CINXE.COM
ArchiveBot User Guide — ArchiveBot 1.6 documentation
<!doctype html><!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--><!--[if gt IE 8]><!--> <html class="no-js" lang="en"><!--<![endif]--> <head> <base href="https://archivebot.readthedocs.io/en/latest/"> <meta charset="utf-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>ArchiveBot User Guide — ArchiveBot 1.6 documentation</title> <script type="text/javascript" src="_static/js/modernizr.min.js"></script> <script type="text/javascript" id="documentation_options" data-url_root="./" src="_static/documentation_options.js"></script> <script type="text/javascript" src="_static/jquery.js"></script> <script type="text/javascript" src="_static/underscore.js"></script> <script type="text/javascript" src="_static/doctools.js"></script> <script type="text/javascript" src="_static/language_data.js"></script> <script type="text/javascript" src="_static/js/theme.js"></script> <link rel="stylesheet" href="_static/css/theme.css" type="text/css"> <link rel="stylesheet" href="_static/pygments.css" type="text/css"> <link rel="index" title="Index" href="genindex.html"> <link rel="search" title="Search" href="search.html"> <link rel="next" title="Commands" href="commands.html"><!-- RTD Extra Head --> <script type="application/json" id="READTHEDOCS_DATA">{"ad_free": false, "api_host": "https://readthedocs.org", "builder": "sphinx", "canonical_url": null, "docroot": "/doc/", "features": {"docsearch_disabled": false}, "global_analytics_code": "UA-17997319-1", "language": "en", "page": "index", "programming_language": "py", "project": "archivebot", "proxied_api_host": "/_", "source_suffix": ".rst", "subprojects": {}, "theme": "sphinx_rtd_theme", "user_analytics_code": "", "version": "latest"}</script><!-- Using this variable directly instead of using `JSON.parse` is deprecated. The READTHEDOCS_DATA global variable will be removed in the future. --> <script type="text/javascript"> READTHEDOCS_DATA = JSON.parse(document.getElementById('READTHEDOCS_DATA').innerHTML); </script><!-- end RTD <extrahead> --> <script async type="text/javascript" src="/_/static/javascript/readthedocs-addons.js"></script> <meta name="readthedocs-project-slug" content="archivebot"> <meta name="readthedocs-version-slug" content="latest"> <meta name="readthedocs-resolver-filename" content="/"> <meta name="readthedocs-http-status" content="200"> <meta http-equiv="X-Translated-By" content="Google"> <meta http-equiv="X-Translated-To" content="en"> <script type="text/javascript" src="https://www.gstatic.com/_/translate_http/_/js/k=translate_http.tr.en_GB.1hbgkFx4Qn8.O/am=DgY/d=1/rs=AN8SPfqlmAPxwfG457BPbRXwNq39oSMGHg/m=corsproxy" data-sourceurl="https://archivebot.readthedocs.io/en/latest/"></script> <link href="https://fonts.googleapis.com/css2?family=Material+Symbols+Outlined:opsz,wght,FILL,GRAD@20..48,100..700,0..1,-50..200" rel="stylesheet"> <script type="text/javascript" src="https://www.gstatic.com/_/translate_http/_/js/k=translate_http.tr.en_GB.1hbgkFx4Qn8.O/am=DgY/d=1/exm=corsproxy/ed=1/rs=AN8SPfqlmAPxwfG457BPbRXwNq39oSMGHg/m=phishing_protection" data-phishing-protection-enabled="false" data-forms-warning-enabled="true" data-source-url="https://archivebot.readthedocs.io/en/latest/"></script> <meta name="robots" content="none"> </head> <body class="wy-body-for-nav"> <script type="text/javascript" src="https://www.gstatic.com/_/translate_http/_/js/k=translate_http.tr.en_GB.1hbgkFx4Qn8.O/am=DgY/d=1/exm=corsproxy,phishing_protection/ed=1/rs=AN8SPfqlmAPxwfG457BPbRXwNq39oSMGHg/m=navigationui" data-environment="prod" data-proxy-url="https://archivebot-readthedocs-io.translate.goog" data-proxy-full-url="https://archivebot-readthedocs-io.translate.goog/en/latest/?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB" data-source-url="https://archivebot.readthedocs.io/en/latest/" data-source-language="auto" data-target-language="en" data-display-language="en-GB" data-detected-source-language="en" data-is-source-untranslated="false" data-source-untranslated-url="https://translate.google.com/website?sl=auto&tl=en&hl=en-GB&u=https://archivebot.readthedocs.io/en/latest/&anno=2" data-client="tr"></script> <div class="wy-grid-for-nav"> <nav data-toggle="wy-nav-shift" class="wy-nav-side"> <div class="wy-side-scroll"> <div class="wy-side-nav-search"><a href="https://archivebot-readthedocs-io.translate.goog/en/latest/?