I34b}

html/server/step2.html

@@ -141,6 +141,8 @@ ${do:copy:KeepSlashes:keepslashes}
 ${do:copy:KeepQueryOrder:keepqueryorder}
 ${do:copy:StripQuery:stripquery}
 ${do:copy:StoreAllInCache:cache2}
+${do:copy:Warc:warc}
+${do:copy:WarcFile:warcfile}
 ${do:copy:LogType:logtype}
 ${do:copy:UseHTTPProxyForFTP:ftpprox}
 ${do:copy:ProxyType:proxytype}

html/server/step3.html

@@ -95,7 +95,7 @@ ${do:end-if}
 
 <table border="0" width="100%">
 <tr><td width="90%">
-	<h2 align="center"><em>Select URLs</em></h2>
+	<h2 align="center"><em>${LANG_G44}</em></h2>
 </td>
 ${/* show help only if available */}
 ${do:if-file-exists:html/index.html}

html/server/step4.html

@@ -77,7 +77,7 @@ ${do:end-if}
 
 <table border="0" width="100%">
 <tr><td width="90%">
-	<h2 align="center"><em>Start</em></h2>
+	<h2 align="center"><em>${LANG_J9}</em></h2>
 </td>
 ${/* show help only if available */}
 ${do:if-file-exists:html/index.html}
@@ -187,6 +187,8 @@ ${do:end-if}
 	${test:toler:--tolerant}
 	${test:http10:--http-10}
 	${test:cache2:--store-all-in-cache}
+	${test:warc:--warc}
+	${test:warcfile:--warc-file "}${html:warcfile}${test:warcfile:"}
 	${test:norecatch:--do-not-recatch}
 	${test:logf:--single-log}
 	${test:logtype:::--extra-log:--debug-log}
@@ -237,6 +239,8 @@ KeepSlashes=${ztest:keepslashes:0:1}
 KeepQueryOrder=${ztest:keepqueryorder:0:1}
 StripQuery=${stripquery}
 StoreAllInCache=${ztest:cache2:0:1}
+Warc=${ztest:warc:0:1}
+WarcFile=${warcfile}
 LogType=${logtype}
 UseHTTPProxyForFTP=${ztest:ftpprox:0:1}
 ProxyType=${proxytype}

lang.def

@@ -1034,3 +1034,11 @@ LANG_STRIPQUERY
 Strip query keys:
 LANG_STRIPQUERYTIP
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+LANG_WARC
+Write a WARC archive of the crawl
+LANG_WARCTIP
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+LANG_WARCFILE
+WARC archive name:
+LANG_WARCFILETIP
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.

lang/Bulgarian.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Ïðåìàõâàíå íà êëþ÷îâå îò çàÿâêàòà:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Êëþ÷îâå îò çàÿâêàòà, ðàçäåëåíè ñúñ çàïåòàÿ, êîèòî äà ñå ïðåìàõíàò îò èìåòî íà çàïèñàíèÿ ôàéë (íàïðèìåð sid,utm_source).
+Write a WARC archive of the crawl
+Çàïèñâàíå íà WARC àðõèâ íà îáõîæäàíåòî
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Çàïèñâàíå íà âñåêè èçòåãëåí îòãîâîð è â WARC/1.1 àðõèâ ïî ISO-28500, äî îãëåäàëîòî.
+WARC archive name:
+Èìå íà WARC àðõèâà:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Íåçàäúëæèòåëíî áàçîâî èìå çà WARC àðõèâà; îñòàâåòå ïðàçíî çà àâòîìàòè÷íî èìåíóâàíå â èçõîäíàòà äèðåêòîðèÿ.

lang/Castellano.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Eliminar claves de query string:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Claves de query string, separadas por comas, que se eliminarán del nombre de los archivos guardados (p. ej. sid,utm_source).
+Write a WARC archive of the crawl
+Escribir un archivo WARC del rastreo
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Guardar también cada respuesta descargada en un archivo WARC/1.1 ISO-28500, junto a la réplica.
+WARC archive name:
+Nombre del archivo WARC:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Nombre base opcional para el archivo WARC; déjelo en blanco para nombrarlo automáticamente en el directorio de salida.

lang/Cesky.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Odebrat klíèe dotazu:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Klíèe dotazu oddìlené èárkami, které se vynechají z pojmenování ukládaných souborù (napø. sid,utm_source).
+Write a WARC archive of the crawl
+Zapsat archiv WARC z procházení
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Uložit také každou staženou odpovìï do archivu WARC/1.1 podle ISO-28500 vedle zrcadla.
+WARC archive name:
+Název archivu WARC:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Volitelný základní název archivu WARC; ponechte prázdné pro automatické pojmenování ve výstupním adresáøi.

lang/Chinese-BIG5.txt

@@ -956,3 +956,11 @@ Strip query keys:
 移除查詢鍵:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 以逗號分隔的查詢鍵，將其從儲存檔案的命名中移除 (例如 sid,utm_source)。
+Write a WARC archive of the crawl
+寫入此次抓取的 WARC 封存檔
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+同時將每個已擷取的回應儲存為 ISO-28500 WARC/1.1 封存檔，置於鏡像網站旁。
+WARC archive name:
+WARC 封存檔名稱：
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+WARC 封存檔的選用基本名稱；留空則於輸出目錄中自動命名。

lang/Chinese-Simplified.txt

@@ -956,3 +956,11 @@ Strip query keys:
 剥离查询键:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 用逗号分隔的查询键，将其从保存文件的命名中删除 (例如 sid,utm_source)。
+Write a WARC archive of the crawl
+写入本次抓取的 WARC 归档
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+同时将每个已获取的响应保存为 ISO-28500 WARC/1.1 归档，置于镜像站点旁边。
+WARC archive name:
+WARC 归档名称：
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+WARC 归档的可选基本名称；留空则在输出目录中自动命名。

lang/Croatian.txt

@@ -958,3 +958,11 @@ Strip query keys:
 Ukloniti kljuèeve upita:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Zarezom odvojeni kljuèevi upita koji se izostavljaju iz naziva spremljenih datoteka (npr. sid,utm_source).
+Write a WARC archive of the crawl
+Zapi¹i WARC arhivu obilaska
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Spremi i svaki preuzeti odgovor u ISO-28500 WARC/1.1 arhivu, uz zrcalo.
+WARC archive name:
+Naziv WARC arhive:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Neobavezni osnovni naziv WARC arhive; ostavite prazno za automatsko imenovanje u izlaznom direktoriju.

lang/Dansk.txt

@@ -1004,3 +1004,11 @@ Strip query keys:
 Fjern forespørgselsnøgler:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Kommaseparerede forespørgselsnøgler, der udelades i navngivningen af gemte filer (f.eks. sid,utm_source).
+Write a WARC archive of the crawl
+Skriv et WARC-arkiv af gennemsøgningen
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Gem også hvert hentet svar i et ISO-28500 WARC/1.1-arkiv ved siden af spejlet.
+WARC archive name:
+Navn på WARC-arkiv:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Valgfrit basisnavn til WARC-arkivet; lad feltet stå tomt for automatisk navngivning i outputmappen.

lang/Deutsch.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Query-Schlüssel entfernen:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Kommagetrennte Query-Schlüssel, die bei der Benennung gespeicherter Dateien entfallen (z. B. sid,utm_source).
+Write a WARC archive of the crawl
+WARC-Archiv des Crawls schreiben
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Jede heruntergeladene Antwort zusätzlich in einem ISO-28500-WARC/1.1-Archiv neben dem Spiegel speichern.
+WARC archive name:
+Name des WARC-Archivs:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Optionaler Basisname für das WARC-Archiv; leer lassen, um es automatisch im Ausgabeverzeichnis zu benennen.

lang/Eesti.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Eemalda päringuvõtmed:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Komadega eraldatud päringuvõtmed, mis jäetakse salvestatud faili nimest välja (nt sid,utm_source).
+Write a WARC archive of the crawl
+Kirjuta läbimise WARC-arhiiv
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Salvesta iga alla laaditud vastus ka ISO-28500 WARC/1.1 arhiivi peegli kõrvale.
+WARC archive name:
+WARC-arhiivi nimi:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+WARC-arhiivi valikuline põhinimi; jäta tühjaks, et see väljundkataloogis automaatselt nimetada.

lang/English.txt

@@ -1004,3 +1004,11 @@ Strip query keys:
 Strip query keys:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Write a WARC archive of the crawl
+Write a WARC archive of the crawl
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+WARC archive name:
+WARC archive name:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.

lang/Finnish.txt

@@ -958,3 +958,11 @@ Strip query keys:
 Poista kyselyavaimet:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Pilkuin erotellut kyselyavaimet, jotka jätetään pois tallennettujen tiedostojen nimeämisestä (esim. sid,utm_source).
+Write a WARC archive of the crawl
+Kirjoita imuroinnin WARC-arkisto
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Tallenna myös jokainen noudettu vastaus ISO-28500 WARC/1.1 -arkistoon peilin viereen.
+WARC archive name:
+WARC-arkiston nimi:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Valinnainen WARC-arkiston perusnimi; jätä tyhjäksi, jotta se nimetään automaattisesti tulostehakemistoon.

lang/Francais.txt

@@ -1004,3 +1004,11 @@ Strip query keys:
 Supprimer les clés de query string :
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Clés de query string à retirer du nommage des fichiers enregistrés, séparées par des virgules (par ex. sid,utm_source).
+Write a WARC archive of the crawl
+Écrire une archive WARC du crawl
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Enregistrer aussi chaque réponse téléchargée dans une archive WARC/1.1 (ISO-28500), à côté du miroir.
+WARC archive name:
+Nom de l'archive WARC :
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Nom de base optionnel pour l'archive WARC ; laissez vide pour le générer automatiquement dans le répertoire de sortie.

lang/Greek.txt

@@ -958,3 +958,11 @@ Strip query keys:
 Αφαίρεση κλειδιών ερωτήματος:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Κλειδιά ερωτήματος χωρισμένα με κόμμα, που θα αφαιρεθούν από την ονομασία των αποθηκευμένων αρχείων (π.χ. sid,utm_source).
+Write a WARC archive of the crawl
+Εγγραφή αρχείου WARC της ανίχνευσης
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Αποθήκευση κάθε ληφθείσας απόκρισης και σε αρχείο WARC/1.1 ISO-28500, δίπλα στο είδωλο.
+WARC archive name:
+Όνομα αρχείου WARC:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Προαιρετικό βασικό όνομα για το αρχείο WARC. Αφήστε το κενό για αυτόματη ονομασία στον κατάλογο εξόδου.

lang/Italiano.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Rimuovi chiavi della query string:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Chiavi della query string, separate da virgole, da rimuovere dai nomi dei file salvati (ad es. sid,utm_source).
+Write a WARC archive of the crawl
+Scrivi un archivio WARC della scansione
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Salva anche ogni risposta scaricata in un archivio WARC/1.1 ISO-28500, accanto al mirror.
+WARC archive name:
+Nome dell'archivio WARC:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Nome di base facoltativo per l'archivio WARC; lascia vuoto per assegnarlo automaticamente nella directory di output.

lang/Japanese.txt

@@ -956,3 +956,11 @@ Strip query keys:
 削除するクエリキー:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 保存ファイル名の生成から除外するクエリキーをカンマ区切りで指定します (例: sid,utm_source)。
+Write a WARC archive of the crawl
+クロールの WARC アーカイブを書き出す
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+取得した各レスポンスを ISO-28500 WARC/1.1 アーカイブとしてミラーの隣にも保存します。
+WARC archive name:
+WARC アーカイブ名:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+WARC アーカイブの任意のベース名。空欄にすると出力ディレクトリ内で自動的に名前が付けられます。

lang/Macedonian.txt

@@ -956,3 +956,11 @@ Strip query keys:
 ¾âáâàÐÝØ ÚÛãçÕÒØ ÞÔ ÑÐàÐúÕâÞ:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 ºÛãçÕÒØ ÞÔ ÑÐàÐúÕâÞ, ÞÔÔÕÛÕÝØ áÞ ×ÐßØàÚÐ, èâÞ áÕ ÞâáâàÐÝãÒÐÐâ ÞÔ ØÜÕâÞ ÝÐ ×ÐçãÒÐÝÐâÐ ÔÐâÞâÕÚÐ (ÝÐ ßàØÜÕà sid,utm_source).
+Write a WARC archive of the crawl
+·ÐßØèØ WARC ÐàåØÒÐ ÝÐ ßàÕÑÐàãÒÐúÕâÞ
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+·ÐçãÒÐø ÓÞ áÕÚÞø ßàÕ×ÕÜÕÝ ÞÔÓÞÒÞà Ø ÒÞ ISO-28500 WARC/1.1 ÐàåØÒÐ, ßÞÚàÐø ÞÓÛÕÔÐÛÞâÞ.
+WARC archive name:
+¸ÜÕ ÝÐ WARC ÐàåØÒÐâÐ:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+¸×ÑÞàÝÞ ÞáÝÞÒÝÞ ØÜÕ ×Ð WARC ÐàåØÒÐâÐ; ÞáâÐÒÕâÕ ßàÐ×ÝÞ ×Ð ÐÒâÞÜÐâáÚÞ ØÜÕÝãÒÐúÕ ÒÞ Ø×ÛÕ×ÝØÞâ ÔØàÕÚâÞàØãÜ.

