zhouzhongping/wiki
1
0
Fork 0
Code
c90bc4f521
wiki/Tech/programming-language/Python/模块/网络处理/urllib-URL-处理模块.html

475 lines
458 KiB
HTML
Raw Normal View History

Deploy HTML files - 2024-07-18
2024-07-18 17:29:40 +08:00
<!DOCTYPE html>
<html><head><title>urllib URL 处理模块</title><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1.0"/><meta property="og:title" content="urllib URL 处理模块"/><meta property="og:description" content="urllib URL 处理模块."/><meta property="og:image" content="https://wiki.7wate.com/static/og-image.png"/><meta property="og:width" content="1200"/><meta property="og:height" content="675"/><link rel="icon" href="../../../../../static/icon.png"/><meta name="description" content="urllib URL 处理模块."/><meta name="generator" content="Quartz"/><link rel="preconnect" href="https://fonts.googleapis.com"/><link rel="preconnect" href="https://fonts.gstatic.com"/><script async src="https://umami.7wate.com/script.js" data-website-id="c061efdc-95dd-4d21-9d04-a1ffda0a85b9"></script><script>
var _hmt = _hmt || [];
(function() {
var hm = document.createElement("script");
hm.src = "https://hm.baidu.com/hm.js?94d8ccb156eb7c65abf317e6e01cdba9";
var s = document.getElementsByTagName("script")[0];
s.parentNode.insertBefore(hm, s);
})();
</script><script async src="https://www.googletagmanager.com/gtag/js?id=G-MHMEL0F832"></script><script>
(function() {
window.dataLayer = window.dataLayer || [];
function gtag() {
window.dataLayer.push(arguments);
}
gtag('js', new Date());
gtag('config', 'G-MHMEL0F832');
})();
</script><link href="../../../../../index.css" rel="stylesheet" type="text/css" spa-preserve/><link href="https://cdn.jsdelivr.net/npm/katex@0.16.0/dist/katex.min.css" rel="stylesheet" type="text/css" spa-preserve/><link href="https://fonts.googleapis.com/css2?family=IBM Plex Mono&amp;family=Schibsted Grotesk:wght@400;700&amp;family=Source Sans Pro:ital,wght@0,400;0,600;1,400;1,600&amp;display=swap" rel="stylesheet" type="text/css" spa-preserve/><script src="../../../../../prescript.js" type="application/javascript" spa-preserve></script><script type="application/javascript" spa-preserve>const fetchData = fetch(`../../../../../static/contentIndex.json`).then(data => data.json())</script></head><body data-slug="Tech/programming-language/Python/模块/网络处理/urllib-URL-处理模块"><div id="quartz-root" class="page"><div id="quartz-body"><div class="left sidebar"><h1 class="page-title "><a href="../../../../..">📚 X·Eden</a></h1><div class="spacer mobile-only"></div><div class="search "><div id="search-icon"><p>Search</p><div></div><svg tabIndex="0" aria-labelledby="title desc" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 19.9 19.7"><title id="title">Search</title><desc id="desc">Search</desc><g class="search-path" fill="none"><path stroke-linecap="square" d="M18.5 18.3l-5.4-5.4"></path><circle cx="8" cy="8" r="7"></circle></g></svg></div><div id="search-container"><div id="search-space"><input autocomplete="off" id="search-bar" name="search" type="text" aria-label="Search for something" placeholder="Search for something"/><div id="results-container"></div></div></div></div><div class="darkmode "><input class="toggle" id="darkmode-toggle" type="checkbox" tabIndex="-1"/><label id="toggle-label-light" for="darkmode-toggle" tabIndex="-1"><svg xmlns="http://www.w3.org/2000/svg" xmlnsXlink="http://www.w3.org/1999/xlink" version="1.1" id="dayIcon" x="0px" y="0px" viewBox="0 0 35 35" style="enable-background:new 0 0 35 35;" xmlSpace="preserve"><title>Light mode</title><path d="M6,17.5C6,16.672,5.328,16,4.5,16h-3C0.672,16,0,16.672,0,17.5 S0.672,19,1.5,19h3C5.328,19,6,18.328,6,17.5z M7.5,26c-0.414,0-0.789,0.168-1.061,0.439l-2,2C4.168,28.711,4,29.086,4,29.5 C4,30.328,4.671,31,5.5,31c0.414,0,0.789-0.168,1.06-0.44l2-2C8.832,28.289,9,27.914,9,27.5C9,26.672,8.329,26,7.5,26z M17.5,6 C18.329,6,19,5.328,19,4.5v-3C19,0.672,18.329,0,17.5,0S16,0.672,16,1.5v3C16,5.328,16.671,6,17.5,6z M27.5,9 c0.414,0,0.789-0.168,1.06-0.439l2-2C30.832,6.289,31,5.914,31,5.5C31,4.672,30.329,4,29.5,4c-0.414,0-0.789,0.168-1.061,0.44 l-2,2C26.168,6.711,26,7.086,26,7.5C26,8.328,26.671,9,27.5,9z M6.439,8.561C6.711,8.832,7.086,9,7.5,9C8.328,9,9,8.328,9,7.5 c0-0.414-0.168-0.789-0.439-1.061l-2-2C6.289,4.168,5.914,4,5.5,4C4.672,4,4,4.672,4,5.5c0,0.414,0.168,0.789,0.439,1.06 L6.439,8.561z M33.5,16h-3c-0.828,0-1.5,0.672-1.5,1.5s0.672,1.5,1.5,1.5h3c0.828,0,1.5-0.672,1.5-1.5S34.328,16,33.5,16z M28.561,26.439C28.289,26.168,27.914,26,27.5,26c-0.828,0-1.5,0.672-1.5,1.5c0,0.414,0.168,0.789,0.439,1.06l2,2 C28.711,30.832,29.086,31,29.5,31c0.828,0,1.5-0.672,1.5-1.5c0-0.414-0.168-0.789-0.439-1.061L28.561,26.439z M17.5,29 c-0.829,0-1.5,0.672-1.5,1.5v3c0,0.828,0.671,1.5,1.5,1.5s1.5-0.672,1.5-1.5v-3C19,29.672,18.329,29,17.5,29z M17.5,7 C11.71,7,7,11.71,7,17.5S11.71,28,17.5,28S28,23.29,28,17.5S23.29,7,17.5,7z M17.5,25c-4.136,0-7.5-3.364-7.5-7.5 c0-4.136,3.364-7.5,7.5-7.5c4.136,0,7.5,3.364,7.5,7.5C25,21.636,21.636,25,17.5,25z"></path></svg></label><label id="toggle-label-dark" for="darkmode-toggle" tabIndex="-1"><svg xmlns="http://www.w3.org/2000/svg" xmlnsXlink="http://www.w3.org/1999/xlink" version="1.1" id="nightIcon" x="0px" y="0px" viewBox="0 0 100 100" style="enable-background='new 0 0 100 100'" xmlSpace="preserve"><title>Dark mode</title><path d="M96.76,66.458c-0.853-0.852-2.15-1.064-3.23-0.534c-6.063,2.991-12.858,4.571-19.655,4.571 C62.022,70.495,50.88,65.88,42.5,57.5C29.043,44.043,25.658,23.536,34.076,6.47c0.532-1.08,0.318-2.379-0.534-3.23 c-0.851-0.852-2.15-1.064-3.23-0.534c-4.918,2.427-9.375,5.619-13.246,9
