Removed the Requirement to Install Python and NodeJS (Now Bundled with Borealis)

This commit is contained in:
2025-04-24 00:42:19 -06:00
parent 785265d3e7
commit 9c68cdea84
7786 changed files with 2386458 additions and 217 deletions

View File

@ -0,0 +1,423 @@
<!DOCTYPE html>
<html lang="en" data-content_root="../">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<meta property="og:title" content="urllib.robotparser — Parser for robots.txt" />
<meta property="og:type" content="website" />
<meta property="og:url" content="https://docs.python.org/3/library/urllib.robotparser.html" />
<meta property="og:site_name" content="Python documentation" />
<meta property="og:description" content="Source code: Lib/urllib/robotparser.py This module provides a single class, RobotFileParser, which answers questions about whether or not a particular user agent can fetch a URL on the web site tha..." />
<meta property="og:image" content="https://docs.python.org/3/_static/og-image.png" />
<meta property="og:image:alt" content="Python documentation" />
<meta name="description" content="Source code: Lib/urllib/robotparser.py This module provides a single class, RobotFileParser, which answers questions about whether or not a particular user agent can fetch a URL on the web site tha..." />
<meta property="og:image:width" content="200">
<meta property="og:image:height" content="200">
<meta name="theme-color" content="#3776ab">
<title>urllib.robotparser — Parser for robots.txt &#8212; Python 3.13.3 documentation</title><meta name="viewport" content="width=device-width, initial-scale=1.0">
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=b86133f3" />
<link rel="stylesheet" type="text/css" href="../_static/pydoctheme.css?v=23252803" />
<link id="pygments_dark_css" media="(prefers-color-scheme: dark)" rel="stylesheet" type="text/css" href="../_static/pygments_dark.css?v=5349f25f" />
<script src="../_static/documentation_options.js?v=5d57ca2d"></script>
<script src="../_static/doctools.js?v=9bcbadda"></script>
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../_static/sidebar.js"></script>
<link rel="search" type="application/opensearchdescription+xml"
title="Search within Python 3.13.3 documentation"
href="../_static/opensearch.xml"/>
<link rel="author" title="About these documents" href="../about.html" />
<link rel="index" title="Index" href="../genindex.html" />
<link rel="search" title="Search" href="../search.html" />
<link rel="copyright" title="Copyright" href="../copyright.html" />
<link rel="next" title="http — HTTP modules" href="http.html" />
<link rel="prev" title="urllib.error — Exception classes raised by urllib.request" href="urllib.error.html" />
<link rel="canonical" href="https://docs.python.org/3/library/urllib.robotparser.html">
<style>
@media only screen {
table.full-width-table {
width: 100%;
}
}
</style>
<link rel="stylesheet" href="../_static/pydoctheme_dark.css" media="(prefers-color-scheme: dark)" id="pydoctheme_dark_css">
<link rel="shortcut icon" type="image/png" href="../_static/py.svg" />
<script type="text/javascript" src="../_static/copybutton.js"></script>
<script type="text/javascript" src="../_static/menu.js"></script>
<script type="text/javascript" src="../_static/search-focus.js"></script>
<script type="text/javascript" src="../_static/themetoggle.js"></script>
<script type="text/javascript" src="../_static/rtd_switcher.js"></script>
<meta name="readthedocs-addons-api-version" content="1">
</head>
<body>
<div class="mobile-nav">
<input type="checkbox" id="menuToggler" class="toggler__input" aria-controls="navigation"
aria-pressed="false" aria-expanded="false" role="button" aria-label="Menu" />
<nav class="nav-content" role="navigation">
<label for="menuToggler" class="toggler__label">
<span></span>
</label>
<span class="nav-items-wrapper">
<a href="https://www.python.org/" class="nav-logo">
<img src="../_static/py.svg" alt="Python logo"/>
</a>
<span class="version_switcher_placeholder"></span>
<form role="search" class="search" action="../search.html" method="get">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" class="search-icon">
<path fill-rule="nonzero" fill="currentColor" d="M15.5 14h-.79l-.28-.27a6.5 6.5 0 001.48-5.34c-.47-2.78-2.79-5-5.59-5.34a6.505 6.505 0 00-7.27 7.27c.34 2.8 2.56 5.12 5.34 5.59a6.5 6.5 0 005.34-1.48l.27.28v.79l4.25 4.25c.41.41 1.08.41 1.49 0 .41-.41.41-1.08 0-1.49L15.5 14zm-6 0C7.01 14 5 11.99 5 9.5S7.01 5 9.5 5 14 7.01 14 9.5 11.99 14 9.5 14z"></path>
</svg>
<input placeholder="Quick search" aria-label="Quick search" type="search" name="q" />
<input type="submit" value="Go"/>
</form>
</span>
</nav>
<div class="menu-wrapper">
<nav class="menu" role="navigation" aria-label="main navigation">
<div class="language_switcher_placeholder"></div>
<label class="theme-selector-label">
Theme
<select class="theme-selector" oninput="activateTheme(this.value)">