lang/Magyar.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Lekérdezési kulcsok eltávolítása:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Vesszõvel elválasztott lekérdezési kulcsok, amelyeket el kell hagyni a mentett fájl elnevezésébõl (pl. sid,utm_source).
+Write a WARC archive of the crawl
+A bejárás WARC archívumának írása
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Minden letöltött válasz mentése ISO-28500 WARC/1.1 archívumba is, a tükör mellé.
+WARC archive name:
+WARC archívum neve:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+A WARC archívum opcionális alapneve; hagyja üresen az automatikus elnevezéshez a kimeneti könyvtárban.

lang/Nederlands.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Query-sleutels verwijderen:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Door komma's gescheiden query-sleutels die bij het benoemen van opgeslagen bestanden worden weggelaten (bijv. sid,utm_source).
+Write a WARC archive of the crawl
+Schrijf een WARC-archief van de crawl
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Sla ook elke opgehaalde respons op in een ISO-28500 WARC/1.1-archief, naast de mirror.
+WARC archive name:
+Naam van WARC-archief:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Optionele basisnaam voor het WARC-archief; laat leeg om het automatisch een naam te geven in de uitvoermap.

lang/Norsk.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Fjern spørrenøkler:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Kommaseparerte spørrenøkler som utelates i navngivingen av lagrede filer (f.eks. sid,utm_source).
+Write a WARC archive of the crawl
+Skriv et WARC-arkiv av gjennomgangen
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Lagre også hvert nedlastet svar i et ISO-28500 WARC/1.1-arkiv ved siden av speilet.
+WARC archive name:
+Navn på WARC-arkiv:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Valgfritt basisnavn for WARC-arkivet; la feltet stå tomt for automatisk navngivning i utdatamappen.

lang/Polski.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Usuñ klucze zapytania:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Rozdzielone przecinkami klucze zapytania pomijane przy nazywaniu zapisanych plików (np. sid,utm_source).
+Write a WARC archive of the crawl
+Zapisz archiwum WARC z indeksowania
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Zapisz te¿ ka¿d± pobran± odpowied¼ do archiwum WARC/1.1 ISO-28500, obok kopii lustrzanej.
+WARC archive name:
+Nazwa archiwum WARC:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Opcjonalna nazwa bazowa archiwum WARC; pozostaw puste, aby nazwaæ je automatycznie w katalogu wyj¶ciowym.

lang/Portugues-Brasil.txt

@@ -1004,3 +1004,11 @@ Strip query keys:
 Remover chaves da query string:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Chaves da query string, separadas por vírgulas, a serem removidas da nomeação dos arquivos salvos (ex.: sid,utm_source).
+Write a WARC archive of the crawl
+Gravar um arquivo WARC do rastreamento
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Salvar também cada resposta baixada em um arquivo WARC/1.1 ISO-28500, ao lado do espelho.
+WARC archive name:
+Nome do arquivo WARC:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Nome base opcional para o arquivo WARC; deixe em branco para nomeá-lo automaticamente no diretório de saída.

lang/Portugues.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Remover chaves da query string:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Chaves da query string, separadas por vírgulas, a remover da nomeação dos ficheiros guardados (por ex. sid,utm_source).
+Write a WARC archive of the crawl
+Escrever um arquivo WARC do rastreio
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Guardar também cada resposta transferida num arquivo WARC/1.1 ISO-28500, ao lado do espelho.
+WARC archive name:
+Nome do arquivo WARC:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Nome base opcional para o arquivo WARC; deixe em branco para o nomear automaticamente no diretório de saída.

lang/Romanian.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Elimina cheile din query string:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Chei din query string, separate prin virgula, de eliminat din denumirea fisierelor salvate (de ex. sid,utm_source).
+Write a WARC archive of the crawl
+Scrie o arhiva WARC a parcurgerii
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Salveaza si fiecare raspuns descarcat intr-o arhiva WARC/1.1 ISO-28500, langa oglinda.
+WARC archive name:
+Numele arhivei WARC:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Nume de baza optional pentru arhiva WARC; lasati gol pentru a-l denumi automat in directorul de iesire.

lang/Russian.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Óäàëÿòü êëþ÷è çàïðîñà:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Êëþ÷è çàïðîñà ÷åðåç çàïÿòóþ, óäàëÿåìûå èç èìåíè ñîõðàíÿåìîãî ôàéëà (íàïðèìåð, sid,utm_source).
+Write a WARC archive of the crawl
+Çàïèñàòü WARC-àðõèâ îáõîäà
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Ñîõðàíÿòü êàæäûé çàãðóæåííûé îòâåò òàêæå â àðõèâ WARC/1.1 ISO-28500 ðÿäîì ñ çåðêàëîì.
+WARC archive name:
+Èìÿ WARC-àðõèâà:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Íåîáÿçàòåëüíîå áàçîâîå èìÿ WARC-àðõèâà; îñòàâüòå ïóñòûì äëÿ àâòîìàòè÷åñêîãî èìåíîâàíèÿ â âûõîäíîì êàòàëîãå.

lang/Slovak.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Odstráni» kµúèe dotazu:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Kµúèe dotazu oddelené èiarkami, ktoré sa vynechajú z pomenovania ukladaných súborov (napr. sid,utm_source).
+Write a WARC archive of the crawl
+Zapísa» archív WARC z prehµadávania
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Ulo¾i» aj ka¾dú stiahnutú odpoveï do archívu WARC/1.1 ISO-28500 vedµa zrkadla.
+WARC archive name:
+Názov archívu WARC:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Voliteµný základný názov archívu WARC; ponechajte prázdne pre automatické pomenovanie vo výstupnom adresári.

lang/Slovenian.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Odstrani kljuce poizvedbe:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Z vejicami loceni kljuci poizvedbe, ki se izpustijo pri poimenovanju shranjenih datotek (npr. sid,utm_source).
+Write a WARC archive of the crawl
+Zapisi arhiv WARC iz pregledovanja
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Shrani tudi vsak preneseni odgovor v arhiv WARC/1.1 ISO-28500 poleg zrcala.
+WARC archive name:
+Ime arhiva WARC:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Neobvezno osnovno ime arhiva WARC; pustite prazno za samodejno poimenovanje v izhodni mapi.

lang/Svenska.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Ta bort frågenycklar:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Kommaseparerade frågenycklar som utelämnas vid namngivningen av sparade filer (t.ex. sid,utm_source).
+Write a WARC archive of the crawl
+Skriv ett WARC-arkiv av genomsökningen
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Spara även varje hämtat svar i ett ISO-28500 WARC/1.1-arkiv, bredvid spegeln.
+WARC archive name:
+WARC-arkivets namn:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Valfritt basnamn för WARC-arkivet; lämna tomt för att namnge det automatiskt i utdatakatalogen.

lang/Turkish.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Sorgu anahtarlarýný çýkar:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Kaydedilen dosya adlandýrmasýndan çýkarýlacak, virgülle ayrýlmýþ sorgu anahtarlarý (örn. sid,utm_source).
+Write a WARC archive of the crawl
+Taramanýn WARC arþivini yaz
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Ýndirilen her yanýtý ayrýca aynanýn yanýna bir ISO-28500 WARC/1.1 arþivine kaydet.
+WARC archive name:
+WARC arþivi adý:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+WARC arþivi için isteðe baðlý temel ad; çýktý dizininde otomatik adlandýrma için boþ býrakýn.

lang/Ukrainian.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Âèëó÷àòè êëþ÷³ çàïèòó:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Êëþ÷³ çàïèòó ÷åðåç êîìó, ÿê³ âèëó÷àþòüñÿ ç ³ìåí³ çáåðåæåíîãî ôàéëó (íàïðèêëàä, sid,utm_source).
+Write a WARC archive of the crawl
+Çàïèñàòè WARC-àðõ³â îáõîäó
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Çáåð³ãàòè êîæíó çàâàíòàæåíó â³äïîâ³äü òàêîæ ó àðõ³â WARC/1.1 ISO-28500 ïîðÿä ³ç äçåðêàëîì.
+WARC archive name:
+²ì'ÿ WARC-àðõ³âó:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+Íåîáîâ'ÿçêîâà áàçîâà íàçâà WARC-àðõ³âó; çàëèøòå ïîðîæí³ì äëÿ àâòîìàòè÷íîãî íàéìåíóâàííÿ ó âèõ³äíîìó êàòàëîç³.

lang/Uzbek.txt

@@ -956,3 +956,11 @@ Strip query keys:
 Olib tashlanadigan so’rov kalitlari:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Saqlangan fayl nomidan olib tashlanadigan, vergul bilan ajratilgan so’rov kalitlari (masalan, sid,utm_source).
+Write a WARC archive of the crawl
+Qidiruvning WARC arxivini yozish
+Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
+Har bir yuklab olingan javobni ISO-28500 WARC/1.1 arxiviga ham, ko'zgu yonida saqlash.
+WARC archive name:
+WARC arxivi nomi:
+Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
+WARC arxivi uchun ixtiyoriy asosiy nom; chiqish katalogida avtomatik nomlash uchun bo'sh qoldiring.

man/httrack.1

@@ -3,7 +3,7 @@
 .\"
 .\" This file is generated by man/makeman.sh; do not edit by hand.
 .\" SPDX-License-Identifier: GPL-3.0-or-later
-.TH httrack 1 "22 July 2026" "httrack website copier"
+.TH httrack 1 "23 July 2026" "httrack website copier"
 .SH NAME
 httrack \- offline browser : copy websites to a local directory
 .SH SYNOPSIS
@@ -58,6 +58,7 @@ httrack \- offline browser : copy websites to a local directory
 [ \fB\-sN, \-\-robots[=N]\fR ]
 [ \fB\-%h, \-\-http\-10\fR ]
 [ \fB\-%k, \-\-keep\-alive\fR ]
+[ \fB\-%z, \-\-disable\-compression\fR ]
 [ \fB\-%B, \-\-tolerant\fR ]
 [ \fB\-%s, \-\-updatehack\fR ]
 [ \fB\-%u, \-\-urlhack\fR ]
@@ -73,6 +74,7 @@ httrack \- offline browser : copy websites to a local directory
 [ \fB\-%X, \-\-headers\fR ]
 [ \fB\-C, \-\-cache[=N]\fR ]
 [ \fB\-k, \-\-store\-all\-in\-cache\fR ]
+[ \fB\-%r, \-\-warc\fR ]
 [ \fB\-%n, \-\-do\-not\-recatch\fR ]
 [ \fB\-%v, \-\-display\fR ]
 [ \fB\-Q, \-\-do\-not\-log\fR ]
@@ -98,6 +100,7 @@ httrack \- offline browser : copy websites to a local directory
 [ \fB\-%!, \-\-disable\-security\-limits\fR ]
 [ \fB\-V, \-\-userdef\-cmd\fR ]
 [ \fB\-%W, \-\-callback\fR ]
+[ \fB\-y, \-\-background\-on\-suspend\fR ]
 [ \fB\-K, \-\-keep\-links[=N]\fR ]
 .SH DESCRIPTION
 .B httrack
@@ -195,6 +198,8 @@ delayed type check, don't make any link test but wait for files download to star
 cached delayed type check, don't wait for remote type during updates, to speedup them (%D0 wait, * %D1 don't wait) (\-\-cached\-delayed\-type\-check)
 .IP \-%M
 generate a RFC MIME\-encapsulated full\-archive (.mht) (\-\-mime\-html)
+.IP \-%t
+keep the original file extension, don't rewrite it from the MIME type (%t0 rewrite)
 .IP \-LN
 long names (L1 *long names / L0 8\-3 conversion / L2 ISO9660 compatible) (\-\-long\-names[=N])
 .IP \-KN
@@ -232,6 +237,8 @@ follow robots.txt and meta robots tags (0=never,1=sometimes,* 2=always, 3=always
 force HTTP/1.0 requests (reduce update features, only for old servers or proxies) (\-\-http\-10)
 .IP \-%k
 use keep\-alive if possible, greately reducing latency for small files and test requests (%k0 don't use) (\-\-keep\-alive)
+.IP \-%z
+do not request compressed content (%z0 request) (\-\-disable\-compression)
 .IP \-%B
 tolerant requests (accept bogus responses on some servers, but not standard!) (\-\-tolerant)
 .IP \-%s
@@ -258,7 +265,7 @@ default referer field sent in HTTP headers (\-\-referer <param>)
 .IP \-%E
 from email address sent in HTTP headers (\-\-from <param>)
 .IP \-%F
-footer string in Html code (\-%F "Mirrored [from host %s [file %s [at %s]]]" (\-\-footer <param>)
+footer string in Html code (\-%F "Mirrored from {url} on {date}"; fields {addr} {path} {url} {date} {lastmodified} {version} {mime} {charset} {status} {size}, or legacy %s) (\-\-footer <param>)
 .IP \-%l
 preferred language (\-%l "fr, en, jp, *" (\-\-language <param>)
 .IP \-%a
@@ -270,6 +277,8 @@ additional HTTP header line (\-%X "X\-Magic: 42" (\-\-headers <param>)
 create/use a cache for updates and retries (C0 no cache,C1 cache is prioritary,* C2 test update before) (\-\-cache[=N])
 .IP \-k
 store all files in cache (not useful if files on disk) (\-\-store\-all\-in\-cache)
+.IP \-%r
+write an ISO\-28500 WARC/1.1 archive; \-\-warc\-file NAME sets the output name, \-\-warc\-max\-size N rotates segments past N bytes, \-\-warc\-cdx also writes a sorted CDXJ index, \-\-wacz packages it all as a WACZ file (\-\-warc)
 .IP \-%n
 do not re\-download locally erased files (\-\-do\-not\-recatch)
 .IP \-%v
@@ -326,8 +335,6 @@ go everywhere on the web (\-\-go\-everywhere)
 .IP \-%H
 debug HTTP headers in logfile (\-\-debug\-headers)
 .SS Guru options: (do NOT use if possible)
-.IP \-#X
-*use optimized engine (limited memory boundary checks) (\-\-fast\-engine)
 .IP \-#test
 list engine self\-tests (run one with \-#test=NAME [args])
 .IP \-#C
@@ -352,8 +359,6 @@ maximum number of links (\-#L1000000) (\-\-advanced\-maxlinks[=N])
 display ugly progress information (\-\-advanced\-progressinfo)
 .IP \-#P
 catch URL (\-\-catch\-url)
-.IP \-#R
-old FTP routines (debug) (\-\-repair\-cache)
 .IP \-#T
 generate transfer ops. log every minutes (\-\-debug\-xfrstats)
 .IP \-#u
@@ -372,6 +377,8 @@ USE IT WITH EXTREME CARE
 execute system command after each files ($0 is the filename: \-V "rm \\$0") (\-\-userdef\-cmd <param>)
 .IP \-%W
 use an external library function as a wrapper (\-%W myfoo.so[,myparameters]) (\-\-callback <param>)
+.IP \-y
+go to background when suspended (y0 don't) (\-\-background\-on\-suspend)
 .SS Details: Option N
 .IP \-N0
 Site\-structure (default)