<p><code>urllib</code> 是 Python 标准库中用于处理 URL（统一资源定位符）相关操作的模块，它提供了多个子模块，用于执行网络请求、解析 URL、处理错误以及解析 robots.txt 文件等。以下是 <code>urllib</code> 的子模块：</p>
<h3 id="子模块">子模块<a aria-hidden="true" tabindex="-1" href="#子模块" class="internal"> §</a></h3>
<ul>
<li><strong><code>urllib.request</code></strong>：提供打开和读取 URL 的功能。支持多种网络协议，如 HTTP、FTP 等。</li>
<li><strong><code>urllib.error</code></strong>：包含与网络请求相关的异常类，用于处理错误和异常情况。</li>
<li><strong><code>urllib.parse</code></strong>：用于解析和构建 URL，提供各种操作，如分割、组合、编码和解码。</li>
<li><strong><code>urllib.robotparser</code></strong>：用于解析网站的 <code>robots.txt</code> 文件，确定哪些页面可以被爬取。</li>
</ul>
<h3 id="优点">优点<a aria-hidden="true" tabindex="-1" href="#优点" class="internal"> §</a></h3>
<ul>
<li><strong>内置模块</strong>：作为 Python 标准库的一部分，无需单独安装。</li>
<li><strong>全面功能</strong>：支持多种网络协议和操作，适用于多种网络操作需求。</li>
<li><strong>高度可定制</strong>：用于处理 URL 的多个方面，如打开、读取、解析等。</li>
</ul>
<h3 id="缺点">缺点<a aria-hidden="true" tabindex="-1" href="#缺点" class="internal"> §</a></h3>
<ul>
<li><strong>较低层次的 API</strong>：与一些第三方库相比（如 <code>requests</code>），<code>urllib</code> 的 API 较为底层，可能需要编写更多的代码。</li>
<li><strong>繁琐的错误处理</strong>：错误处理需要额外的代码，相比使用像 <code>requests</code> 这样的库可能更复杂。</li>
</ul>
<h3 id="同类产品对比">同类产品对比<a aria-hidden="true" tabindex="-1" href="#同类产品对比" class="internal"> §</a></h3>
<table><thead><tr><th>产品</th><th>优点</th><th>缺点</th><th>适用背景</th><th>社区支持</th></tr></thead><tbody><tr><td>urllib</td><td>标准库，全面</td><td>API 较底层</td><td>网络请求，URL 操作</td><td>Python 社区</td></tr><tr><td>requests</td><td>API 简单</td><td>需要单独安装</td><td>HTTP 请求</td><td>Python 社区</td></tr><tr><td>httplib2</td><td>功能丰富</td><td>使用复杂</td><td>HTTP 请求</td><td>Python 社区</td></tr></tbody></table>
<h2 id="urllibrequest"><code>urllib.request</code><a aria-hidden="true" tabindex="-1" href="#urllibrequest" class="internal"> §</a></h2>
<table><thead><tr><th>方法</th><th>功能描述</th><th>示例</th></tr></thead><tbody><tr><td><code>urlopen()</code></td><td>打开并读取一个 URL 的内容</td><td><code>urllib.request.urlopen(url)</code></td></tr><tr><td><code>urlretrieve()</code></td><td>将 URL 指向的文件下载到本地</td><td><code>urllib.request.urlretrieve(url, filename)</code></td></tr><tr><td><code>build_opener()</code></td><td>构建一个可自定义的 <code>Opener</code> 对象</td><td><code>opener = urllib.request.build_opener()</code></td></tr><tr><td><code>install_opener()</code></td><td>安装全局的 <code>Opener</code></td><td><code>urllib.request.install_opener(opener)</code></td></tr><tr><td><code>HTTPBasicAuthHandler()</code></td><td>HTTP 基础认证处理程序</td><td><code>handler = urllib.request.HTTPBasicAuthHandler()</code></td></tr><tr><td><code>HTTPCookieProcessor()</code></td><td>用于处理 HTTP cookies</td><td><code>handler = urllib.request.HTTPCookieProcessor()</code></td></tr><tr><td><code>ProxyHandler()</code></td><td>设置代理</td><td><code>proxy = urllib.request.ProxyHandler({'http': 'http://www.example.com:8080'})</code></td></tr><tr><td><code>Request()</code></td><td>创建一个请求对象，用于定制 HTTP 头等</td><td><code>req = urllib.request.Request(url, headers={...})</code></td></tr></tbody></table>
<h3 id="urlopen-打开-url"><code>urlopen()</code> 打开 URL<a aria-hidden="true" tabindex="-1" href="#urlopen-打开-url" class="internal"> §</a></h3>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 打开一个网页</span></span>
<span data-line><span style="color:var(--shiki-color-text);">response </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">urlopen</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'http://www.example.com'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 读取网页内容</span></span>
<span data-line><span style="color:var(--shiki-color-text);">data </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> response</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">read</span><span style="color:var(--shiki-token-punctuation);">()</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 输出网页内容</span></span>
<span data-line><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(data)</span></span></code></pre></div>
<h3 id="urlretrieve-下载文件"><code>urlretrieve()</code> 下载文件<a aria-hidden="true" tabindex="-1" href="#urlretrieve-下载文件" class="internal"> §</a></h3>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 从指定 URL 下载文件，并保存到本地</span></span>
<span data-line><span style="color:var(--shiki-color-text);">urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">urlretrieve</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'http://www.example.com/file.txt'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'local_file.txt'</span><span style="color:var(--shiki-token-punctuation);">)</span></span></code></pre></div>