<option value="auto" selected>Auto</option>
<option value="light">Light</option>
<option value="dark">Dark</option>
</select>
</label>
<div>
<h4>Previous topic</h4>
<p class="topless"><a href="urllib.error.html"
title="previous chapter"><code class="xref py py-mod docutils literal notranslate"><span class="pre">urllib.error</span></code> — Exception classes raised by urllib.request</a></p>
</div>
<div>
<h4>Next topic</h4>
<p class="topless"><a href="http.html"
title="next chapter"><code class="xref py py-mod docutils literal notranslate"><span class="pre">http</span></code> — HTTP modules</a></p>
</div>
<div role="note" aria-label="source link">
<h3>This Page</h3>
<ul class="this-page-menu">
<li><a href="../bugs.html">Report a Bug</a></li>
<li>
<a href="https://github.com/python/cpython/blob/main/Doc/library/urllib.robotparser.rst"
rel="nofollow">Show Source
</a>
</li>
</ul>
</div>
</nav>
</div>
</div>
<div class="related" role="navigation" aria-label="Related">
<h3>Navigation</h3>
<ul>
<li class="right" style="margin-right: 10px">
<a href="../genindex.html" title="General Index"
accesskey="I">index</a></li>
<li class="right" >
<a href="../py-modindex.html" title="Python Module Index"
>modules</a> |</li>
<li class="right" >
<a href="http.html" title="http — HTTP modules"
accesskey="N">next</a> |</li>
<li class="right" >
<a href="urllib.error.html" title="urllib.error — Exception classes raised by urllib.request"
accesskey="P">previous</a> |</li>
<li><img src="../_static/py.svg" alt="Python logo" style="vertical-align: middle; margin-top: -1px"/></li>
<li><a href="https://www.python.org/">Python</a> &#187;</li>
<li class="switchers">
<div class="language_switcher_placeholder"></div>
<div class="version_switcher_placeholder"></div>
</li>
<li>
</li>
<li id="cpython-language-and-version">
<a href="../index.html">3.13.3 Documentation</a> &#187;
</li>
<li class="nav-item nav-item-1"><a href="index.html" >The Python Standard Library</a> &#187;</li>
<li class="nav-item nav-item-2"><a href="internet.html" accesskey="U">Internet Protocols and Support</a> &#187;</li>
<li class="nav-item nav-item-this"><a href=""><code class="xref py py-mod docutils literal notranslate"><span class="pre">urllib.robotparser</span></code> — Parser for robots.txt</a></li>
<li class="right">
<div class="inline-search" role="search">
<form class="inline-search" action="../search.html" method="get">
<input placeholder="Quick search" aria-label="Quick search" type="search" name="q" id="search-box" />
<input type="submit" value="Go" />
</form>
</div>
|
</li>
<li class="right">
<label class="theme-selector-label">
Theme
<select class="theme-selector" oninput="activateTheme(this.value)">
<option value="auto" selected>Auto</option>
<option value="light">Light</option>
<option value="dark">Dark</option>
</select>
</label> |</li>
</ul>
</div>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<section id="module-urllib.robotparser">
<span id="urllib-robotparser-parser-for-robots-txt"></span><h1><code class="xref py py-mod docutils literal notranslate"><span class="pre">urllib.robotparser</span></code> — Parser for robots.txt<a class="headerlink" href="#module-urllib.robotparser" title="Link to this heading"></a></h1>
<p><strong>Source code:</strong> <a class="extlink-source reference external" href="https://github.com/python/cpython/tree/3.13/Lib/urllib/robotparser.py">Lib/urllib/robotparser.py</a></p>
<hr class="docutils" id="index-0" />
<p>This module provides a single class, <a class="reference internal" href="#urllib.robotparser.RobotFileParser" title="urllib.robotparser.RobotFileParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">RobotFileParser</span></code></a>, which answers
questions about whether or not a particular user agent can fetch a URL on the
web site that published the <code class="file docutils literal notranslate"><span class="pre">robots.txt</span></code> file. For more details on the
structure of <code class="file docutils literal notranslate"><span class="pre">robots.txt</span></code> files, see <a class="reference external" href="http://www.robotstxt.org/orig.html">http://www.robotstxt.org/orig.html</a>.</p>
<dl class="py class">
<dt class="sig sig-object py" id="urllib.robotparser.RobotFileParser">
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">urllib.robotparser.</span></span><span class="sig-name descname"><span class="pre">RobotFileParser</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">url</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#urllib.robotparser.RobotFileParser" title="Link to this definition"></a></dt>
<dd><p>This class provides methods to read, parse and answer questions about the
<code class="file docutils literal notranslate"><span class="pre">robots.txt</span></code> file at <em>url</em>.</p>
<dl class="py method">
<dt class="sig sig-object py" id="urllib.robotparser.RobotFileParser.set_url">