src/Makefile.am

@@ -63,7 +63,7 @@ libhttrack_la_SOURCES =  htscore.c htsparse.c htsback.c htscache.c \
 	htshelp.c htslib.c htsurlport.c htscoremain.c \
 	htsname.c htsrobots.c htstools.c htswizard.c \
 	htsalias.c htsthread.c htsindex.c htsbauth.c \
-	htsmd5.c htscodec.c htsproxy.c htszlib.c htswrap.c htsconcat.c \
+	htsmd5.c htscodec.c htswarc.c htsproxy.c htszlib.c htswrap.c htsconcat.c \
 	htsmodules.c htscharset.c punycode.c htsencoding.c htssniff.c \
 	md5.c \
 	minizip/ioapi.c minizip/mztools.c minizip/unzip.c minizip/zip.c \
@@ -74,7 +74,7 @@ libhttrack_la_SOURCES =  htscore.c htsparse.c htsback.c htscache.c \
 	htshelp.h htsindex.h htslib.h htsurlport.h htsmd5.h \
 	htsmodules.h htsname.h htsnet.h htssniff.h \
 	htsopt.h htsrobots.h htsthread.h  \
-	htstools.h htswizard.h htswrap.h htscodec.h htsproxy.h htszlib.h  \
+	htstools.h htswizard.h htswrap.h htscodec.h htswarc.h htsproxy.h htszlib.h  \
 	htsstrings.h htsarrays.h httrack-library.h \
 	htscharset.h punycode.h htsencoding.h \
 	htsentities.h htsentities.sh htsbasiccharsets.sh htscodepages.h \

src/htsalias.c

@@ -114,6 +114,15 @@ const char *hts_optalias[][4] = {
    "strip [host/pattern=]key1,key2,... from URLs"},
   {"cookies-file", "-%K", "param1",
    "load extra cookies from a Netscape cookies.txt"},
+  {"warc", "-%r", "single", "write an ISO-28500 WARC/1.1 archive of the crawl"},
+  {"warc-file", "-%rf", "param1", "write a WARC archive to the given base name"},
+  {"warc-max-size", "-%rs", "param1",
+   "rotate the WARC archive once a segment passes N bytes (0: single file)"},
+  {"warc-cdx", "-%rc", "single",
+   "write a sorted CDXJ index next to the WARC archive"},
+  {"warc-cdxj", "-%rc", "single", ""},
+  {"wacz", "-%rz", "single",
+   "package the WARC archive, CDXJ index and pages as a WACZ file"},
   {"why", "-%Y", "param1",
    "explain which filter rule accepts or rejects a URL, then exit"},
   {"pause", "-%G", "param1",

src/htsback.c

@@ -37,6 +37,7 @@ Please visit our Website: http://www.httrack.com
 /* specific definitions */
 #include "htsnet.h"
 #include "htscore.h"
+#include "htswarc.h"
 #include "htsthread.h"
 #include <time.h>
 /* END specific definitions */
@@ -749,9 +750,20 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
                     fexist_utf8(back[p].url_sav))
                   filenote(&opt->state.strc, back[p].url_sav, NULL);
               }
+              /* Keep the compressed spool so the WARC record stores the body
+                 verbatim (Content-Encoding preserved) instead of unlinking it.
+               */
+              if (StringNotEmpty(opt->warc_file)) {
+                warc_adopt_rawspool(&back[p].r, back[p].tmpfile);
+                if (back[p].r.warc_rawpath != NULL)
+                  back[p].tmpfile =
+                      NULL; /* adopted: freed via warc_free_request */
+              }
               /* ensure that no remaining temporary file exists */
-              unlink(back[p].tmpfile);
-              back[p].tmpfile = NULL;
+              if (back[p].tmpfile != NULL) {
+                unlink(back[p].tmpfile);
+                back[p].tmpfile = NULL;
+              }
             }
             // stats
             HTS_STAT.total_packed += back[p].compressed_size;
@@ -979,6 +991,10 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
         // status finished callback
         RUN_CALLBACK1(opt, xfrstatus, &back[p]);
 
+        // WARC archive of the transaction (request + response/revisit)
+        if (StringNotEmpty(opt->warc_file))
+          warc_write_backtransaction(opt, &back[p]);
+
         return 0;
       } else {                  // testmode
         if (back[p].r.statuscode / 100 >= 3) {  /* Store 3XX, 4XX, 5XX test response codes, but NOT 2XX */
@@ -1055,6 +1071,11 @@ void back_copy_static(const lien_back * src, lien_back * dst) {
   dst->r.soc = INVALID_SOCKET;
   dst->r.adr = NULL;
   dst->r.headers = NULL;
+  dst->r.warc_reqhdr = NULL;
+  dst->r.warc_resphdr = NULL;
+  dst->r.warc_rawpath =
+      NULL; /* the spool stays owned by src (no double-unlink) */
+  dst->r.warc_truncated = 0;
   dst->r.out = NULL;
   dst->r.location = dst->location_buffer;
   dst->r.fp = NULL;
@@ -1118,6 +1139,10 @@ int back_unserialize(FILE * fp, lien_back ** dst) {
     (*dst)->chunk_adr = NULL;
     (*dst)->r.adr = NULL;
     (*dst)->r.out = NULL;
+    (*dst)->r.warc_reqhdr = NULL;
+    (*dst)->r.warc_resphdr = NULL;
+    (*dst)->r.warc_rawpath = NULL;
+    (*dst)->r.warc_truncated = 0;
     (*dst)->r.location = (*dst)->location_buffer;
     (*dst)->r.fp = NULL;
     (*dst)->r.soc = INVALID_SOCKET;
@@ -1585,6 +1610,7 @@ int back_clear_entry(lien_back * back) {
       freet(back->r.headers);
       back->r.headers = NULL;
     }
+    warc_free_request(&back->r);
     // Tout nettoyer
     memset(back, 0, sizeof(lien_back));
     back->r.soc = INVALID_SOCKET;
@@ -2509,6 +2535,19 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
 
     for (i = 0; i < (unsigned int) back_max; i++) {
       if (back[i].status > 0 && back[i].status < STATUS_FTP_TRANSFER) {
+        /* A cap-truncated body is deliberate, not broken: archive what arrived
+           with WARC-Truncated before the abort overwrites the slot's real 2xx
+           status. HTTrack still treats the slot as incomplete afterwards. */
+        if (StringNotEmpty(opt->warc_file) && back[i].r.statuscode > 0 &&
+            back[i].r.warc_resphdr != NULL && back[i].r.size > 0 &&
+            !(back[i].r.is_write && IS_DELAYED_EXT(back[i].url_sav))) {
+          if (back[i].r.is_write && back[i].r.out != NULL)
+            fflush(back[i].r.out);
+          back[i].r.warc_truncated = (limit == HTS_MIRROR_LIMIT_SIZE)
+                                         ? WARC_TRUNC_LENGTH
+                                         : WARC_TRUNC_TIME;
+          warc_write_backtransaction(opt, &back[i]);
+        }
         if (back[i].r.soc != INVALID_SOCKET) {
           deletehttp(&back[i].r);
         }
@@ -3631,6 +3670,10 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                     deleteaddr(&back[i].r);
                     back[i].r.headers = block;
                   }
+                  // Stash the raw response headers for WARC (deletehttp frees
+                  // r.headers when the socket closes, before back_finalize)
+                  if (StringNotEmpty(opt->warc_file))
+                    warc_stash_response(&back[i].r, back[i].r.headers);
 
                   /* 
                      Status code and header-response hacks

src/htscore.c

@@ -39,6 +39,7 @@ Please visit our Website: http://www.httrack.com
 
 /* File defs */
 #include "htscore.h"
+#include "htswarc.h"
 
 /* specific definitions */
 #include "htsbase.h"
@@ -2245,6 +2246,7 @@ int httpmirror(char *url1, httrackp * opt) {
 
   // ending
   usercommand(opt, 0, NULL, NULL, NULL, NULL);
+  warc_close_opt(opt);
 
   // désallocation mémoire & buffers
   XH_uninit;
@@ -3628,6 +3630,12 @@ HTSEXT_API int copy_htsopt(const httrackp * from, httrackp * to) {
   if (StringNotEmpty(from->cookies_file))
     StringCopyS(to->cookies_file, from->cookies_file);
 
+  if (StringNotEmpty(from->warc_file))
+    StringCopyS(to->warc_file, from->warc_file);
+  to->warc_max_size = from->warc_max_size;
+  to->warc_cdx = from->warc_cdx;
+  to->warc_wacz = from->warc_wacz;
+
   if (from->pause_max_ms > 0) {
     to->pause_min_ms = from->pause_min_ms;
     to->pause_max_ms = from->pause_max_ms;

src/htscoremain.c

@@ -40,6 +40,7 @@ Please visit our Website: http://www.httrack.com
 #include "htscore.h"
 #include "htsdefines.h"
 #include "htsalias.h"
+#include "htswarc.h"
 #include "htsbauth.h"
 #include "htswrap.h"
 #include "htsmodules.h"
@@ -1622,10 +1623,9 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
                 if ((na + 1 >= argc) || (argv[na + 1][0] == '-')) {
                   HTS_PANIC_PRINTF
                     ("Option %F needs to be followed by a blank space, and a footer string");
-                  printf
-                    ("Example: -%%F \"<!-- Mirrored from %%s by HTTrack Website Copier/"
-                     HTTRACK_AFF_VERSION " " HTTRACK_AFF_AUTHORS
-                     ", %%s -->\"\n");
+                  printf("Example: -%%F \"<!-- Mirrored from {addr}{path} by "
+                         "HTTrack Website Copier/"
+                         "{version} " HTTRACK_AFF_AUTHORS ", {date} -->\"\n");
                   htsmain_free();
                   return -1;
                 } else {
@@ -1790,6 +1790,54 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
                   StringCopy(opt->cookies_file, argv[na]);
                 }
                 break;
+              case 'r': // warc / warc-file: write an ISO-28500 WARC archive
+                if (*(com + 1) == 'f') { // --warc-file NAME: explicit basename
+                  com++;
+                  if ((na + 1 >= argc) || (argv[na + 1][0] == '-')) {
+                    HTS_PANIC_PRINTF(
+                        "Option warc-file needs a blank space and a WARC name");
+                    htsmain_free();
+                    return -1;
+                  }
+                  na++;
+                  if (strlen(argv[na]) >= 1024) {
+                    HTS_PANIC_PRINTF("WARC file name too long");
+                    htsmain_free();
+                    return -1;
+                  }
+                  StringCopy(opt->warc_file, argv[na]);
+                } else if (*(com + 1) == 's') { // --warc-max-size N: rotation
+                  com++;
+                  if ((na + 1 >= argc) || (argv[na + 1][0] == '-')) {
+                    HTS_PANIC_PRINTF(
+                        "Option warc-max-size needs a blank space and a size");
+                    htsmain_free();
+                    return -1;
+                  }
+                  na++;
+                  { // reject non-numeric/negative/overflow; keep default 0
+                    // (single file)
+                    char *end;
+                    LLint v;
+                    errno = 0;
+                    v = strtoll(argv[na], &end, 10);
+                    if (isdigit((unsigned char) argv[na][0]) && *end == '\0' &&
+                        errno != ERANGE)
+                      opt->warc_max_size = v;
+                  }
+                } else if (*(com + 1) == 'c') { // --warc-cdx: sorted CDXJ index
+                  com++;
+                  opt->warc_cdx = 1;
+                } else if (*(com + 1) == 'z') { // --wacz: WACZ package
+                  com++;
+                  opt->warc_wacz = 1;
+                  opt->warc_cdx = 1; // WACZ embeds the CDXJ index
+                  if (!StringNotEmpty(opt->warc_file))
+                    StringCopy(opt->warc_file, WARC_AUTONAME);
+                } else { // --warc: auto-named archive under the output dir
+                  StringCopy(opt->warc_file, WARC_AUTONAME);
+                }
+                break;
               case 'Y': // why: explain the filter verdict for a URL, no crawl
                 if ((na + 1 >= argc) || (argv[na + 1][0] == '-')) {
                   HTS_PANIC_PRINTF("Option why needs a blank space and a URL");