<h3 id="build_opener-和-install_opener"><code>build_opener()</code> 和 <code>install_opener()</code><a aria-hidden="true" tabindex="-1" href="#build_opener-和-install_opener" class="internal"> §</a></h3>
<p><code>build_opener()</code> 传递一系列处理程序（handlers），这些处理程序用于定义如何处理各种 HTTP 功能，比如重定向、基础认证、cookies 等。一旦你使用 <code>build_opener()</code> 创建了一个 <code>Opener</code> 对象，你可以使用 <code>install_opener()</code> 来设置它作为默认的 <code>Opener</code>。</p>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 创建基础认证处理程序</span></span>
<span data-line><span style="color:var(--shiki-color-text);">auth_handler </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">HTTPBasicAuthHandler</span><span style="color:var(--shiki-token-punctuation);">()</span></span>
<span data-line><span style="color:var(--shiki-color-text);">auth_handler</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">add_password</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'realm'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'host'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'username'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'password'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 创建代理处理程序</span></span>
<span data-line><span style="color:var(--shiki-color-text);">proxy_handler </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">ProxyHandler</span><span style="color:var(--shiki-token-punctuation);">({</span><span style="color:var(--shiki-token-string-expression);">'http'</span><span style="color:var(--shiki-token-punctuation);">: </span><span style="color:var(--shiki-token-string-expression);">'http://www.proxy.com:8080'</span><span style="color:var(--shiki-token-punctuation);">})</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 创建 Opener</span></span>
<span data-line><span style="color:var(--shiki-color-text);">opener </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">build_opener</span><span style="color:var(--shiki-token-punctuation);">(auth_handler, proxy_handler)</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 安装 Opener</span></span>
<span data-line><span style="color:var(--shiki-color-text);">urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">install_opener</span><span style="color:var(--shiki-token-punctuation);">(opener)</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 使用 urlopen() 方法，这样会应用我们之前设置的所有处理程序</span></span>
<span data-line><span style="color:var(--shiki-color-text);">response </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">urlopen</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'http://www.example.com'</span><span style="color:var(--shiki-token-punctuation);">)</span></span></code></pre></div>
<h3 id="http-基础认证-httpbasicauthhandler">HTTP 基础认证 (<code>HTTPBasicAuthHandler</code>)<a aria-hidden="true" tabindex="-1" href="#http-基础认证-httpbasicauthhandler" class="internal"> §</a></h3>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 创建一个 HTTPBasicAuthHandler 对象</span></span>
<span data-line><span style="color:var(--shiki-color-text);">auth_handler </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">HTTPBasicAuthHandler</span><span style="color:var(--shiki-token-punctuation);">()</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 添加认证信息</span></span>
<span data-line><span style="color:var(--shiki-color-text);">auth_handler</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">add_password</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'realm'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'host'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'username'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'password'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 创建并安装 opener</span></span>
<span data-line><span style="color:var(--shiki-color-text);">opener </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">build_opener</span><span style="color:var(--shiki-token-punctuation);">(auth_handler)</span></span>
<span data-line><span style="color:var(--shiki-color-text);">urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">install_opener</span><span style="color:var(--shiki-token-punctuation);">(opener)</span></span></code></pre></div>
<h3 id="httpcookieprocessor-处理-cookies"><code>HTTPCookieProcessor</code> 处理 Cookies<a aria-hidden="true" tabindex="-1" href="#httpcookieprocessor-处理-cookies" class="internal"> §</a></h3>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span></span>
<span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> http</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">cookiejar</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 创建一个 CookieJar 对象</span></span>
<span data-line><span style="color:var(--shiki-color-text);">cookie_jar </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> http</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">cookiejar</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">CookieJar</span><span style="color:var(--shiki-token-punctuation);">()</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 创建一个 HTTPCookieProcessor 对象</span></span>