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#" class="icon icon-home"> ArchiveBot </a> <div class="version"> latest </div> <div role="search"> <form id="rtd-search-form" class="wy-form" action="search.html" method="get"><input type="text" name="q" placeholder="Search docs"> <input type="hidden" name="check_keywords" value="yes"> <input type="hidden" name="area" value="default"> </form> </div> </div> <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> <ul> <li class="toctree-l1"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB">Commands</a></li> <li class="toctree-l1"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB">ArchiveBot Redis layout</a></li> <li class="toctree-l1"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/admin.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB">ArchiveBot Administration</a></li> </ul> </div> </div> </nav> <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> <nav class="wy-nav-top" aria-label="top navigation"><i data-toggle="wy-nav-top" class="fa fa-bars"></i> <a href="https://archivebot-readthedocs-io.translate.goog/en/latest/?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#">ArchiveBot</a> </nav> <div class="wy-nav-content"> <div class="rst-content"> <div role="navigation" aria-label="breadcrumbs navigation"> <ul class="wy-breadcrumbs"> <li><a href="https://archivebot-readthedocs-io.translate.goog/en/latest/?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#">Docs</a> »</li> <li>ArchiveBot User Guide</li> <li class="wy-breadcrumbs-aside"><a href="https://translate.google.com/website?sl=auto&tl=en&hl=en-GB&u=https://github.com/ArchiveTeam/ArchiveBot/blob/master/doc/index.rst" class="fa fa-github"> Edit on GitHub</a></li> </ul> <hr> </div> <div role="main" class="document" itemscope itemtype="http://schema.org/Article"> <div itemprop="articleBody"> <div class="section" id="archivebot-user-guide"> <h1>ArchiveBot User Guide<a class="headerlink" href="https://archivebot-readthedocs-io.translate.goog/en/latest/?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#archivebot-user-guide" title="Permalink to this headline">¶</a></h1> <table class="docutils field-list" frame="void" rules="none"> <colgroup> <col class="field-name"> <col class="field-body"> </colgroup> <tbody valign="top"> <tr class="field-odd field"> <th class="field-name">Homepage:</th> <td class="field-body"><a class="reference external" href="https://translate.google.com/website?sl=auto&tl=en&hl=en-GB&u=http://www.archiveteam.org/index.php?title%3DArchiveBot">http://www.archiveteam.org/index.php?title=ArchiveBot</a></td> </tr> </tbody> </table> <p>Contents:</p> <div class="toctree-wrapper compound"> <ul> <li class="toctree-l1"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB">Commands</a> <ul> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#archive">archive</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#abort">abort</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#archiveonly">archiveonly</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#explain">explain</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#archiveonly-file">archiveonly < FILE</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#ignore">ignore</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#unignore">unignore</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#ignoreset">ignoreset</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#ignorereports">ignorereports</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#delay">delay</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#concurrency">concurrency</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#yahoo">yahoo</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#expire">expire</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#status">status</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#pending">pending</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#whereis">whereis</a></li> </ul></li> <li class="toctree-l1"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB">ArchiveBot Redis layout</a> <ul> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#connection">Connection</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#pipeline-pipeline-id"><code class="docutils literal notranslate"><span class="pre">pipeline:PIPELINE_ID</span></code></a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#hash-keys">Hash keys</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#ident-i-e-a-z0-9-25"><code class="docutils literal notranslate"><span class="pre">IDENT</span></code> (i.e. <code class="docutils literal notranslate"><span class="pre">[a-z0-9]{25,}</span></code>)</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#hash-keys-1">Hash keys</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#ident-ignores"><code