src/htshelp.c

@@ -524,6 +524,8 @@ void help(const char *app, int more) {
   infomsg
     (" %D  cached delayed type check, don't wait for remote type during updates, to speedup them (%D0 wait, * %D1 don't wait)");
   infomsg(" %M  generate a RFC MIME-encapsulated full-archive (.mht)");
+  infomsg(" %t  keep the original file extension, don't rewrite it from the "
+          "MIME type (%t0 rewrite)");
   infomsg
     ("  LN long names (L1 *long names / L0 8-3 conversion / L2 ISO9660 compatible)");
   infomsg
@@ -554,6 +556,7 @@ void help(const char *app, int more) {
     (" %h  force HTTP/1.0 requests (reduce update features, only for old servers or proxies)");
   infomsg
     (" %k  use keep-alive if possible, greately reducing latency for small files and test requests (%k0 don't use)");
+  infomsg(" %z  do not request compressed content (%z0 request)");
   infomsg
     (" %B  tolerant requests (accept bogus responses on some servers, but not standard!)");
   infomsg
@@ -578,8 +581,10 @@ void help(const char *app, int more) {
     ("  F  user-agent field sent in HTTP headers (-F \"user-agent name\")");
   infomsg(" %R  default referer field sent in HTTP headers");
   infomsg(" %E  from email address sent in HTTP headers");
-  infomsg
-    (" %F  footer string in Html code (-%F \"Mirrored [from host %s [file %s [at %s]]]\"");
+  infomsg(
+      " %F  footer string in Html code (-%F \"Mirrored from {url} on "
+      "{date}\"; fields {addr} {path} {url} {date} {lastmodified} {version} "
+      "{mime} {charset} {status} {size}, or legacy %s)");
   infomsg(" %l  preferred language (-%l \"fr, en, jp, *\"");
   infomsg(" %a  accepted formats (-%a \"text/html,image/png;q=0.9,*/*;q=0.1\"");
   infomsg(" %X  additional HTTP header line (-%X \"X-Magic: 42\"");
@@ -588,6 +593,10 @@ void help(const char *app, int more) {
   infomsg
     ("  C  create/use a cache for updates and retries (C0 no cache,C1 cache is prioritary,* C2 test update before)");
   infomsg("  k  store all files in cache (not useful if files on disk)");
+  infomsg(" %r  write an ISO-28500 WARC/1.1 archive; --warc-file NAME sets the "
+          "output name, --warc-max-size N rotates segments past N bytes, "
+          "--warc-cdx also writes a sorted CDXJ index, --wacz packages it all "
+          "as a WACZ file");
   infomsg(" %n  do not re-download locally erased files");
   infomsg
     (" %v  display on screen filenames downloaded (in realtime) - * %v1 short version - %v2 full animation");
@@ -620,7 +629,6 @@ void help(const char *app, int more) {
   infomsg(" %H  debug HTTP headers in logfile");
   infomsg("");
   infomsg("Guru options: (do NOT use if possible)");
-  infomsg(" #X *use optimized engine (limited memory boundary checks)");
   infomsg(" #test  list engine self-tests (run one with -#test=NAME [args])");
   infomsg(" #C  cache list (-#C '*.com/spider*.gif'");
   infomsg(" #R  cache repair (damaged cache)");
@@ -633,7 +641,6 @@ void help(const char *app, int more) {
   infomsg(" #L  maximum number of links (-#L1000000)");
   infomsg(" #p  display ugly progress information");
   infomsg(" #P  catch URL");
-  infomsg(" #R  old FTP routines (debug)");
   infomsg(" #T  generate transfer ops. log every minutes");
   infomsg(" #u  wait time");
   infomsg(" #Z  generate transfer rate statistics every minutes");
@@ -650,6 +657,7 @@ void help(const char *app, int more) {
     ("  V execute system command after each files ($0 is the filename: -V \"rm \\$0\")");
   infomsg(" %W use an external library function as a wrapper (-%W "
           "myfoo.so[,myparameters])");
+  infomsg("  y  go to background when suspended (y0 don't)");
   infomsg("");
   infomsg("Details: Option N");
   infomsg("  N0 Site-structure (default)");

src/htslib.c

@@ -36,6 +36,7 @@ Please visit our Website: http://www.httrack.com
 // Fichier librairie .c
 
 #include "htscore.h"
+#include "htswarc.h"
 
 /* specific definitions */
 #include "htsbase.h"
@@ -1201,6 +1202,11 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode,
   }                             // Fin test pas postfile
   //
 
+  // Stash the raw request for the WARC request record (freed at
+  // back_clear_entry)
+  if (StringNotEmpty(opt->warc_file))
+    warc_stash_request(retour, bstr.buffer);
+
   // Callback
   {
     int test_head =
@@ -2114,6 +2120,8 @@ htsblk http_test(httrackp * opt, const char *adr, const char *fil, char *loc) {
 #if HTS_DEBUG_CLOSESOCK
     DEBUG_W("http_test: deletehttp\n");
 #endif
+    // this probe's htsblk is discarded by callers, so free any WARC stash here
+    warc_free_request(&retour);
     deletehttp(&retour);
     retour.soc = INVALID_SOCKET;
   }
@@ -6010,6 +6018,8 @@ HTSEXT_API httrackp *hts_create_opt(void) {
   StringCopy(opt->footer, HTS_DEFAULT_FOOTER);
   StringCopy(opt->strip_query, "");
   StringCopy(opt->cookies_file, "");
+  StringCopy(opt->warc_file, "");
+  opt->warc_max_size = 0; /* no rotation unless --warc-max-size sets it */
   StringCopy(opt->why_url, "");
   opt->pause_min_ms = 0;
   opt->pause_max_ms = 0;
@@ -6161,6 +6171,7 @@ HTSEXT_API void hts_free_opt(httrackp * opt) {
     StringFree(opt->strip_query);
     StringFree(opt->cookies_file);
     StringFree(opt->why_url);
+    StringFree(opt->warc_file);
 
     StringFree(opt->path_html);
     StringFree(opt->path_html_utf8);

src/htsopt.h

@@ -256,6 +256,7 @@ struct htsoptstate {
   unsigned int debug_state;
   unsigned int tmpnameid; /**< counter for temporary file names */
   int is_ended;           /**< mirror has finished */
+  void *warc;             /**< open WARC writer (warc_writer*), or NULL */
 };
 
 /* Library handles */
@@ -538,6 +539,14 @@ struct httrackp {
   int pause_max_ms; /**< inter-file pause upper bound, ms */
   String why_url;   /**< URL to diagnose (--why): print the deciding filter rule
                          and exit without crawling */
+  String warc_file; /**< WARC output: WARC_AUTONAME for --warc, or the
+                         --warc-file basename (appended at the tail: ABI) */
+  LLint warc_max_size;  /**< --warc-max-size: rotate the archive past this many
+                             bytes (<=0: single file). Tail: ABI */
+  hts_boolean warc_cdx; /**< --warc-cdx: write a sorted CDXJ index next to the
+                             archive. Tail: ABI */
+  hts_boolean warc_wacz; /**< --wacz: package archive+index+pages as a WACZ zip
+                              (implies --warc + --warc-cdx). Tail: ABI */
 };
 
 /* Running statistics for a mirror. */
@@ -661,6 +670,14 @@ struct htsblk {
   /* Restart-whole signal: a resume this response rejected (unusable 206) must
      retry with no Range, else a surviving partial/temp-ref loops (#581). */
   hts_boolean refetch_wholefile;
+  char *warc_reqhdr; /**< stashed raw request header block for WARC (or NULL) */
+  char *
+      warc_resphdr; /**< stashed raw response header block for WARC (or NULL) */
+  int warc_truncated; /**< WARC-Truncated reason for a cap-truncated body
+                           (WARC_TRUNC_*, 0=none). Tail: ABI */
+  char *warc_rawpath; /**< verbatim WARC: spooled compressed body path, or NULL
+                           (owns the file; unlinked on free). Tail: ABI */
+  LLint warc_rawsize; /**< byte length of warc_rawpath. Tail: ABI */
   /*char digest[32+2];   // md5 digest generated by the engine ("" if none) */
 };
 

src/htsparse.c

@@ -792,17 +792,72 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                   char gmttime[256];
                   char BIGSTK safe_adr[HTS_URLMAXSIZE * 3 + 4];
                   char BIGSTK safe_fil[HTS_URLMAXSIZE * 3 + 4];
+                  char BIGSTK safe_url[HTS_URLMAXSIZE * 6 + 16];
+                  char safe_lastmod[sizeof(r->lastmodified) * 3 + 4];
+                  char safe_ctype[sizeof(r->contenttype) * 3 + 4];
+                  char safe_charset[sizeof(r->charset) * 3 + 4];
+                  char status_str[16];
+                  char size_str[32];
+                  // {url} scheme: jump_identification_const strips it for
+                  // http/https/ftp, so re-add it (bare host is http); for any
+                  // other scheme the host keeps its "scheme://" and we add
+                  // none.
+                  const char *const url_host =
+                      jump_identification_const(urladr());
+                  const char *const url_scheme =
+                      strstr(url_host, "://") != NULL  ? ""
+                      : strfield(urladr(), "https://") ? "https://"
+                      : strfield(urladr(), "ftp://")   ? "ftp://"
+                                                       : "http://";
 
-                  tempo[0] = '\0';
+                  // {addr}/{path} are the escaped host and remote path; {url}
+                  // prepends the scheme to them (credentials already stripped
+                  // by jump_identification_const, and the scheme is a safe
+                  // literal, so no re-escaping is needed).
+                  html_inline_safe(url_host, safe_adr, sizeof(safe_adr));
+                  html_inline_safe(urlfil(), safe_fil, sizeof(safe_fil));
+                  snprintf(safe_url, sizeof(safe_url), "%s%s%s", url_scheme,
+                           safe_adr, safe_fil);
+                  snprintf(status_str, sizeof(status_str), "%d", r->statuscode);
+                  snprintf(size_str, sizeof(size_str), LLintP, (LLint) r->size);
                   time_gmt_rfc822(gmttime);
-                  strcatbuff(tempo, eol);
-                  hts_template_format_str(tempo + strlen(tempo), sizeof(tempo) - strlen(tempo),
-                          StringBuff(opt->footer),
-                          html_inline_safe(jump_identification_const(urladr()), safe_adr, sizeof(safe_adr)),
-                          html_inline_safe(urlfil(), safe_fil, sizeof(safe_fil)), gmttime,
-                          HTTRACK_VERSIONID, /* EOF */ NULL);
-                  strcatbuff(tempo, eol);
-                  HT_ADD(tempo);
+
+                  {
+                    // Every network-derived string is html_inline_safe()'d: the
+                    // footer sits inside an HTML comment, so a value holding
+                    // "-->" would otherwise close it and inject markup (#165).
+                    // status/size are formatted integers and need no escaping.
+                    const hts_footer_field fields[] = {
+                        {"addr", safe_adr},
+                        {"path", safe_fil},
+                        {"url", safe_url},
+                        {"date", gmttime},
+                        {"lastmodified",
+                         html_inline_safe(r->lastmodified, safe_lastmod,
+                                          sizeof(safe_lastmod))},
+                        {"version", HTTRACK_VERSIONID},
+                        {"mime", html_inline_safe(r->contenttype, safe_ctype,
+                                                  sizeof(safe_ctype))},
+                        {"charset", html_inline_safe(r->charset, safe_charset,
+                                                     sizeof(safe_charset))},
+                        {"status", status_str},
+                        {"size", size_str},
+                    };
+
+                    tempo[0] = '\0';
+                    strcatbuff(tempo, eol);
+                    // hts_footer_format returns <0 on overflow, leaving tempo
+                    // unterminated; emitting it would abort in strcatbuff
+                    // below.
+                    if (hts_footer_format(tempo + strlen(tempo),
+                                          sizeof(tempo) - strlen(tempo),
+                                          StringBuff(opt->footer), fields,
+                                          sizeof(fields) / sizeof(fields[0])) >=
+                        0) {
+                      strcatbuff(tempo, eol);
+                      HT_ADD(tempo);
+                    }
+                  }
                 }
                 // Emit charset ?
                 if (emited_footer == 1 && strnotempty(r->charset)) {

src/htstools.c

@@ -754,35 +754,48 @@ typedef struct hts_template_format_buf {
   size_t offset;
 } hts_template_format_buf;
 