<span data-line><span style="color:var(--shiki-color-text);">cookie_handler </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">HTTPCookieProcessor</span><span style="color:var(--shiki-token-punctuation);">(cookie_jar)</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 构建和安装 opener</span></span>
<span data-line><span style="color:var(--shiki-color-text);">opener </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">build_opener</span><span style="color:var(--shiki-token-punctuation);">(cookie_handler)</span></span></code></pre></div>
<h3 id="proxyhandler-设置代理"><code>ProxyHandler</code> 设置代理<a aria-hidden="true" tabindex="-1" href="#proxyhandler-设置代理" class="internal"> §</a></h3>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 创建一个 ProxyHandler 对象</span></span>
<span data-line><span style="color:var(--shiki-color-text);">proxy_handler </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">ProxyHandler</span><span style="color:var(--shiki-token-punctuation);">({</span><span style="color:var(--shiki-token-string-expression);">'http'</span><span style="color:var(--shiki-token-punctuation);">: </span><span style="color:var(--shiki-token-string-expression);">'http://www.proxy.com:8080'</span><span style="color:var(--shiki-token-punctuation);">})</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 构建并安装 opener</span></span>
<span data-line><span style="color:var(--shiki-color-text);">opener </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">build_opener</span><span style="color:var(--shiki-token-punctuation);">(proxy_handler)</span></span></code></pre></div>
<h3 id="request-自定义请求"><code>Request()</code> 自定义请求<a aria-hidden="true" tabindex="-1" href="#request-自定义请求" class="internal"> §</a></h3>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 创建一个 Request 对象</span></span>
<span data-line><span style="color:var(--shiki-color-text);">req </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">Request</span><span style="color:var(--shiki-token-punctuation);">(url</span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-token-string-expression);">'http://www.example.com'</span><span style="color:var(--shiki-token-punctuation);">, headers</span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-token-punctuation);">{</span><span style="color:var(--shiki-token-string-expression);">'User-Agent'</span><span style="color:var(--shiki-token-punctuation);">: </span><span style="color:var(--shiki-token-string-expression);">'MyApp/1.0'</span><span style="color:var(--shiki-token-punctuation);">})</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 使用 urlopen 打开自定义的请求</span></span>
<span data-line><span style="color:var(--shiki-color-text);">response </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">urlopen</span><span style="color:var(--shiki-token-punctuation);">(req)</span></span></code></pre></div>
<h2 id="urlliberror"><code>urllib.error</code><a aria-hidden="true" tabindex="-1" href="#urlliberror" class="internal"> §</a></h2>
<table><thead><tr><th>方法</th><th>功能描述</th></tr></thead><tbody><tr><td><code>URLError</code></td><td>所有 <code>urllib</code> 产生的异常的基类</td></tr><tr><td><code>HTTPError</code></td><td>处理 HTTP 错误状态，继承自 <code>URLError</code></td></tr><tr><td><code>ContentTooShortError</code></td><td>在下载过程中，数据不足时抛出的异常</td></tr></tbody></table>
<h3 id="urlerror"><code>URLError</code><a aria-hidden="true" tabindex="-1" href="#urlerror" class="internal"> §</a></h3>
<p>当使用 <code>urllib.request</code> 打开一个 URL 失败时，通常会抛出 <code>URLError</code> 异常。</p>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span></span>
<span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">error</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-keyword);">try</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
<span data-line><span style="color:var(--shiki-color-text);"> response </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">urlopen</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'http://www.nonexistentwebsite.com'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
<span data-line><span style="color:var(--shiki-token-keyword);">except</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">error</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">URLError </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> e</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(e.reason)</span></span></code></pre></div>
<h3 id="httperror"><code>HTTPError</code><a aria-hidden="true" tabindex="-1" href="#httperror" class="internal"> §</a></h3>
<p>当服务器返回 HTTP 错误状态码（如 404、500 等）时，会抛出 <code>HTTPError</code>。</p>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span></span>
<span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">error</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-keyword);">try</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
<span data-line><span style="color:var(--shiki-color-text);"> response </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">urlopen</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'http://www.example.com/404'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
