mirror of
https://github.com/xroche/httrack.git
synced 2026-07-28 03:22:12 +03:00
c38bf69c7d
--update already knows which resources were new, which changed and which the server called unchanged, and throws it away: the flags reach file_notify() and go no further than a log line, while deletions exist only as a side effect of purging. --changes (-%d) keeps all of it and writes hts-changes.json plus a one-line summary in the log. "Changed" means the bytes differ, not that the server re-sent the resource. Comparing the mirrored files directly would not work: HTTrack stamps every parsed page with the crawl date via the footer, so those bytes differ on every run. Payloads are compared instead, the previous one coming from the cache for parsed pages and from the local copy sampled just before it is overwritten for everything else. The mirror-relative path, not the URL, is the accumulator's key, so a redirect and its target that share a save name are one entry; and only the first notify for a file samples its pre-run state, so a retried transfer is not counted twice. What counts as already mirrored comes from the previous run's file index rather than from the file's presence on disk: a partial left by this crawl's own failed attempt is on disk but was never part of the previous mirror. The deleted set is now computed whether or not purging is enabled; unlinking still happens only under --purge-old. Closes #714 Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Signed-off-by: Xavier Roche <xroche@gmail.com>
298 lines
8.7 KiB
HTML
298 lines
8.7 KiB
HTML
<html xmlns="http://www.w3.org/1999/xhtml" lang="${LANGUAGE_ISO}">
|
|
|
|
<head>
|
|
<meta http-equiv="Content-Type" content="text/html; charset=${LANGUAGE_CHARSET}" />
|
|
<meta name="description" content="${LANG_METADESC}" />
|
|
<meta name="keywords" content="${LANG_METAKEYW}" />
|
|
<title>'${projname}' - HTTrack Website Copier</title>
|
|
|
|
<link rel="stylesheet" type="text/css" media="screen" href="style.css">
|
|
<script type="text/javascript" src="ping.js" defer></script>
|
|
|
|
<script language="javascript">
|
|
<!--
|
|
function do_unload() {
|
|
}
|
|
function do_load() {
|
|
window.status=' ';
|
|
form.projname.select();
|
|
}
|
|
function key_event(event) {
|
|
if (event && event.keyCode && (event.keyCode == 13 || event.keyCode == 10)) {
|
|
form.nextBtn.click();
|
|
return false;
|
|
}
|
|
return true;
|
|
}
|
|
function checkname() {
|
|
if (form.projname.value != '') {
|
|
return true;
|
|
}
|
|
window.status='${LANG_S1}';
|
|
form.projname.select();
|
|
return false;
|
|
}
|
|
function info(str) {
|
|
window.status = str;
|
|
}
|
|
// -->
|
|
</script>
|
|
|
|
</head>
|
|
<body onLoad="do_load();" onUnload="do_unload();" onKeyPress="return key_event(event);">
|
|
|
|
<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 width="90%" id="subTitle">${LANG_OSFWB}</td>
|
|
<td id="subTitle" align="right">
|
|
<a href="/server/file.html" target="_blank"
|
|
onClick="window.open('/server/file.html', 'help', 'toolbar=no, location=no, directories=no, status=yes, menubar=no, scrollbars=yes, resizable=yes, width=640, height=480'); return false"
|
|
title='${html:LANG_O1}' onMouseOver="info('${html:html:LANG_O1}'); return true" onMouseOut="info(' '); return true"
|
|
style="color:#FFFFFF"
|
|
>
|
|
${LANG_O1}
|
|
</a>
|
|
</td>
|
|
${/* show help only if available */}
|
|
${do:if-file-exists:html/index.html}
|
|
<td id="subTitle">|</td>
|
|
<td id="subTitle" align="right">
|
|
<a href="/index.html" target="_blank"
|
|