+// Bounded append to a template buffer (or FILE); returns -1 on overflow/error.
+static int htsfmt_putc(hts_template_format_buf *buf, char c) {
+  if (buf->fp != NULL) {
+    assertf(buf->buffer == NULL);
+    if (fputc(c, buf->fp) < 0)
+      return -1;
+  } else {
+    assertf(buf->buffer != NULL);
+    if (buf->offset + 1 < buf->size)
+      buf->buffer[buf->offset++] = c;
+    else
+      return -1;
+  }
+  return 0;
+}
+
+static int htsfmt_puts(hts_template_format_buf *buf, const char *s) {
+  size_t i;
+  assertf(s != NULL);
+  for (i = 0; s[i] != '\0'; i++) {
+    if (htsfmt_putc(buf, s[i]) < 0)
+      return -1;
+  }
+  return 0;
+}
+
 // note: upstream arg list MUST be NULL-terminated for safety
 // returns a negative value upon error
-static int hts_template_formatv(hts_template_format_buf *buf, 
+static int hts_template_formatv(hts_template_format_buf *buf,
                                 const char *format, va_list args) {
 #undef FPUTC
 #undef FPUTS
-#define FPUTC(C) do { \
-  if (buf->fp != NULL) { \
-    assertf(buf->buffer == NULL); \
-    if (fputc(C, buf->fp) < 0) { \
-      return -1; \
-    } \
-  } else { \
-    assertf(buf->buffer != NULL); \
-    if (buf->offset + 1 < buf->size) { \
-      buf->buffer[buf->offset++] = (C); \
-    } else { \
-      return -1; \
-    } \
-  } \
-} while(0)
-#define FPUTS(S) do { \
-  size_t i; \
-  const char *const str_ = (S); \
-  assertf(str_ != NULL); \
-  for(i = 0 ; str_[i] != '\0' ; i++) { \
-    FPUTC(str_[i]); \
-  } \
-} while(0)
+#define FPUTC(C)                                                               \
+  do {                                                                         \
+    if (htsfmt_putc(buf, (C)) < 0)                                             \
+      return -1;                                                               \
+  } while (0)
+#define FPUTS(S)                                                               \
+  do {                                                                         \
+    if (htsfmt_puts(buf, (S)) < 0)                                             \
+      return -1;                                                               \
+  } while (0)
 
   if (buf != NULL && format != NULL) {
     const char *arg_expanded[32];
@@ -859,6 +872,74 @@ int hts_template_format_str(char *buffer, size_t size, const char *format, ...)
   return success;
 }
 
+// Value of the named field, or "" if absent (never NULL, so callers can pass it
+// straight to a formatter).
+static const char *footer_field_value(const hts_footer_field *fields,
+                                      size_t nfields, const char *name) {
+  size_t j;
+  for (j = 0; j < nfields; j++) {
+    if (strcmp(fields[j].name, name) == 0)
+      return fields[j].value != NULL ? fields[j].value : "";
+  }
+  return "";
+}
+
+int hts_footer_format(char *buffer, size_t size, const char *footer,
+                      const hts_footer_field *fields, size_t nfields) {
+  hts_template_format_buf buf = {NULL, buffer, size, 0};
+  size_t i;
+
+  if (footer == NULL || buffer == NULL || size == 0)
+    return -1;
+  // %s keeps the legacy positional model, byte-for-byte for existing -%F
+  // strings: addr, path, date, version, looked up by name and
+  // order-independent.
+  if (strstr(footer, "%s") != NULL)
+    return hts_template_format_str(
+        buffer, size, footer, footer_field_value(fields, nfields, "addr"),
+        footer_field_value(fields, nfields, "path"),
+        footer_field_value(fields, nfields, "date"),
+        footer_field_value(fields, nfields, "version"), /* EOF */ NULL);
+  // "{{"/"}}" emit a literal brace; an unknown "{...}" is left verbatim so
+  // typos stay visible.
+  for (i = 0; footer[i] != '\0'; i++) {
+    const char c = footer[i];
+    if (c == '{' && footer[i + 1] == '{') {
+      if (htsfmt_putc(&buf, '{') < 0)
+        return -1;
+      i++;
+    } else if (c == '}' && footer[i + 1] == '}') {
+      if (htsfmt_putc(&buf, '}') < 0)
+        return -1;
+      i++;
+    } else if (c == '{') {
+      const char *const end = strchr(footer + i + 1, '}');
+      int matched = 0;
+      if (end != NULL) {
+        const size_t namelen = (size_t) (end - (footer + i + 1));
+        size_t j;
+        for (j = 0; j < nfields; j++) {
+          if (strlen(fields[j].name) == namelen &&
+              strncmp(fields[j].name, footer + i + 1, namelen) == 0) {
+            if (htsfmt_puts(&buf,
+                            fields[j].value != NULL ? fields[j].value : "") < 0)
+              return -1;
+            i += namelen + 1; // consume the name and its closing '}'
+            matched = 1;
+            break;
+          }
+        }
+      }
+      if (!matched && htsfmt_putc(&buf, '{') < 0)
+        return -1;
+    } else if (htsfmt_putc(&buf, c) < 0) {
+      return -1;
+    }
+  }
+  buffer[buf.offset] = '\0';
+  return 1;
+}
+
 /* Note: NOT utf-8 */
 HTSEXT_API int hts_buildtopindex(httrackp * opt, const char *path,
                                  const char *binpath) {

src/htstools.h

@@ -73,6 +73,20 @@ HTS_INLINE int rech_tageq_all(const char *adr, const char *s);
 int hts_template_format(FILE *const out, const char *format, ...);
 int hts_template_format_str(char *buffer, size_t size, const char *format, ...);
 
+// A footer named field and its already-context-escaped value.
+typedef struct hts_footer_field {
+  const char *name;
+  const char *value;
+} hts_footer_field;
+
+// Expand a footer template. A "%s" in it selects the legacy positional model,
+// consuming the "addr"/"path"/"date"/"version" fields in that order; otherwise
+// "{name}" is substituted from fields by name ("{{"/"}}" emit a literal brace,
+// an unknown "{...}" is left verbatim). Values must already be escaped for the
+// target context by the caller. Returns <0 on overflow.
+int hts_footer_format(char *buffer, size_t size, const char *footer,
+                      const hts_footer_field *fields, size_t nfields);
+
 #define rech_tageq(adr,s) \
   ( \
     ( (*((adr)-1)=='<') || (is_space(*((adr)-1))) ) ? \

src/htswarc.h

@@ -0,0 +1,131 @@
+/* ------------------------------------------------------------ */
+/*
+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
+*/
+
+/* ------------------------------------------------------------ */
+/* HTTrack WARC/1.1 output writer (ISO 28500). Internal, not installed.
+   All WARC record serialization, gzip-member framing, digests, UUID and
+   revisit dedup live here; the engine only stashes the request, frees it,
+   and calls one entry point per finished transaction. */
+/* ------------------------------------------------------------ */
+
+#ifndef HTS_WARC_DEFH
+#define HTS_WARC_DEFH
+
+#include "htsopt.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* opt->warc_file sentinel: --warc with no argument => auto-name the archive
+   under the project's output directory at open time. */
+#define WARC_AUTONAME "\001auto"
+
+/* htsblk.warc_truncated / WARC-Truncated reason tokens (ISO 28500 sec 5.13).
+   A cap-truncated body is still archived, tagged with why it was cut short. */
+#define WARC_TRUNC_NONE 0
+#define WARC_TRUNC_LENGTH 1     /* hit a size cap (-M mirror / -m per-file) */
+#define WARC_TRUNC_TIME 2       /* hit the mirror time cap (-E/--max-time) */
+#define WARC_TRUNC_DISCONNECT 3 /* connection dropped mid-body */
+
+/* WARC-Truncated token for a warc_truncated code, or NULL for none. */
+const char *warc_truncated_reason(int code);
+
+typedef struct warc_writer warc_writer;
+
+/* Stash the raw request header block (bstr.buffer) on r for the later WARC
+   request record; frees any prior stash. No-op when reqhdr is NULL. */
+void warc_stash_request(htsblk *r, const char *reqhdr);
+
+/* Stash the raw response header block: deletehttp frees r.headers when the
+   socket closes, before back_finalize, so keep a WARC-owned copy. */
+void warc_stash_response(htsblk *r, const char *resphdr);
+
+/* Free both stashed header blocks (idempotent, NULL-safe). */
+void warc_free_request(htsblk *r);
+
+/* Adopt the de-chunked compressed spool at tmpfile_path onto
+   r->warc_rawpath/warc_rawsize (strdupt; frees any prior) so the WARC record
+   stores the body verbatim. No-op leaving warc_rawpath NULL when tmpfile_path
+   is empty or the spool is missing/empty (the record then stores the decoded
+   in-memory/on-disk body instead). */
+void warc_adopt_rawspool(htsblk *r, const char *tmpfile_path);
+
+/* Emit the request + response (or revisit) records for one finished
+   transaction. Lazily opens the writer into opt->state.warc; a no-op (logged
+   once) if the archive cannot be created. */
+void warc_write_backtransaction(httrackp *opt, lien_back *back);
+
+/* Close and free the writer held in opt->state.warc, if any. */
+void warc_close_opt(httrackp *opt);
+
+/* --- Direct writer API (used by the hooks above and the self-test). --- */
+
+/* Create the archive at path (auto-named when path is WARC_AUTONAME), writing
+   the warcinfo record. .warc.gz => one gzip member per record; .warc => raw.
+   Returns NULL on failure. */
+warc_writer *warc_open(httrackp *opt, const char *path);
+
+/* Flush, close and free the writer (NULL-safe). */
+void warc_close(warc_writer *w);
+
+/* SURT-canonicalize url into out[outsz] (the CDXJ sort key). Returns 0 on
+   success, -1 on error or truncation. Exposed for the -#test=warc-surt test. */
+int warc_surt(const char *url, char *out, size_t outsz);
+
+/* Write one transaction's request + response (or revisit) records.
+   target_uri:  absolute URL fetched.
+   ip:          numeric peer IP, or NULL/"" to omit.
+   req_hdr:     exact request header block sent, or NULL to skip the request.
+   resp_hdr:    raw received response header block (status line + headers).
+   body/body_len: decoded in-memory body, or NULL when on disk.
+   body_path:   file re-read for the body when body==NULL (may be NULL).
+   is_update_unchanged: nonzero for a 304 server-not-modified revisit.
+   truncated: a WARC_TRUNC_* reason to tag a cap-truncated body, else 0.
+   The body is stored verbatim: Content-Encoding is kept and Content-Length set
+   to body_len, so body/body_len must be the as-received (coded) bytes.
+   Returns 0 on success, -1 on error. */
+int warc_write_transaction(warc_writer *w, const char *target_uri,
+                           const char *ip, const char *req_hdr,
+                           const char *resp_hdr, const char *body,
+                           size_t body_len, const char *body_path,
+                           int statuscode, int is_update_unchanged,
+                           int truncated);
+
+/* Write one non-HTTP capture as a single WARC 'resource' record: the block is
+   the raw payload (no HTTP envelope), Content-Type is the payload's own MIME.
+   Used for ftp:// transfers. truncated is a WARC_TRUNC_* reason or 0.
+   Returns 0 on success, -1 on error. */
+int warc_write_resource(warc_writer *w, const char *target_uri, const char *ip,
+                        const char *content_type, const char *body,
+                        size_t body_len, const char *body_path, int truncated);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif

src/libhttrack.vcxproj

@@ -135,6 +135,7 @@
     <ClCompile Include="htswizard.c" />
     <ClCompile Include="htswrap.c" />
     <ClCompile Include="htszlib.c" />
+    <ClCompile Include="htswarc.c" />
     <ClCompile Include="md5.c" />
     <ClCompile Include="minizip\ioapi.c" />
     <ClCompile Include="minizip\iowin32.c" />

tests/01_engine-footer-overflow.test

@@ -0,0 +1,56 @@
+#!/bin/bash
+#
+# Keep this POSIX-portable: the harness runs it via $(BASH), which is a plain
+# POSIX /bin/sh on some platforms (e.g. macOS), so avoid bashisms despite the
+# #!/bin/bash above.
+
+# A -%F footer whose expansion overflows the on-page buffer must be dropped, not
+# crash the crawl. Before the fix the unchecked hts_footer_format return left the
+# buffer unterminated and the next strcatbuff aborted (SIGABRT).
+
+set -eu
+
+# The overflow needs a path longer than Windows MAX_PATH (260), so both the
+# source tree and the mirror output blow past it there; run on POSIX only. The
+# fix itself is platform-independent and covered on Linux/macOS.
+case "$(uname -s 2>/dev/null)" in
+MINGW* | MSYS* | CYGWIN*) exit 77 ;;
+esac
+
+dir=$(mktemp -d)
+trap 'rm -rf "$dir"' EXIT
+
+# A few-hundred-char file path (kept well under the URL length limit) makes the
+# {path} field long.
+seg=aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+deep="$dir"
+i=0
+while [ "$i" -lt 6 ]; do
+    deep="$deep/$seg"
+    i=$((i + 1))
+done
+mkdir -p "$deep"
+printf '<html><body>hi</body></html>' >"$deep/index.html"
+
+# 40 {path} references (~240 chars, under the 254-char -%F cap); expanded against
+# a few-hundred-char path this far exceeds the per-page footer buffer.
+footer=""
+i=0
+while [ "$i" -lt 40 ]; do
+    footer="$footer{path}"
+    i=$((i + 1))
+done
+
+mir="$dir/mir"
+httrack "file://$deep/index.html" -O "$mir" -%F "$footer" -q -s0 -%v0 \
+    >/dev/null 2>&1 || {
+    echo "crawl failed/aborted (exit $?) on an oversized footer" >&2
+    exit 1
+}
+
+# The crawled page must exist (proves the URL wasn't rejected for length, so the
+# footer path ran). Look under file/, not $mir, to skip the makeindex top index.
+find "$mir/file" -name index.html | grep -q . || {
+    echo "page not mirrored; the oversized-footer path was not exercised" >&2
+    exit 1
+}