<span class="sig-name descname"><span class="pre">set_url</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">url</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#urllib.robotparser.RobotFileParser.set_url" title="Link to this definition"></a></dt>
<dd><p>Sets the URL referring to a <code class="file docutils literal notranslate"><span class="pre">robots.txt</span></code> file.</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="urllib.robotparser.RobotFileParser.read">
<span class="sig-name descname"><span class="pre">read</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#urllib.robotparser.RobotFileParser.read" title="Link to this definition"></a></dt>
<dd><p>Reads the <code class="file docutils literal notranslate"><span class="pre">robots.txt</span></code> URL and feeds it to the parser.</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="urllib.robotparser.RobotFileParser.parse">
<span class="sig-name descname"><span class="pre">parse</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lines</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#urllib.robotparser.RobotFileParser.parse" title="Link to this definition"></a></dt>
<dd><p>Parses the lines argument.</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="urllib.robotparser.RobotFileParser.can_fetch">
<span class="sig-name descname"><span class="pre">can_fetch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">useragent</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">url</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#urllib.robotparser.RobotFileParser.can_fetch" title="Link to this definition"></a></dt>
<dd><p>Returns <code class="docutils literal notranslate"><span class="pre">True</span></code> if the <em>useragent</em> is allowed to fetch the <em>url</em>
according to the rules contained in the parsed <code class="file docutils literal notranslate"><span class="pre">robots.txt</span></code>
file.</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="urllib.robotparser.RobotFileParser.mtime">
<span class="sig-name descname"><span class="pre">mtime</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#urllib.robotparser.RobotFileParser.mtime" title="Link to this definition"></a></dt>
<dd><p>Returns the time the <code class="docutils literal notranslate"><span class="pre">robots.txt</span></code> file was last fetched. This is
useful for long-running web spiders that need to check for new
<code class="docutils literal notranslate"><span class="pre">robots.txt</span></code> files periodically.</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="urllib.robotparser.RobotFileParser.modified">
<span class="sig-name descname"><span class="pre">modified</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#urllib.robotparser.RobotFileParser.modified" title="Link to this definition"></a></dt>
<dd><p>Sets the time the <code class="docutils literal notranslate"><span class="pre">robots.txt</span></code> file was last fetched to the current
time.</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="urllib.robotparser.RobotFileParser.crawl_delay">
<span class="sig-name descname"><span class="pre">crawl_delay</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">useragent</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#urllib.robotparser.RobotFileParser.crawl_delay" title="Link to this definition"></a></dt>
<dd><p>Returns the value of the <code class="docutils literal notranslate"><span class="pre">Crawl-delay</span></code> parameter from <code class="docutils literal notranslate"><span class="pre">robots.txt</span></code>
for the <em>useragent</em> in question. If there is no such parameter or it
doesnt apply to the <em>useragent</em> specified or the <code class="docutils literal notranslate"><span class="pre">robots.txt</span></code> entry
for this parameter has invalid syntax, return <code class="docutils literal notranslate"><span class="pre">None</span></code>.</p>
<div class="versionadded">
<p><span class="versionmodified added">Added in version 3.6.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="urllib.robotparser.RobotFileParser.request_rate">
<span class="sig-name descname"><span class="pre">request_rate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">useragent</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#urllib.robotparser.RobotFileParser.request_rate" title="Link to this definition"></a></dt>
<dd><p>Returns the contents of the <code class="docutils literal notranslate"><span class="pre">Request-rate</span></code> parameter from
<code class="docutils literal notranslate"><span class="pre">robots.txt</span></code> as a <a class="reference internal" href="../glossary.html#term-named-tuple"><span class="xref std std-term">named tuple</span></a> <code class="docutils literal notranslate"><span class="pre">RequestRate(requests,</span> <span class="pre">seconds)</span></code>.