class="docutils literal notranslate"><span class="pre">IDENT_ignores</span></code></a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#ident-log"><code class="docutils literal notranslate"><span class="pre">IDENT_log</span></code></a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#pipelines"><code class="docutils literal notranslate"><span class="pre">pipelines</span></code></a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#jobs-completed-jobs-aborted-jobs-failed"><code class="docutils literal notranslate"><span class="pre">jobs_completed</span></code>, <code class="docutils literal notranslate"><span class="pre">jobs_aborted</span></code>, <code class="docutils literal notranslate"><span class="pre">jobs_failed</span></code></a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#tweets-done-tweets-queue"><code class="docutils literal notranslate"><span class="pre">tweets:done</span></code>, <code class="docutils literal notranslate"><span class="pre">tweets:queue</span></code></a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#pubsub-channels">Pubsub channels</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#updates"><code class="docutils literal notranslate"><span class="pre">updates</span></code></a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/redis.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#archivebot-job-ident"><code class="docutils literal notranslate"><span class="pre">archivebot:job:IDENT</span></code></a></li> </ul></li> <li class="toctree-l1"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/admin.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB">ArchiveBot Administration</a> <ul> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/admin.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#basic-information">Basic Information</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/admin.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#how-to-add-new-archivebot-pipelines">How to add new ArchiveBot pipelines</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/admin.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#all-about-tmux">All about tmux</a></li> <li class="toctree-l2"><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/admin.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#re-sync-the-irc-status-command-to-actual-redis-data">Re-sync the IRC !status command to actual Redis data</a></li> </ul></li> </ul> </div> </div> <div class="section" id="indices-and-tables"> <h1>Indices and tables<a class="headerlink" href="https://archivebot-readthedocs-io.translate.goog/en/latest/?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB#indices-and-tables" title="Permalink to this headline">¶</a></h1> <ul class="simple"> <li><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/genindex.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB"><span class="std std-ref">Index</span></a></li> <li><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/py-modindex.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB"><span class="std std-ref">Module Index</span></a></li> <li><a class="reference internal" href="https://archivebot-readthedocs-io.translate.goog/en/latest/search.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB"><span class="std std-ref">Search Page</span></a></li> </ul> </div> </div> </div> <footer> <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"><a href="https://archivebot-readthedocs-io.translate.goog/en/latest/commands.html?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-GB" class="btn btn-neutral float-right" title="Commands" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a> </div> <hr> <div role="contentinfo"> <p>© Copyright 2014, ArchiveTeam <span class="commit"> Revision <code>b22627e4</code>. </span></p> </div> Built with <a href="https://translate.google.com/website?sl=auto&tl=en&hl=en-GB&u=http://sphinx-doc.org/">Sphinx</a> using a <a href="https://translate.google.com/website?sl=auto&tl=en&hl=en-GB&u=https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://translate.google.com/website?sl=auto&tl=en&hl=en-GB&u=https://readthedocs.org">Read the Docs</a>. </footer> </div> </div> </section> </div> <script type="text/javascript"> jQuery(function () { SphinxRtdTheme.Navigation.enable(true); }); </script> <script>function gtElInit() {var lib = new google.translate.TranslateService();lib.translatePage('en', 'en', function () {});}</script> <script src="https://translate.google.com/translate_a/element.js?cb=gtElInit&hl=en-GB&client=wt" type="text/javascript"></script> </body> </html>