tests/01_engine-footerfmt.test

@@ -0,0 +1,42 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# -%F footer expansion (hts_footer_format via -#test=footerfmt). Fixed fields:
+# addr=host.example path=/dir/page.html date=DATE version=VER.
+ftr() {
+    out="$(httrack -O /dev/null -#test=footerfmt "$1")"
+    test "$out" == "$2" || {
+        echo "FAIL: '$1' -> '$out' (want '$2')"
+        exit 1
+    }
+}
+
+# Legacy positional model: a template with %s keeps the historic addr/path/date
+# order byte-for-byte (backward compatibility).
+ftr '<!-- Mirrored from %s%s by X, %s -->' \
+    '<!-- Mirrored from host.example/dir/page.html by X, DATE -->'
+# Legacy arg overflow past the four fields yields the historic "???" marker.
+ftr 'a %s b %s c %s d %s e %s' 'a host.example b /dir/page.html c DATE d VER e ???'
+# Legacy %% is a literal percent; an unknown %x passes through verbatim.
+ftr '100%% %d %s' '100% %d host.example'
+
+# Named model (no %s): fields substitute by name, in any order or subset.
+ftr '{addr}{path} {version} {date}' 'host.example/dir/page.html VER DATE'
+ftr 'built {date}' 'built DATE'
+# A literal char abutting a field's '}' survives (guards the index advance).
+ftr '{date}!{addr}' 'DATE!host.example'
+# {{ and }} escape to a literal brace.
+ftr 'a {{ b }} {addr}' 'a { b } host.example'
+# Unknown, empty, or unterminated braces are emitted verbatim (typos stay visible).
+ftr '{bogus} {} {addr' '{bogus} {} {addr'
+# A literal percent is untouched in named mode (no positional interpretation).
+ftr '100% {path}' '100% /dir/page.html'
+# %s anywhere forces legacy mode, so a mixed template leaves {addr} literal.
+ftr '{addr} %s' '{addr} host.example'
+
+# The added named fields (url, lastmodified, mime, charset, status, size).
+ftr '{url}' 'http://host.example/dir/page.html'
+ftr 'src {lastmodified}, got {date}' 'src LASTMOD, got DATE'
+ftr '{mime}; {charset}; {status}; {size}' 'text/html; utf-8; 200; 1234'

tests/01_engine-warc-surt.test

@@ -0,0 +1,8 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# SURT canonicalization of the CDXJ sort key (--warc-cdx). Pure string work,
+# so it runs under the MSan-instrumented 01_engine glob.
+httrack -O /dev/null -#test=warc-surt | grep -q "warc-surt: OK"

tests/01_zlib-warc-cdx.test

@@ -0,0 +1,19 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# --warc-cdx CDXJ index over synthetic transactions: sorted, one line per
+# response/revisit/resource, each offset/length inflates to the right member.
+
+httrack_bin=$(cd "$(dirname "$(command -v httrack)")" && pwd)/httrack
+
+scratch=$(mktemp -d)
+trap 'rm -rf "$scratch"' EXIT
+
+out=$("$httrack_bin" -O /dev/null -#test=warc-cdx "$scratch/")
+echo "$out"
+case "$out" in
+*": OK") ;;
+*) exit 1 ;;
+esac

tests/01_zlib-warc-wacz.test

@@ -0,0 +1,26 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# --wacz packaging over synthetic transactions: the WACZ unzips in-process to
+# the fixed layout, every entry is ZIP STORE, each datapackage sha256 recomputes
+# from the stored bytes, and the digest chains datapackage.json. WACZ needs the
+# OpenSSL SHA-256 digests, so the self-test is absent on non-OpenSSL builds.
+
+httrack_bin=$(cd "$(dirname "$(command -v httrack)")" && pwd)/httrack
+
+if ! "$httrack_bin" -#test 2>&1 | grep -q '^  warc-wacz'; then
+    echo "warc-wacz self-test unavailable (build without OpenSSL); skipping"
+    exit 77
+fi
+
+scratch=$(mktemp -d)
+trap 'rm -rf "$scratch"' EXIT
+
+out=$("$httrack_bin" -O /dev/null -#test=warc-wacz "$scratch/")
+echo "$out"
+case "$out" in
+*": OK") ;;
+*) exit 1 ;;
+esac

tests/01_zlib-warc.test

@@ -0,0 +1,22 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# WARC/1.1 writer self-test: framing, Content-Length, gzip members, round-trip,
+# revisit dedup, plus v1.1 WARC-Truncated, ftp resource records, and
+# --warc-max-size rotation, over synthetic transactions.
+
+httrack_bin=$(cd "$(dirname "$(command -v httrack)")" && pwd)/httrack
+
+scratch=$(mktemp -d)
+trap 'rm -rf "$scratch"' EXIT
+
+for t in warc warc-trunc warc-ftp warc-rotate warc-verbatim; do
+    out=$("$httrack_bin" -O /dev/null "-#test=$t" "$scratch/")
+    echo "$out"
+    case "$out" in
+    *": OK") ;;
+    *) exit 1 ;;
+    esac
+done

tests/72_watchdog-crawl.test

@@ -0,0 +1,36 @@
+#!/bin/bash
+#
+# Control for wait_bounded: a wedged fetch must be reaped at the harness deadline,
+# not hang the CI step to its 45-min cap.
+
+: "${top_srcdir:=..}"
+
+fail() {
+    echo "FAIL: $*" >&2
+    exit 1
+}
+
+start=$SECONDS
+out=$(CRAWL_DEADLINE=3 bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
+    httrack 'BASEURL/watchdog/stall' 2>&1) && rc=0 || rc=$?
+elapsed=$((SECONDS - start))
+
+# Skip (not fail) on causes unrelated to the watchdog: no python3/server, or a
+# port-announce race (flaky-13).
+test "$rc" -ne 77 || {
+    echo "SKIP: local crawl prerequisites missing" >&2
+    exit 77
+}
+if printf '%s\n' "$out" | grep -q "could not discover server port"; then
+    echo "SKIP: server port announce raced" >&2
+    exit 77
+fi
+
+# The message prints only on the 124 reap, and 25s < the engine's --timeout=30, so
+# together they pin the fast exit on the 3s watchdog, not httrack giving up.
+test "$rc" -ne 0 || fail "stalled crawl reported success"
+test "$elapsed" -lt 25 || fail "watchdog fired late (${elapsed}s)"
+printf '%s\n' "$out" | grep -q "watchdog fired" ||
+    fail "crawl failed but not via the watchdog: $out"
+
+echo "crawl watchdog OK (reaped in ${elapsed}s)"

tests/73_local-warc.test

@@ -0,0 +1,21 @@
+#!/bin/bash
+#
+# A --warc crawl writes a standards-conformant WARC/1.1 archive, and an
+# --update re-crawl of an unchanged (all-304) site emits revisit records.
+# The stdlib validator (no warcio) is the real gate: it byte-compares the
+# fresh page.html response body against what the server served, asserts the
+# encoding headers were stripped and the payload digest matches, then checks
+# the update pass turned the unchanged assets into revisits (no full response).
+
+set -eu
+
+: "${top_srcdir:=..}"
+
+# page.html body served by tests/local-server.py (route_mini304_page).
+export WARC_VALIDATE_BODY="page.html=3c68746d6c3e3c626f64793e74696e7920636163686561626c6520706167653c2f626f64793e3c2f68746d6c3e0a"
+export WARC_VALIDATE_NORESP="index.html page.html"
+
+bash "$top_srcdir/tests/local-crawl.sh" --errors 0 --rerun --warc-validate \
+    --log-found 'no files updated' \
+    --found 'mini304/index.html' --found 'mini304/page.html' \
+    httrack 'BASEURL/mini304/index.html' --warc-file warc-out

tests/74_local-warc-verbatim.test

@@ -0,0 +1,22 @@
+#!/bin/bash
+#
+# A --warc crawl stores compressed bodies verbatim (the default): the response
+# record keeps Content-Encoding: gzip and its stored bytes inflate back to the
+# served page. The validator's --verbatim mode is the differential gate:
+# inflate(stored) must equal the decoded body the server compressed.
+#
+# Two fixtures cover both adoption branches of back_finalize: page.html (text/html)
+# takes the in-memory branch; data.bin (application/octet-stream) is streamed to
+# disk, so it exercises the is_write direct-to-disk spool adoption.
+
+set -eu
+
+: "${top_srcdir:=..}"
+
+# decoded bodies served (gzip-coded) by route_warcgz_page and route_warcgz_data.
+export WARC_VALIDATE_BODY="warcgz/page.html=3c68746d6c3e3c626f64793e766572626174696d20677a6970207061676520666f72205741524320737472617465677920413c2f626f64793e3c2f68746d6c3e0a warcgz/data.bin=766572626174696d20677a6970206f637465742d73747265616d20626f647920666f722074686520574152432069735f777269746520706174680a"
+export WARC_VALIDATE_VERBATIM=1
+
+bash "$top_srcdir/tests/local-crawl.sh" --errors 0 --warc-validate \
+    --found 'warcgz/index.html' --found 'warcgz/page.html' --found 'warcgz/data.bin' \
+    httrack 'BASEURL/warcgz/index.html' --warc-file warc-out

tests/74_local-warc-wacz.test

@@ -0,0 +1,15 @@
+#!/bin/bash
+#
+# A --wacz crawl packages the WARC archive, its CDXJ index and a generated
+# pages.jsonl into a single WACZ file at crawl end. The stdlib validator is the
+# real gate: STORE-mode entries, the fixed layout, recomputed sha256 digests and
+# the datapackage-digest chain (plus py-wacz/pywb when importable). The crawl
+# skips cleanly on a build without OpenSSL (no conformant SHA-256 -> no package).
+
+set -eu
+
+: "${top_srcdir:=..}"
+
+bash "$top_srcdir/tests/local-crawl.sh" --errors 0 --wacz-validate \
+    --found 'mini304/index.html' --found 'mini304/page.html' \
+    httrack 'BASEURL/mini304/index.html' --warc-file warc-out --wacz

tests/Makefile.am

@@ -3,7 +3,7 @@
 # silently drop it from the dist tarball and break "make distcheck".
 EXTRA_DIST = $(TESTS) crawl-test.sh run-all-tests.sh check-network.sh \
 	proxy-https-server.py socks5-server.py proxy-connect-server.py \
-	proxytestlib.py tls-stall-server.py \
+	proxytestlib.py tls-stall-server.py warc-validate.py wacz-validate.py \
 	local-crawl.sh local-server.py testlib.sh server.crt server.key \
 	server-root/simple/basic.html server-root/simple/link.html \
 	server-root/stripquery/index.html server-root/stripquery/a.html \
@@ -38,6 +38,8 @@ TESTS = \
 	01_engine-dnstimeout.test \
 	01_engine-doitlog.test \
 	01_engine-entities.test \
+	01_engine-footerfmt.test \
+	01_engine-footer-overflow.test \
 	01_engine-filelist.test \
 	01_engine-filter.test \
 	01_engine-filterdual.test \
@@ -76,8 +78,12 @@ TESTS = \
 	01_engine-unescape-bounds.test \
 	01_engine-useragent.test \
 	01_engine-version-macros.test \
+	01_engine-warc-surt.test \
 	01_engine-xfread.test \
 	01_zlib-acceptencoding.test \
+	01_zlib-warc.test \
+	01_zlib-warc-cdx.test \
+	01_zlib-warc-wacz.test \
 	01_zlib-contentcodings.test \
 	01_zlib-cache.test \
 	01_zlib-cache-corrupt.test \
@@ -152,6 +158,10 @@ TESTS = \
 	67_engine-delayed-truncate.test \
 	68_webhttrack-outdir-charset.test \
 	69_local-intl-logdir.test \
-	71_local-crange-repaircache.test
+	71_local-crange-repaircache.test \
+	72_watchdog-crawl.test \
+	73_local-warc.test \
+	74_local-warc-wacz.test \
+	74_local-warc-verbatim.test
 
 CLEANFILES = check-network_sh.cache

tests/local-crawl.sh

@@ -47,6 +47,8 @@ key="${testdir}/server.key"
 
 tls=
 verbose=
+warc_validate=
+wacz_validate=
 html_subdir=
 outdir_intl=
 rerun=
@@ -114,6 +116,10 @@ while test "$pos" -lt "$nargs"; do
     --debug) verbose=1 ;;
     --rerun) rerun=1 ;;           # run httrack a second time (update pass) before auditing
     --rerun-dead) rerun_dead=1 ;; # re-run with the server stopped (cache rollback)
+    # validate the produced .warc.gz (see the validation block near the end)
+    --warc-validate) warc_validate=1 ;;
+    # validate the produced .wacz package (stdlib, plus py-wacz/pywb if present)
+    --wacz-validate) wacz_validate=1 ;;
     --no-purge)
         nopurge=1
         audit+=("--no-purge")
@@ -183,16 +189,12 @@ debug "starting $python $server ${serverargs[*]}"
 "$python" "$(nativepath "$server")" "${serverargs[@]}" >"$serverlog" 2>&1 &
 serverpid=$!
 