If there is no such parameter or it doesnt apply to the <em>useragent</em>
specified or the <code class="docutils literal notranslate"><span class="pre">robots.txt</span></code> entry for this parameter has invalid
syntax, return <code class="docutils literal notranslate"><span class="pre">None</span></code>.</p>
<div class="versionadded">
<p><span class="versionmodified added">Added in version 3.6.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="urllib.robotparser.RobotFileParser.site_maps">
<span class="sig-name descname"><span class="pre">site_maps</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#urllib.robotparser.RobotFileParser.site_maps" title="Link to this definition"></a></dt>
<dd><p>Returns the contents of the <code class="docutils literal notranslate"><span class="pre">Sitemap</span></code> parameter from
<code class="docutils literal notranslate"><span class="pre">robots.txt</span></code> in the form of a <a class="reference internal" href="stdtypes.html#list" title="list"><code class="xref py py-func docutils literal notranslate"><span class="pre">list()</span></code></a>. If there is no such
parameter or the <code class="docutils literal notranslate"><span class="pre">robots.txt</span></code> entry for this parameter has
invalid syntax, return <code class="docutils literal notranslate"><span class="pre">None</span></code>.</p>
<div class="versionadded">
<p><span class="versionmodified added">Added in version 3.8.</span></p>
</div>
</dd></dl>
</dd></dl>
<p>The following example demonstrates basic use of the <a class="reference internal" href="#urllib.robotparser.RobotFileParser" title="urllib.robotparser.RobotFileParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">RobotFileParser</span></code></a>
class:</p>
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">import</span><span class="w"> </span><span class="nn">urllib.robotparser</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">rp</span> <span class="o">=</span> <span class="n">urllib</span><span class="o">.</span><span class="n">robotparser</span><span class="o">.</span><span class="n">RobotFileParser</span><span class="p">()</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">rp</span><span class="o">.</span><span class="n">set_url</span><span class="p">(</span><span class="s2">&quot;http://www.musi-cal.com/robots.txt&quot;</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">rp</span><span class="o">.</span><span class="n">read</span><span class="p">()</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">rrate</span> <span class="o">=</span> <span class="n">rp</span><span class="o">.</span><span class="n">request_rate</span><span class="p">(</span><span class="s2">&quot;*&quot;</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">rrate</span><span class="o">.</span><span class="n">requests</span>
<span class="go">3</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">rrate</span><span class="o">.</span><span class="n">seconds</span>
<span class="go">20</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">rp</span><span class="o">.</span><span class="n">crawl_delay</span><span class="p">(</span><span class="s2">&quot;*&quot;</span><span class="p">)</span>
<span class="go">6</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">rp</span><span class="o">.</span><span class="n">can_fetch</span><span class="p">(</span><span class="s2">&quot;*&quot;</span><span class="p">,</span> <span class="s2">&quot;http://www.musi-cal.com/cgi-bin/search?city=San+Francisco&quot;</span><span class="p">)</span>
<span class="go">False</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">rp</span><span class="o">.</span><span class="n">can_fetch</span><span class="p">(</span><span class="s2">&quot;*&quot;</span><span class="p">,</span> <span class="s2">&quot;http://www.musi-cal.com/&quot;</span><span class="p">)</span>