onClick="window.open('/server/help.html', 'help', 'toolbar=no, location=no, directories=no, status=yes, menubar=no, scrollbars=yes, resizable=yes, width=640, height=480'); return false"
|
|
title='${html:LANG_TIPHELP}' onMouseOver="info('${html:html:LANG_TIPHELP}'); return true" onMouseOut="info(' '); return true"
|
|
style="color:#FFFFFF"
|
|
>
|
|
${LANG_O5}
|
|
</a>
|
|
</td>
|
|
${do:end-if}
|
|
</tr>
|
|
</table>
|
|
<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
|
|
<tr class="blak">
|
|
<td>
|
|
<table width="100%" border="0" align="center" cellspacing="1" cellpadding="0">
|
|
<tr>
|
|
<td colspan="6">
|
|
<table width="100%" border="0" align="center" cellspacing="0" cellpadding="10">
|
|
<tr>
|
|
<td id="pageContent">
|
|
<!-- ==================== End prologue ==================== -->
|
|
|
|
<table border="0" width="100%">
|
|
<tr><td width="90%">
|
|
<h2 align="center"><em>${fexist:index.html:LANG_G42}</em></h2>
|
|
</td>
|
|
${/* show help only if available */}
|
|
${do:if-file-exists:html/index.html}
|
|
<td>
|
|
<a href="/step1.html" target="_blank"
|
|
onClick="window.open('/step1.html', 'help', 'toolbar=no, location=no, directories=no, status=yes, menubar=no, scrollbars=yes, resizable=yes, width=640, height=480'); return false"
|
|
title='${html:LANG_TIPHELP}' onMouseOver="info('${html:html:LANG_TIPHELP}'); return true" onMouseOut="info(' '); return true"
|
|
>${LANG_TIPHELP}</a>
|
|
</td>
|
|
${do:end-if}
|
|
</tr></table>
|
|
|
|
${/* Default values for empty settings */}
|
|
${do:set:cache:1}
|
|
|
|
${/* Convert winprofile.ini into internal variables */}
|
|
${do:copy:CurrentUrl:urls}
|
|
${do:copy:Category:projcateg}
|
|
${do:copy:CurrentAction:todo}
|
|
${do:copy:CurrentURLList:filelist}
|
|
${do:copy:Proxy:proxy}
|
|
${do:copy:Port:port}
|
|
${do:copy:Near:link}
|
|
${do:copy:Test:testall}
|
|
${do:copy:ParseAll:parseall}
|
|
${do:copy:HTMLFirst:htmlfirst}
|
|
${do:copy:Cache:cache}
|
|
${do:copy:NoRecatch:norecatch}
|
|
${do:copy:Dos:dos}
|
|
${do:copy:Index:index}
|
|
${do:copy:WordIndex:index2}
|
|
${do:copy:Log:logf}
|
|
${do:copy:RemoveTimeout:remt}
|
|
${do:copy:RemoveRateout:rems}
|
|
${do:copy:KeepAlive:ka}
|
|
${do:copy:FollowRobotsTxt:robots}
|
|
${do:copy:NoErrorPages:errpage}
|
|
${do:copy:NoExternalPages:external}
|
|
${do:copy:NoPwdInPages:hidepwd}
|
|
${do:copy:NoQueryStrings:hidequery}
|
|
${do:copy:NoPurgeOldFiles:nopurge}
|
|
${do:copy:Cookies:cookies}
|
|
${do:copy:CookiesFile:cookiesfile}
|
|
${do:copy:CheckType:checktype}
|
|
${do:copy:ParseJava:parsejava}
|
|
${do:copy:HTTP10:http10}
|
|
${do:copy:TolerantRequests:toler}
|
|
${do:copy:UpdateHack:updhack}
|
|
${do:copy:URLHack:urlhack}
|
|
${do:copy:KeepWww:keepwww}
|
|
${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:Changes:changes}
|
|
${do:copy:LogType:logtype}
|
|
${do:copy:UseHTTPProxyForFTP:ftpprox}
|
|
${do:copy:ProxyType:proxytype}
|
|
${do:copy:Build:build}
|
|
${do:copy:PrimaryScan:filter}
|
|
${do:copy:Travel:travel}
|
|
${do:copy:GlobalTravel:travel2}
|
|
${do:copy:RewriteLinks:travel3}
|
|
${do:copy:BuildString:BuildString}
|
|
${do:copy:MaxHtml:maxhtml}
|
|
${do:copy:MaxOther:othermax}
|
|
${do:copy:MaxAll:sizemax}
|
|
${do:copy:MaxWait:pausebytes}
|
|
${do:copy:PauseFiles:pausefiles}
|
|
${do:copy:Sockets:connexion}
|
|
${do:copy:Retry:retry}
|
|
${do:copy:MaxTime:maxtime}
|
|
${do:copy:TimeOut:timeout}
|
|
${do:copy:RateOut:rate}
|
|
${do:copy:UserID:user}
|
|
${do:copy:Footer:footer}
|
|
${do:copy:MaxRate:maxrate}
|
|
${do:copy:WildCardFilters:url2}