-# Wait for the "PORT <n>" line (server prints it once bound).
+# Wait for the "PORT <n>" line (server prints it once bound). A cold Python
+# start under a parallel `make check -jN` can lag past a second on a loaded Windows runner.
 port=
-for _ in $(seq 1 50); do
-    if test -s "$serverlog"; then
-        line=$(head -n1 "$serverlog")
-        if test "${line%% *}" == "PORT"; then
-            port="${line#PORT }"
-            break
-        fi
-    fi
+for _ in $(seq 1 300); do
+    # Match anywhere: a startup warning merged via 2>&1 could precede the PORT line.
+    line=$(grep -m1 '^PORT ' "$serverlog" 2>/dev/null) && port="${line#PORT }" && break
     kill -0 "$serverpid" 2>/dev/null || die "server exited early: $(cat "$serverlog")"
     sleep 0.1
 done
@@ -243,13 +245,17 @@ fi
 # Localhost is fast; disable the rate/bandwidth safety limits but keep a
 # max-time backstop so a hang cannot wedge the suite.
 declare -a moreargs=(--quiet --max-time=120 --timeout=30 --disable-security-limits --robots=0)
+# Watchdog above --max-time so the engine limit fires first when healthy; only a
+# genuine wedge trips it. CRAWL_DEADLINE lets 72_watchdog-crawl drive it low.
+crawl_deadline=${CRAWL_DEADLINE:-180}
 log="${tmpdir}/log"
 info "running httrack ${hts[*]}"
 httrack -O "$odir" --user-agent="httrack $ver local ($(uname -mrs))" "${moreargs[@]}" "${hts[@]}" >"$log" 2>&1 &
 crawlpid=$!
-wait "$crawlpid"
+wait_bounded "$crawlpid" "$crawl_deadline"
 crawlres=$?
 crawlpid=
+test "$crawlres" -ne 124 || warning "crawl watchdog fired after ${crawl_deadline}s"
 # httrack exits 0 even on hard connect/DNS errors, so this is a backstop only;
 # the real guard is the audit below (--errors 0 plus the host-root existence check).
 test "$crawlres" -eq 0 || ! result "httrack exited $crawlres" || {
@@ -259,13 +265,20 @@ test "$crawlres" -eq 0 || ! result "httrack exited $crawlres" || {
 result "OK"
 grep -iE "^[0-9:]*[[:space:]]Error:" "${logroot}/hts-log.txt" >&2
 
+# Snapshot the first-pass WARC before an update pass overwrites it: the fresh
+# crawl carries the full response bodies, the update pass only revisits.
+if test -n "$warc_validate"; then
+    w1=$(find "$mirrorroot" -maxdepth 2 -name '*.warc.gz' 2>/dev/null | sort | tail -n1)
+    test -z "$w1" || cp "$w1" "${tmpdir}/warc-pass1.gz"
+fi
+
 # --- optional second pass: re-mirror into the same dir (cache/update path) ----
 if test -n "$rerun"; then
     info "re-running httrack (update pass)"
     httrack -O "$odir" --user-agent="httrack $ver local ($(uname -mrs))" \
         "${moreargs[@]}" "${hts[@]}" >"${log}.2" 2>&1 &
     crawlpid=$!
-    wait "$crawlpid"
+    wait_bounded "$crawlpid" "$crawl_deadline"
     crawlres=$?
     crawlpid=
     test "$crawlres" -eq 0 || ! result "update pass exited $crawlres" || {
@@ -293,7 +306,7 @@ if test -n "$rerun_args"; then
     httrack -O "$odir" --user-agent="httrack $ver local ($(uname -mrs))" \
         "${moreargs[@]}" "${hts[@]}" "${extra[@]}" >"${log}.2" 2>&1 &
     crawlpid=$!
-    wait "$crawlpid"
+    wait_bounded "$crawlpid" "$crawl_deadline"
     crawlres=$?
     crawlpid=
     test "$crawlres" -eq 0 || ! result "second pass exited $crawlres" || {
@@ -315,7 +328,7 @@ if test -n "$rerun_dead"; then
     httrack -O "$odir" --user-agent="httrack $ver local ($(uname -mrs))" \
         "${moreargs[@]}" "${hts[@]}" >"${log}.dead" 2>&1 &
     crawlpid=$!
-    wait "$crawlpid" || true
+    wait_bounded "$crawlpid" "$crawl_deadline" || true
     crawlpid=
     result "OK (dead pass ran)"
     # The dead pass must have gone through the no-data rollback, not bailed out
@@ -350,6 +363,65 @@ done
 test -n "$hostroot" || die "could not find host root under $out"
 debug "host root: $hostroot"
 
+# --- optional WARC validation (stdlib validator, no warcio) ------------------
+# WARC_VALIDATE_BODY="URLSUB=HEX" byte-checks a fresh-crawl response body;
+# WARC_VALIDATE_NORESP="URLSUB..." asserts those assets are revisits post-update.
+if test -n "$warc_validate"; then
+    validator=$(nativepath "${testdir}/warc-validate.py")
+    warc=$(find "$mirrorroot" -maxdepth 2 \( -name '*.warc.gz' -o -name '*.warc' \) 2>/dev/null | sort | tail -n1)
+    test -n "$warc" || die "no WARC file produced under $mirrorroot"
+
+    # Fresh-crawl file (snapshot if an update pass overwrote it): full responses.
+    fresh="${tmpdir}/warc-pass1.gz"
+    test -f "$fresh" || fresh="$warc"
+    declare -a bodyargs=()
+    # WARC_VALIDATE_BODY holds one or more whitespace-separated SUB=HEX specs.
+    for spec in ${WARC_VALIDATE_BODY:-}; do
+        bodyargs+=(--expect-body-hex "$spec")
+    done
+    # compressed asset: assert the stored (verbatim) body inflates to the served
+    # body and keeps Content-Encoding, instead of expecting a decoded body.
+    test -n "${WARC_VALIDATE_VERBATIM:-}" && bodyargs+=(--verbatim)
+    info "validating fresh WARC (response bodies)"
+    "$python" "$validator" "$(nativepath "$fresh")" "${bodyargs[@]}" >&2 ||
+        die "fresh WARC validation failed"
+    result "OK"
+
+    # Final file: after an update pass the unchanged assets must be revisits.
+    if test -n "$rerun"; then
+        declare -a revargs=(--expect-revisit)
+        for sub in ${WARC_VALIDATE_NORESP:-}; do
+            revargs+=(--no-response-for "$sub")
+        done
+        info "validating update WARC (revisits)"
+        "$python" "$validator" "$(nativepath "$warc")" "${revargs[@]}" >&2 ||
+            die "update WARC validation failed"
+        result "OK"
+    fi
+
+    if command -v warcio >/dev/null 2>&1; then
+        info "warcio check (optional)"
+        if warcio check -v "$warc" >&2; then result "OK"; else die "warcio check failed"; fi
+    fi
+fi
+
+# --- optional WACZ validation (--wacz) --------------------------------------
+if test -n "$wacz_validate"; then
+    wacz=$(find "$mirrorroot" -maxdepth 2 -name '*.wacz' 2>/dev/null | sort | tail -n1)
+    if test -z "$wacz"; then
+        # No package: only acceptable when the build lacks OpenSSL (SHA-256).
+        if grep -aqi "WACZ requires an OpenSSL" "${logroot}/hts-log.txt"; then
+            info "no .wacz produced (build without OpenSSL); skipping"
+            exit 77
+        fi
+        die "no .wacz file produced under $mirrorroot"
+    fi
+    validator=$(nativepath "${testdir}/wacz-validate.py")
+    info "validating WACZ package"
+    "$python" "$validator" "$(nativepath "$wacz")" >&2 || die "WACZ validation failed"
+    result "OK"
+fi
+
 # No crawl, even a cancelled one, may leave engine temporaries: .delayed (#107,
 # #483), or the .z/.u content-coding temps (#557).
 info "checking for leftover engine temporaries"

tests/local-server.py

@@ -635,6 +635,34 @@ class Handler(SimpleHTTPRequestHandler):
             extra_headers=[("Content-Encoding", "gzip")],
         )
 
+    # A gzip-coded HTML page whose decoded body is known, for the verbatim-WARC
+    # differential (stored compressed bytes must inflate to this).
+    WARCGZ_BODY = b"<html><body>verbatim gzip page for WARC strategy A</body></html>\n"
+
+    # A NON-html gzip-coded asset: HTTrack streams it straight to disk, so the
+    # verbatim spool adoption runs on the is_write (direct-to-disk) branch of
+    # back_finalize, not the in-memory branch route_warcgz_page exercises.
+    WARCGZ_BIN_BODY = b"verbatim gzip octet-stream body for the WARC is_write path\n"
+
+    def route_warcgz_index(self):
+        self.send_html(
+            '\t<a href="page.html">page</a>\n' '\t<a href="data.bin">data</a>\n'
+        )
+
+    def route_warcgz_page(self):
+        self.send_raw(
+            gzip.compress(self.WARCGZ_BODY),
+            "text/html",
+            extra_headers=[("Content-Encoding", "gzip")],
+        )
+
+    def route_warcgz_data(self):
+        self.send_raw(
+            gzip.compress(self.WARCGZ_BIN_BODY),
+            "application/octet-stream",
+            extra_headers=[("Content-Encoding", "gzip")],
+        )
+
     # --- content codings ---------------------------------------------------
     # Canned br/zstd bodies (no brotli/zstd module in the stdlib): both decode
     # to CODEC_BODY. Regenerate with the brotli/zstd CLIs over that string.
@@ -979,6 +1007,22 @@ class Handler(SimpleHTTPRequestHandler):
         self.send_header("Content-Length", "0")
         self.end_headers()
 
+    # Always-stall endpoint for 72_watchdog-crawl: never finishes, so the harness
+    # watchdog must reap it.
+    def route_watchdog_stall(self):
+        self.send_response(200)
+        self.send_header("Content-Type", "application/octet-stream")
+        self.send_header("Content-Length", "1000000")  # never delivered
+        self.end_headers()
+        if self.command != "HEAD":
+            self.wfile.write(b"STALL")
+            self.wfile.flush()
+            try:
+                while True:
+                    time.sleep(3600)
+            except OSError:
+                pass
+
     # C7: stall the first GET (partial + temp-ref), then answer the resume's
     # Range with a bogus 304; httrack must drop the partial and refetch.
     RESUME304_BODY = b"C7DATA--" + bytes((i * 7 + 3) % 256 for i in range(8192))
@@ -1526,6 +1570,9 @@ class Handler(SimpleHTTPRequestHandler):
         "/gated/index.php": route_gated_index,
         "/gated/secret.php": route_gated_secret,
         "/robots.txt": route_robots,
+        "/warcgz/index.html": route_warcgz_index,
+        "/warcgz/page.html": route_warcgz_page,
+        "/warcgz/data.bin": route_warcgz_data,
         "/codec/index.html": route_codec_index,
         "/codec/br.html": route_codec_br,
         "/codec/zstd.html": route_codec_zstd,
@@ -1563,6 +1610,7 @@ class Handler(SimpleHTTPRequestHandler):
         "/types/gen.php": route_types,
         "/intl/index.html": route_intl_index,
         "/intl/" + INTL_NAME: route_intl_page,
+        "/watchdog/stall": route_watchdog_stall,
         "/resume/index.html": route_resume_index,
         "/resume/blob.txt": route_resume,
         "/resume304/index.html": route_resume304_index,

tests/testlib.sh

@@ -31,15 +31,13 @@ is_windows() {
     esac
 }
 
-# Stop a backgrounded server and reap it; MSYS cannot signal a native python.exe,
-# so only -9 lands. Every step is "|| true": callers run under set -e, and reaping
-# a server we just signalled makes wait return 143.
+# On Windows MSYS can't signal a native python.exe, so kill_tree ends the whole
+# tree (a bare kill -9 leaves children). "|| true" throughout: callers run under
+# set -e and the reap makes wait return 143.
 stop_server() {
     test -n "${1:-}" || return 0
     kill "$1" 2>/dev/null || true
-    if is_windows; then
-        kill -9 "$1" 2>/dev/null || true
-    fi
+    if is_windows; then kill_tree "$1"; fi
     wait "$1" 2>/dev/null || true
     return 0
 }
@@ -109,3 +107,19 @@ run_with_timeout() {
     done
     wait "$pid"
 }
+
+# Bound an already-backgrounded crawl (pid $1) at $2s, reaping it and returning 124
+# on overrun: a wedge past --max-time would else block wait() forever and hang the CI step.
+wait_bounded() {
+    local pid=$1 secs=$2 waited=0
+    while kill -0 "$pid" 2>/dev/null; do
+        if test "$waited" -ge "$secs"; then
+            kill_tree "$pid"
+            wait "$pid" 2>/dev/null || true
+            return 124
+        fi
+        sleep 1
+        waited=$((waited + 1))
+    done
+    wait "$pid"
+}