<span data-line><span style="color:var(--shiki-token-keyword);">except</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">error</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">HTTPError </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> e</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-keyword);">f</span><span style="color:var(--shiki-token-string-expression);">'HTTP Error Code: </span><span style="color:var(--shiki-token-constant);">{</span><span style="color:var(--shiki-token-punctuation);">e.code</span><span style="color:var(--shiki-token-constant);">}</span><span style="color:var(--shiki-token-string-expression);">'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-keyword);">f</span><span style="color:var(--shiki-token-string-expression);">'Reason: </span><span style="color:var(--shiki-token-constant);">{</span><span style="color:var(--shiki-token-punctuation);">e.reason</span><span style="color:var(--shiki-token-constant);">}</span><span style="color:var(--shiki-token-string-expression);">'</span><span style="color:var(--shiki-token-punctuation);">)</span></span></code></pre></div>
<h3 id="contenttooshorterror"><code>ContentTooShortError</code><a aria-hidden="true" tabindex="-1" href="#contenttooshorterror" class="internal"> §</a></h3>
<p>如果使用 <code>urlretrieve()</code> 函数，但获取的数据长度与 <code>Content-Length</code> 头中声明的长度不匹配时，会抛出 <code>ContentTooShortError</code>。</p>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span></span>
<span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">error</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-keyword);">try</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
<span data-line><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">request</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">urlretrieve</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'http://www.example.com/file'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'local_file.txt'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
<span data-line><span style="color:var(--shiki-token-keyword);">except</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">error</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">ContentTooShortError </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> e</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'The downloaded data is less than expected.'</span><span style="color:var(--shiki-token-punctuation);">)</span></span></code></pre></div>
<h2 id="urllibparse"><code>urllib.parse</code><a aria-hidden="true" tabindex="-1" href="#urllibparse" class="internal"> §</a></h2>
<table><thead><tr><th>方法</th><th>功能描述</th><th>示例</th></tr></thead><tbody><tr><td><code>urlparse()</code></td><td>解析 URL，返回一个 ParseResult 对象</td><td><code>urllib.parse.urlparse(url)</code></td></tr><tr><td><code>urlunparse()</code></td><td>将 ParseResult 对象转回 URL</td><td><code>urllib.parse.urlunparse(parse_result)</code></td></tr><tr><td><code>urlsplit()</code></td><td>类似于 <code>urlparse()</code>，但不分割 params</td><td><code>urllib.parse.urlsplit(url)</code></td></tr><tr><td><code>urlunsplit()</code></td><td>将由 <code>urlsplit()</code> 返回的对象转回 URL</td><td><code>urllib.parse.urlunsplit(split_result)</code></td></tr><tr><td><code>urljoin()</code></td><td>合并两个 URL</td><td><code>urllib.parse.urljoin(base, url)</code></td></tr><tr><td><code>urlencode()</code></td><td>将字典或序列转换为 URL 查询字符串</td><td><code>urllib.parse.urlencode(query_dict)</code></td></tr><tr><td><code>quote()</code></td><td>将字符串进行 URL 编码</td><td><code>urllib.parse.quote(string)</code></td></tr><tr><td><code>unquote()</code></td><td>对 URL 编码的字符串进行解码</td><td><code>urllib.parse.unquote(encoded_string)</code></td></tr></tbody></table>
<h3 id="解析和构建-url">解析和构建 URL<a aria-hidden="true" tabindex="-1" href="#解析和构建-url" class="internal"> §</a></h3>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">from</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">parse </span><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urlparse</span><span style="color:var(--shiki-token-punctuation);">,</span><span style="color:var(--shiki-color-text);"> urlunparse</span><span style="color:var(--shiki-token-punctuation);">,</span><span style="color:var(--shiki-color-text);"> urlsplit</span><span style="color:var(--shiki-token-punctuation);">,</span><span style="color:var(--shiki-color-text);"> urlunsplit</span><span style="color:var(--shiki-token-punctuation);">,</span><span style="color:var(--shiki-color-text);"> urljoin</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 解析URL并返回ParseResult对象</span></span>
<span data-line><span style="color:var(--shiki-color-text);">parsed_url </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">urlparse</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'http://www.example.com/path?query=arg'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 将ParseResult对象转换回URL</span></span>