|
|
${do:copy:Proxy:proxy}
|
|
${do:copy:Port:port}
|
|
${do:copy:Depth:depth}
|
|
${do:copy:ExtDepth:depth2}
|
|
${do:copy:MaxConn:maxconn}
|
|
${do:copy:MaxLinks:maxlinks}
|
|
${do:copy:MIMEDefsExt1:ext1}
|
|
${do:copy:MIMEDefsExt2:ext2}
|
|
${do:copy:MIMEDefsExt3:ext3}
|
|
${do:copy:MIMEDefsExt4:ext4}
|
|
${do:copy:MIMEDefsExt5:ext5}
|
|
${do:copy:MIMEDefsExt6:ext6}
|
|
${do:copy:MIMEDefsExt7:ext7}
|
|
${do:copy:MIMEDefsExt8:ext8}
|
|
${do:copy:MIMEDefsMime1:mime1}
|
|
${do:copy:MIMEDefsMime2:mime2}
|
|
${do:copy:MIMEDefsMime3:mime3}
|
|
${do:copy:MIMEDefsMime4:mime4}
|
|
${do:copy:MIMEDefsMime5:mime5}
|
|
${do:copy:MIMEDefsMime6:mime6}
|
|
${do:copy:MIMEDefsMime7:mime7}
|
|
${do:copy:MIMEDefsMime8:mime8}
|
|
${/* End convert winprofile.ini into internal variables */}
|
|
|
|
|
|
<br>
|
|
|
|
<form method="POST" action="step3.html" name="form">
|
|
<input type="hidden" name="sid" value="${sid}">
|
|
<input type="hidden" name="redirect" value="">
|
|
<input type="hidden" name="todo" value="1">
|
|
${do:if-project-file-exists:/hts-cache/winprofile.ini}
|
|
<input type="hidden" name="todo" value="7">
|
|
${do:end-if}
|
|
${do:if-project-file-exists:/hts-in_progress.lock}
|
|
<input type="hidden" name="todo" value="6">
|
|
${do:end-if}
|
|
|
|
<table border="0" width="100%">
|
|
<tr><td>
|
|
|
|
|
|
${do:loadhash}
|
|
|
|
${LANG_S11b}
|
|
<select name="loadprojname" onChange="form.redirect.value='step2.html'; form.submit()">
|
|
<option value=""> </option>
|
|
${liststr:winprofile}
|
|
</select>
|
|
|
|
<br>
|
|
|
|
${LANG_S11}
|
|
<input name="projname" value="${projname}"
|
|
title='${html:LANG_S1}' onMouseOver="info('${html:html:LANG_S1}'); return true" onMouseOut="info(' '); return true"
|
|
>
|
|
|
|
<br>
|
|
|
|
<table border="0">
|
|
<tr><td>
|
|
|
|
${LANG_S13}
|
|
<select name="loadprojcateg" onChange="form.redirect.value='step2.html'; form.submit()">
|
|
<option value=""> </option>
|
|
${liststr:wincateg}
|
|
</select>
|
|
</td><td>
|
|
<input name="projcateg" value="${projcateg}"
|
|
title='${html:LANG_S5}' onMouseOver="info('${html:html:LANG_S5}'); return true" onMouseOut="info(' '); return true"
|
|
>
|
|
|
|
</td></tr></table>
|
|
|
|
<br>
|
|
${LANG_S12}
|
|
<input name="path" value="${path}"
|
|
title='${html:LANG_S2}' onMouseOver="info('${html:html:LANG_S2}'); return true" onMouseOut="info(' '); return true"
|
|
>
|
|
<input type="button" value="refresh" onClick="form.redirect.value='step2.html'; form.submit()">
|
|
|
|
</td></tr>
|
|
|
|
<tr><td>
|
|
<table width="100%" border="0"><tr><td align="left">
|
|
<input type="submit" value=" << ${LANG_PREVIOUS} " onClick="form.redirect.value='index.html'; form.submit()"
|
|
title='${html:LANG_TIPPREV}' onMouseOver="info('${html:html:LANG_TIPPREV}'); return true" onMouseOut="info(' '); return true"
|
|
>
|
|
</td><td align="right">
|
|
<input name="nextBtn" type="submit" value=" ${LANG_NEXT} >> " onClick="return checkname();" default
|
|
title='${html:LANG_TIPNEXT}' onMouseOver="info('${html:html:LANG_TIPNEXT}'); return true" onMouseOut="info(' '); return true"
|
|
>
|
|
</td></tr></table>
|
|
|
|
${do:if-not-empty:urls}
|
|
<br>
|
|
<h2>${LANG_URLS}:</h2><br>
|
|
<h3><pre>${urls}</pre></h3>
|
|
<br>
|
|
${do:end-if:}
|
|
|
|
</td></tr>
|
|
</table>
|
|
|
|
</form>
|
|
|
|
<!-- ==================== 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><small>© 1998-2026 Xavier Roche & other contributors - Web Design: Leto Kauler.</small></small></td>
|
|
</tr>
|
|
</table>
|
|
|
|
</body>
|
|
|
|
</html>
|
|
|
|
|