tests/wacz-validate.py

@@ -0,0 +1,95 @@
+#!/usr/bin/env python3
+# Validate a WACZ package with the stdlib only (no py-wacz needed): every entry
+# is ZIP STORE, the fixed layout is present, each datapackage resource hash and
+# size recomputes, the digest chains datapackage.json, and pages.jsonl carries
+# the json-pages-1.0 header. If py-wacz (`wacz validate`) is importable it runs
+# too; both gates must pass. Exit 0 = valid, nonzero = invalid.
+import sys
+import json
+import zipfile
+import hashlib
+
+
+def fail(msg):
+    print("wacz-validate: FAIL: %s" % msg, file=sys.stderr)
+    sys.exit(1)
+
+
+def main():
+    if len(sys.argv) < 2:
+        fail("usage: wacz-validate.py FILE.wacz")
+    path = sys.argv[1]
+    z = zipfile.ZipFile(path)
+    names = z.namelist()
+
+    for info in z.infolist():
+        if info.compress_type != zipfile.ZIP_STORED:
+            fail("%s is not STORE mode (%d)" % (info.filename, info.compress_type))
+
+    need_arc = any(
+        n.startswith("archive/") and n.endswith((".warc.gz", ".warc")) for n in names
+    )
+    for req, ok in (
+        ("archive/*.warc.gz", need_arc),
+        ("indexes/index.cdx", "indexes/index.cdx" in names),
+        ("pages/pages.jsonl", "pages/pages.jsonl" in names),
+        ("datapackage.json", "datapackage.json" in names),
+        ("datapackage-digest.json", "datapackage-digest.json" in names),
+    ):
+        if not ok:
+            fail("missing %s (entries: %s)" % (req, names))
+
+    lines = [ln for ln in z.read("pages/pages.jsonl").split(b"\n") if ln.strip()]
+    if not lines or json.loads(lines[0]).get("format") != "json-pages-1.0":
+        fail("pages.jsonl header is not json-pages-1.0: %r" % lines[:1])
+    body = [json.loads(ln) for ln in lines[1:]]
+    if not body:
+        fail("pages.jsonl has no page rows after the header")
+    for row in body:
+        if "url" not in row or "ts" not in row:
+            fail("pages.jsonl row missing url/ts: %r" % row)
+
+    dp = json.loads(z.read("datapackage.json"))
+    if dp.get("profile") != "data-package":
+        fail("profile != data-package: %r" % dp.get("profile"))
+    if dp.get("wacz_version") != "1.1.1":
+        fail("wacz_version != 1.1.1: %r" % dp.get("wacz_version"))
+    resources = dp.get("resources", [])
+    if not resources:
+        fail("datapackage has no resources")
+    for r in resources:
+        data = z.read(r["path"])
+        h = "sha256:" + hashlib.sha256(data).hexdigest()
+        if h != r["hash"]:
+            fail("%s hash %s != %s" % (r["path"], h, r["hash"]))
+        if len(data) != r["bytes"]:
+            fail("%s bytes %d != %d" % (r["path"], len(data), r["bytes"]))
+
+    dig = json.loads(z.read("datapackage-digest.json"))
+    want = "sha256:" + hashlib.sha256(z.read("datapackage.json")).hexdigest()
+    if dig.get("path") != "datapackage.json" or dig.get("hash") != want:
+        fail("digest chain broken: %r" % dig)
+
+    print(
+        "wacz-validate: OK (%d entries, %d resources, stdlib)"
+        % (len(names), len(resources))
+    )
+
+    # Optional stricter gate when py-wacz is present.
+    try:
+        import wacz  # noqa: F401
+    except Exception:
+        return
+    try:
+        from wacz.main import main as wacz_main  # type: ignore
+    except Exception:
+        return
+    print("wacz-validate: running py-wacz validate")
+    rc = wacz_main(["validate", "-f", path])
+    if rc not in (0, None):
+        fail("py-wacz validate returned %r" % rc)
+    print("wacz-validate: py-wacz OK")
+
+
+if __name__ == "__main__":
+    main()

tests/warc-validate.py

@@ -0,0 +1,186 @@
+#!/usr/bin/env python3
+# Structural + semantic WARC/1.1 validator, Python stdlib only (no warcio):
+# walks the concatenated gzip members with zlib (gzip.decompress would fuse them
+# and lose per-record boundaries) and checks each record against the spec.
+#
+# Options:
+#   --expect-revisit          at least one revisit record must be present
+#   --expect-body-hex SUB=HEX a response whose WARC-Target-URI contains SUB must
+#                             have an entity body byte-equal to bytes.fromhex(HEX),
+#                             no Content-Encoding/Transfer-Encoding header, and a
+#                             WARC-Payload-Digest matching sha1(body) when present
+#   --no-response-for SUB     the asset containing SUB must be a revisit: no
+#                             response may target it, and a revisit must
+#   --verbatim                compressed asset: --expect-body-hex instead keeps
+#                             Content-Encoding, checks the HTTP Content-Length is
+#                             the stored (compressed) length, asserts the stored
+#                             body inflates to HEX (the served plaintext), and
+#                             requires the payload digest when the file emits any
+import base64
+import hashlib
+import sys
+import zlib
+
+
+def records(data):
+    """Yield each record's decompressed bytes (one gzip member per record)."""
+    if data[:2] != b"\x1f\x8b":  # uncompressed .warc: split on the record magic
+        parts = data.split(b"WARC/1.")
+        for p in parts[1:]:
+            yield b"WARC/1." + p
+        return
+    while data:
+        d = zlib.decompressobj(zlib.MAX_WBITS | 16)
+        block = d.decompress(data) + d.flush()
+        yield block
+        data = d.unused_data
+
+
+def field(header, name):
+    for line in header.split(b"\r\n"):
+        if line.lower().startswith(name.lower() + b":"):
+            return line.split(b":", 1)[1].strip()
+    return None
+
+
+def opt_values(argv, name):
+    out = []
+    for i, a in enumerate(argv):
+        if a == name and i + 1 < len(argv):
+            out.append(argv[i + 1])
+    return out
+
+
+def check_body(rec, http_hdr, body, sub, want):
+    if b"Content-Encoding" in http_hdr or b"Transfer-Encoding" in http_hdr:
+        sys.exit("record for %s kept a content/transfer-encoding header" % sub)
+    if body != want:
+        sys.exit(
+            "body mismatch for %s: got %d bytes, expected %d"
+            % (sub, len(body), len(want))
+        )
+    pd = field(rec[: rec.find(b"\r\n\r\n")], b"WARC-Payload-Digest")
+    if pd is not None and pd.startswith(b"sha1:"):
+        want_b32 = base64.b32encode(hashlib.sha1(want).digest()).decode("ascii")
+        if pd[5:].decode("ascii") != want_b32:
+            sys.exit("WARC-Payload-Digest mismatch for %s" % sub)
+
+
+def check_body_verbatim(rec, http_hdr, body, sub, want, digests_emitted):
+    """Verbatim: the stored body is the coded octets, Content-Encoding is kept,
+    the HTTP Content-Length equals the stored (compressed) length, inflating the
+    body yields the served plaintext, and the payload digest is over the coded
+    body. The differential: inflate(stored) == the body the server compressed."""
+    if b"Content-Encoding" not in http_hdr:
+        sys.exit("verbatim record for %s dropped Content-Encoding" % sub)
+    if b"Transfer-Encoding" in http_hdr:
+        sys.exit("verbatim record for %s kept Transfer-Encoding" % sub)
+    hcl = field(http_hdr, b"Content-Length")
+    if hcl is None or int(hcl) != len(body):
+        sys.exit("verbatim record for %s: HTTP Content-Length != stored body" % sub)
+    try:
+        decoded = zlib.decompress(body, zlib.MAX_WBITS | 16)
+    except Exception as exc:
+        sys.exit("verbatim record for %s: body did not inflate: %s" % (sub, exc))
+    if decoded != want:
+        sys.exit(
+            "verbatim decoded mismatch for %s: got %d bytes, expected %d"
+            % (sub, len(decoded), len(want))
+        )
+    pd = field(rec[: rec.find(b"\r\n\r\n")], b"WARC-Payload-Digest")
+    # Catch a regression that drops the digest on the verbatim path, but only
+    # when this file emits digests at all (an OpenSSL build; none otherwise).
+    if digests_emitted and pd is None:
+        sys.exit("verbatim record for %s: missing WARC-Payload-Digest" % sub)
+    if pd is not None and pd.startswith(b"sha1:"):
+        want_b32 = base64.b32encode(hashlib.sha1(body).digest()).decode("ascii")
+        if pd[5:].decode("ascii") != want_b32:
+            sys.exit("WARC-Payload-Digest (compressed) mismatch for %s" % sub)
+
+
+def main():
+    argv = sys.argv[1:]
+    expect_revisit = "--expect-revisit" in argv
+    verbatim = "--verbatim" in argv
+    body_specs = [s.split("=", 1) for s in opt_values(argv, "--expect-body-hex")]
+    no_resp = opt_values(argv, "--no-response-for")
+    path = [a for a in argv if not a.startswith("--") and "=" not in a][0]
+    data = open(path, "rb").read()
+
+    # digests are emitted only on an OpenSSL build; detect it once so --verbatim
+    # can require the payload digest exactly when the file carries any.
+    digests_emitted = any(
+        b"WARC-Payload-Digest" in r[: r.find(b"\r\n\r\n")] for r in records(data)
+    )
+
+    total = revisits = responses = infos = 0
+    body_hits = {sub: False for sub, _ in body_specs}
+    revisit_hits = {sub: False for sub in no_resp}
+    for rec in records(data):
+        total += 1
+        if not rec.startswith(b"WARC/1."):
+            sys.exit("record %d: bad magic %r" % (total, rec[:16]))
+        sep = rec.find(b"\r\n\r\n")
+        if sep < 0:
+            sys.exit("record %d: no header terminator" % total)
+        hdr_end = sep + 4
+        header = rec[:sep]
+        cl = field(header, b"Content-Length")
+        if cl is None:
+            sys.exit("record %d: no Content-Length" % total)
+        block_len = int(cl)
+        if hdr_end + block_len + 4 != len(rec):
+            sys.exit(
+                "record %d: Content-Length %d != block length %d"
+                % (total, block_len, len(rec) - hdr_end - 4)
+            )
+        if rec[hdr_end + block_len :] != b"\r\n\r\n":
+            sys.exit("record %d: missing \\r\\n\\r\\n trailer" % total)
+        wtype = field(header, b"WARC-Type")
+        uri = field(header, b"WARC-Target-URI") or b""
+        if wtype == b"warcinfo":
+            infos += 1
+        elif wtype == b"response":
+            responses += 1
+            for sub in no_resp:
+                if sub.encode() in uri:
+                    sys.exit("unexpected full response for %s (want revisit)" % sub)
+            block = rec[hdr_end : hdr_end + block_len]
+            bsep = block.find(b"\r\n\r\n")
+            http_hdr, body = block[:bsep], block[bsep + 4 :]
+            for sub, hexval in body_specs:
+                if sub.encode() in uri:
+                    want = bytes.fromhex(hexval)
+                    if verbatim:
+                        check_body_verbatim(
+                            rec, http_hdr, body, sub, want, digests_emitted
+                        )
+                    else:
+                        check_body(rec, http_hdr, body, sub, want)
+                    body_hits[sub] = True
+        elif wtype == b"revisit":
+            revisits += 1
+            for sub in no_resp:
+                if sub.encode() in uri:
+                    revisit_hits[sub] = True
+
+    if total < 1:
+        sys.exit("no records found")
+    if infos != 1:
+        sys.exit("expected exactly one warcinfo record, got %d" % infos)
+    if expect_revisit and revisits < 1:
+        sys.exit("expected at least one revisit record, found none")
+    for sub, hit in body_hits.items():
+        if not hit:
+            sys.exit("no response record found for --expect-body-hex %s" % sub)
+    for sub, hit in revisit_hits.items():
+        if not hit:
+            sys.exit("no revisit record found for unchanged asset %s" % sub)
+    print(
+        "warc-validate: %d records OK (%d response, %d revisit)"
+        % (total, responses, revisits)
+    )
+
+
+if __name__ == "__main__":
+    main()

tests/webhttrack-smoke.sh

@@ -46,9 +46,12 @@ cat >"$stubdir/x-www-browser" <<EOF
 echo "stub browser invoked with: \$1" >&2
 # Also fetch an option page and require a rendered title='' tooltip: proves the
 # option template expands and the \${html:} filter escapes into the attribute.
+# option9 additionally proves the WARC control renders with its expanded label.
 opturl="\${1%/}/server/option2.html"
+warcurl="\${1%/}/server/option9.html"
 if body="\$(curl -fsSL --max-time 20 "\$1")" && printf '%s' "\$body" | grep -qai httrack && printf '%s' "\$body" | grep -qaF step2.html &&
-    opt="\$(curl -fsSL --max-time 20 "\$opturl")" && printf '%s' "\$opt" | grep -qaF "title='"; then
+    opt="\$(curl -fsSL --max-time 20 "\$opturl")" && printf '%s' "\$opt" | grep -qaF "title='" &&
+    warc="\$(curl -fsSL --max-time 20 "\$warcurl")" && printf '%s' "\$warc" | grep -qaF 'name="warcfile"' && printf '%s' "\$warc" | grep -qaF WARC; then
     echo PASS >"$marker"
 else
     echo "FAIL: unexpected response from \$1" >"$marker"