<span data-line><span style="color:var(--shiki-color-text);">new_url </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">urlunparse</span><span style="color:var(--shiki-token-punctuation);">(parsed_url)</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 类似于urlparse()，但不分割params</span></span>
<span data-line><span style="color:var(--shiki-color-text);">split_result </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">urlsplit</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'http://www.example.com/path?query=arg'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 将由urlsplit()返回的对象转换回URL</span></span>
<span data-line><span style="color:var(--shiki-color-text);">original_url </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">urlunsplit</span><span style="color:var(--shiki-token-punctuation);">(split_result)</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 合并两个URL</span></span>
<span data-line><span style="color:var(--shiki-color-text);">new_url </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">urljoin</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'http://www.example.com/path/'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'/anotherpath.html'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
<span data-line> </span></code></pre></div>
<h3 id="转换查询字符串">转换查询字符串<a aria-hidden="true" tabindex="-1" href="#转换查询字符串" class="internal"> §</a></h3>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">from</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">parse </span><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urlencode</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 将字典或序列转换为URL查询字符串</span></span>
<span data-line><span style="color:var(--shiki-color-text);">query_dict </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-punctuation);">{</span><span style="color:var(--shiki-token-string-expression);">'key1'</span><span style="color:var(--shiki-token-punctuation);">:</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-string-expression);">'value1'</span><span style="color:var(--shiki-token-punctuation);">,</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-string-expression);">'key2'</span><span style="color:var(--shiki-token-punctuation);">:</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-string-expression);">'value2'</span><span style="color:var(--shiki-token-punctuation);">}</span></span>
<span data-line><span style="color:var(--shiki-color-text);">query_string </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">urlencode</span><span style="color:var(--shiki-token-punctuation);">(query_dict)</span></span>
<span data-line> </span></code></pre></div>
<h3 id="url-编码和解码">URL 编码和解码<a aria-hidden="true" tabindex="-1" href="#url-编码和解码" class="internal"> §</a></h3>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">from</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">parse </span><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> quote</span><span style="color:var(--shiki-token-punctuation);">,</span><span style="color:var(--shiki-color-text);"> unquote</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 将字符串进行URL编码</span></span>
<span data-line><span style="color:var(--shiki-color-text);">encoded </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">quote</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'a string with / and ?'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 对URL编码的字符串进行解码</span></span>
<span data-line><span style="color:var(--shiki-color-text);">decoded </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">unquote</span><span style="color:var(--shiki-token-punctuation);">(encoded)</span></span></code></pre></div>
<h2 id="urllibrobotparser"><code>urllib.robotparser</code><a aria-hidden="true" tabindex="-1" href="#urllibrobotparser" class="internal"> §</a></h2>
<p>通过使用 <code>urllib.robotparser</code>，你可以确保你的网络爬虫<strong>尊重网站的抓取策略，这是一种负责任的爬虫行为。</strong></p>
<table><thead><tr><th>方法</th><th>功能描述</th><th>示例</th></tr></thead><tbody><tr><td><code>RobotFileParser()</code></td><td>创建一个 <code>RobotFileParser</code> 对象</td><td><code>rp = urllib.robotparser.RobotFileParser()</code></td></tr><tr><td><code>set_url()</code></td><td>设置 <code>robots.txt</code> 文件的 URL</td><td><code>rp.set_url('http://www.example.com/robots.txt')</code></td></tr><tr><td><code>read()</code></td><td>从设置的 URL 读取 <code>robots.txt</code> 文件</td><td><code>rp.read()</code></td></tr><tr><td><code>parse()</code></td><td>用于手动解析 <code>robots.txt</code> 文件的行</td><td><code>rp.parse(robots_txt_body.split(&quot;\n&quot;))</code></td></tr><tr><td><code>can_fetch()</code></td><td>检查指定的 User-Agent 是否可以访问某个路径</td><td><code>rp.can_fetch('*', 'http://www.example.com/page')</code></td></tr><tr><td><code>mtime()</code></td><td>获取最后一次获取 <code>robots.txt</code> 文件的时间（Unix 时间戳）</td><td><code>rp.mtime()</code></td></tr><tr><td><code>modified()</code></td><td>设置最后一次获取 <code>robots.txt</code> 文件的时间</td><td><code>rp.modified()</code></td></tr></tbody></table>
<h3 id="创建和设置-robotfileparser">创建和设置 RobotFileParser<a aria-hidden="true" tabindex="-1" href="#创建和设置-robotfileparser" class="internal"> §</a></h3>