<span class="go">True</span>
</pre></div>
</div>
</section>
<div class="clearer"></div>
</div>
</div>
</div>
<div class="sphinxsidebar" role="navigation" aria-label="Main">
<div class="sphinxsidebarwrapper">
<div>
<h4>Previous topic</h4>
<p class="topless"><a href="urllib.error.html"
title="previous chapter"><code class="xref py py-mod docutils literal notranslate"><span class="pre">urllib.error</span></code> — Exception classes raised by urllib.request</a></p>
</div>
<div>
<h4>Next topic</h4>
<p class="topless"><a href="http.html"
title="next chapter"><code class="xref py py-mod docutils literal notranslate"><span class="pre">http</span></code> — HTTP modules</a></p>
</div>
<div role="note" aria-label="source link">
<h3>This Page</h3>
<ul class="this-page-menu">
<li><a href="../bugs.html">Report a Bug</a></li>
<li>
<a href="https://github.com/python/cpython/blob/main/Doc/library/urllib.robotparser.rst"
rel="nofollow">Show Source
</a>
</li>
</ul>
</div>
</div>
<div id="sidebarbutton" title="Collapse sidebar">
<span>«</span>
</div>
</div>
<div class="clearer"></div>
</div>
<div class="related" role="navigation" aria-label="Related">
<h3>Navigation</h3>
<ul>
<li class="right" style="margin-right: 10px">
<a href="../genindex.html" title="General Index"
>index</a></li>
<li class="right" >
<a href="../py-modindex.html" title="Python Module Index"
>modules</a> |</li>
<li class="right" >
<a href="http.html" title="http — HTTP modules"
>next</a> |</li>
<li class="right" >
<a href="urllib.error.html" title="urllib.error — Exception classes raised by urllib.request"
>previous</a> |</li>
<li><img src="../_static/py.svg" alt="Python logo" style="vertical-align: middle; margin-top: -1px"/></li>
<li><a href="https://www.python.org/">Python</a> &#187;</li>
<li class="switchers">
<div class="language_switcher_placeholder"></div>
<div class="version_switcher_placeholder"></div>
</li>
<li>
</li>
<li id="cpython-language-and-version">
<a href="../index.html">3.13.3 Documentation</a> &#187;
</li>
<li class="nav-item nav-item-1"><a href="index.html" >The Python Standard Library</a> &#187;</li>
<li class="nav-item nav-item-2"><a href="internet.html" >Internet Protocols and Support</a> &#187;</li>
<li class="nav-item nav-item-this"><a href=""><code class="xref py py-mod docutils literal notranslate"><span class="pre">urllib.robotparser</span></code> — Parser for robots.txt</a></li>
<li class="right">
<div class="inline-search" role="search">
<form class="inline-search" action="../search.html" method="get">
<input placeholder="Quick search" aria-label="Quick search" type="search" name="q" id="search-box" />
<input type="submit" value="Go" />
</form>
</div>
|
</li>
<li class="right">
<label class="theme-selector-label">
Theme
<select class="theme-selector" oninput="activateTheme(this.value)">
<option value="auto" selected>Auto</option>
<option value="light">Light</option>
<option value="dark">Dark</option>
</select>
</label> |</li>
</ul>
</div>
<div class="footer">
&copy;
<a href="../copyright.html">
Copyright
</a>
2001-2025, Python Software Foundation.
<br />
This page is licensed under the Python Software Foundation License Version 2.
<br />
Examples, recipes, and other code in the documentation are additionally licensed under the Zero Clause BSD License.
<br />
See <a href="/license.html">History and License</a> for more information.<br />
<br />
The Python Software Foundation is a non-profit corporation.
<a href="https://www.python.org/psf/donations/">Please donate.</a>
<br />
<br />
Last updated on Apr 08, 2025 (14:33 UTC).
<a href="/bugs.html">Found a bug</a>?
<br />
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 8.2.3.
</div>
</body>
</html>