<p>首先，你需要创建一个 <code>RobotFileParser</code> 对象，并设置要解析的 <code>robots.txt</code> 文件的 URL。</p>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">robotparser</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 创建 RobotFileParser 对象</span></span>
<span data-line><span style="color:var(--shiki-color-text);">rp </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> urllib</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-color-text);">robotparser</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">RobotFileParser</span><span style="color:var(--shiki-token-punctuation);">()</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 设置 robots.txt 文件的 URL</span></span>
<span data-line><span style="color:var(--shiki-color-text);">rp</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">set_url</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'http://www.example.com/robots.txt'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 从 URL 读取 robots.txt 文件</span></span>
<span data-line><span style="color:var(--shiki-color-text);">rp</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">read</span><span style="color:var(--shiki-token-punctuation);">()</span></span></code></pre></div>
<h3 id="检查爬虫是否可以访问特定页面">检查爬虫是否可以访问特定页面<a aria-hidden="true" tabindex="-1" href="#检查爬虫是否可以访问特定页面" class="internal"> §</a></h3>
<p>使用 <code>can_fetch()</code> 方法，您可以检查指定的 User-Agent 是否被允许抓取特定的网页路径。</p>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-comment);"># 检查 '*'（所有 User-Agents）是否允许访问 '/page'</span></span>
<span data-line><span style="color:var(--shiki-color-text);">allowed </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> rp</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">can_fetch</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'*'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'http://www.example.com/page'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-keyword);">if</span><span style="color:var(--shiki-color-text);"> allowed</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">&quot;I can crawl this page.&quot;</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
<span data-line><span style="color:var(--shiki-token-keyword);">else</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">&quot;I cannot crawl this page.&quot;</span><span style="color:var(--shiki-token-punctuation);">)</span></span></code></pre></div>
<h3 id="手动解析-robotstxt">手动解析 robots.txt<a aria-hidden="true" tabindex="-1" href="#手动解析-robotstxt" class="internal"> §</a></h3>
<p>如果你需要手动解析 <code>robots.txt</code> 文件的内容，可以使用 <code>parse()</code> 方法。</p>
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-comment);"># 假设 robots_txt_body 包含了 robots.txt 的文本内容</span></span>
<span data-line><span style="color:var(--shiki-color-text);">robots_txt_body </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-string-expression);">'''</span></span>
<span data-line><span style="color:var(--shiki-token-string-expression);">User-agent: *</span></span>
<span data-line><span style="color:var(--shiki-token-string-expression);">Disallow: /private/</span></span>
<span data-line><span style="color:var(--shiki-token-string-expression);">'''</span></span>
<span data-line> </span>
<span data-line><span style="color:var(--shiki-token-comment);"># 手动解析这些规则</span></span>
<span data-line><span style="color:var(--shiki-color-text);">rp</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">parse</span><span style="color:var(--shiki-token-punctuation);">(robots_txt_body.</span><span style="color:var(--shiki-token-function);">split</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">&quot;\n&quot;</span><span style="color:var(--shiki-token-punctuation);">))</span></span></code></pre></div></article></div><div class="right sidebar"><div class="graph "><h3>Graph View</h3><div class="graph-outer"><div id="graph-container" data-cfg="{&quot;drag&quot;:true,&quot;zoom&quot;:true,&quot;depth&quot;:1,&quot;scale&quot;:1.1,&quot;repelForce&quot;:0.5,&quot;centerForce&quot;:0.3,&quot;linkDistance&quot;:30,&quot;fontSize&quot;:0.6,&quot;opacityScale&quot;:1,&quot;showTags&quot;:true,&quot;removeTags&quot;:[]}"></div><svg version="1.1" id="global-graph-icon" xmlns="http://www.w3.org/2000/svg" xmlnsXlink="http://www.w3.org/1999/xlink" x="0px" y="0px" viewBox="0 0 55 55" fill="currentColor" xmlSpace="preserve"><path d="M49,0c-3.309,0-6,2.691-6,6c0,1.035,0.263,2.009,0.726,2.86l-9.829,9.829C32.542,17.634,30.846,17,29,17
s-3.542,0.634-4.898,1.688l-7.669-7.669C16.785,10.424,17,9.74,17,9c0-2.206-1.794-4-4-4S9,6.794,9,9s1.794,4,4,4
c0.74,0,1.424-0.215,2.019-0.567l7.669,7.669C21.634,21.458,21,23.154,21,25s0.634,3.542,1.688,4.897L10.024,42.562
C8.958,41.595,7.549,41,6,41c-3.309,0-6,2.691-6,6s2.691,6,6,6s6-2.691,6-6c0-1.035-0.263-2.009-0.726-2.86l12.829-12.829
c1.106,0.86,2.44,1.436,3.898,1.619v10.16c-2.833,0.478-5,2.942-5,5.91c0,3.309,2.691,6,6,6s6-2.691,6-6c0-2.967-2.167-5.431-5-5.91
v-10.16c1.458-0.183,2.792-0.759,3.898-1.619l7.669,7.669C41.215,39.576,41,40.26,41,41c0,2.206,1.794,4,4,4s4-1.794,4-4
s-1.794-4-4-4c-0.74,0-1.424,0.215-2.019,0.567l-7.669-7.669C36.366,28.542,37,26.846,37,25s-0.634-3.542-1.688-4.897l9.665-9.665
C46.042,11.405,47.451,12,49,12c3.309,0,6-2.691,6-6S52.309,0,49,0z M11,9c0-1.103,0.897-2,2-2s2,0.897,2,2s-0.897,2-2,2
S11,10.103,11,9z M6,51c-2.206,0-4-1.794-4-4s1.794-4,4-4s4,1.794,4,4S8.206,51,6,51z M33,49c0,2.206-1.794,4-4,4s-4-1.794-4-4
s1.794-4,4-4S33,46.794,33,49z M29,31c-3.309,0-6-2.691-6-6s2.691-6,6-6s6,2.691,6,6S32.309,31,29,31z M47,41c0,1.103-0.897,2-2,2
s-2-0.897-2-2s0.897-2,2-2S47,39.897,47,41z M49,10c-2.206,0-4-1.794-4-4s1.794-4,4-4s4,1.794,4,4S51.206,10,49,10z"></path></svg></div><div id="global-graph-outer"><div id="global-graph-container" data-cfg="{&quot;drag&quot;:true,&quot;zoom&quot;:true,&quot;depth&quot;:-1,&quot;scale&quot;:0.9,&quot;repelForce&quot;:0.5,&quot;centerForce&quot;:0.3,&quot;linkDistance&quot;:30,&quot;fontSize&quot;:0.6,&quot;opacityScale&quot;:1,&quot;showTags&quot;:true,&quot;removeTags&quot;:[]}"></div></div></div><div class="toc desktop-only"><button type="button" id="toc" class><h3>Table of Contents</h3><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="fold"><polyline points="6 9 12 15 18 9"></polyline></svg></button><div id="toc-content"><ul class="overflow"><li class="depth-0"><a href="#概述" data-for="概述">概述</a></li><li class="depth-1"><a href="#子模块" data-for="子模块">子模块</a></li><li class="depth-1"><a href="#优点" data-for="优点">优点</a></li><li class="depth-1"><a href="#缺点" data-for="缺点">缺点</a></li><li class="depth-1"><a href="#同类产品对比" data-for="同类产品对比">同类产品对比</a></li><li class="depth-0"><a href="#urllibrequest" data-for="urllibrequest">urllib.request</a></li><li class="depth-1"><a href="#urlopen-打开-url" data-for="urlopen-打开-url">urlopen() 打开 URL</a></li><li class="depth-1"><a href="#urlretrieve-下载文件" data-for="urlretrieve-下载文件">urlretrieve() 下载文件</a></li><li class="depth-1"><a href="#build_opener-和-install_opener" data-for="build_opener-和-install_opener">build_opener() 和 install_opener()</a></li><li class="depth-1"><a href="#http-基础认证-httpbasicauthhandler" data-for="http-基础认证-httpbasicauthhandler">HTTP 基础认证 (HTTPBasicAuthHandler)</a></li><li class="depth-1"><a href="#httpcookieprocessor-处理-cookies" data-for="httpcookieprocessor-处理-cookies">HTTPCookieProcessor 处理 Cookies</a></li><li class="depth-1"><a href="#proxyhandler-设置代理" data-for="proxyhandler-设置代理">ProxyHandler 设置代理</a></li><li class="depth-1"><a href="#request-自定义请求" data-for="request-自定义请求">Request() 自定义请求</a></li><li class="depth-0"><a href="#urlliberror" data-for="urlliberror">urllib.error</a></li><li class="depth-1"><a href="#urlerror" data-for="urlerror">URLError</a></li><li class="depth-1"><a href="#httperror" data-for="httperror">HTTPError</a></li><li class="depth-1"><a href="#contenttooshorterror" data-for="contenttooshorterror">ContentTooShortError</a></li><li class="depth-0"><a href="#urllibparse" data-for="urllibparse">urllib.parse</a></li><li class="depth-1"><a href="#解析和构建-url" data-for="解析和构建-url">解析和构建 URL</a></li><li class="depth-1"><a href="#转换查询字符串" data-for="转换查询字符串">转换查询字符串</a></li><li class="depth-1"><a href="#url-编码和解码" data-for="url-编码和解码">URL 编码和解码</a></li><li class="depth-0"><a href="#urllibrobotparser" data-for="urllibrobotparser">urllib.robotparser</a></li><li class="depth-1"><a href="#创建和设置-robotfileparser" data-for="创建和设置-robotfileparser">创建和设置 RobotFileParser</a></li><li class="depth-1"><a href="#检查爬虫是否可以访问特定页面" data-for="检查爬虫是否可以访问特定页面">检查爬虫是否可以访问特定页面</a></li><li class="depth-1"><a href="#手动解析-robotstxt" data-for="手动解析-robotstxt">手动解析 robots.txt</a></li></ul></div></div><div class="backlinks "><h3>Backlinks</h3><ul class="overflow"><li>No backlinks found</li></ul></div><div class="explorer mobile-only"><button type="button" id="explorer" data-behavior="collapse" data-collapsed="collapsed" data-savestate="true" data-tree="[{&quot;path&quot;:&quot;Basics&quot;,&quot;collapsed&quot;:true},{&quot;path&quot;:&quot;Basics/english&quot;,&quot;collapsed&quot;:true},{&quot;p
function toggleCallout() {
const outerBlock = this.parentElement;
outerBlock.classList.toggle(`is-collapsed`);
const collapsed = outerBlock.classList.contains(`is-collapsed`);
const height = collapsed ? this.scrollHeight : outerBlock.scrollHeight;
outerBlock.style.maxHeight = height + `px`;
let current = outerBlock;
let parent = outerBlock.parentElement;
while (parent) {
if (!parent.classList.contains(`callout`)) {
return;
}
const collapsed2 = parent.classList.contains(`is-collapsed`);
const height2 = collapsed2 ? parent.scrollHeight : parent.scrollHeight + current.scrollHeight;
parent.style.maxHeight = height2 + `px`;
current = parent;
parent = parent.parentElement;
}
}
function setupCallout() {
const collapsible = document.getElementsByClassName(
`callout is-collapsible`
);
for (const div of collapsible) {
const title = div.firstElementChild;
if (title) {
title.removeEventListener(`click`, toggleCallout);
title.addEventListener(`click`, toggleCallout);
const collapsed = div.classList.contains(`is-collapsed`);
const height = collapsed ? title.scrollHeight : div.scrollHeight;
div.style.maxHeight = height + `px`;
}
}
}
document.addEventListener(`nav`, setupCallout);
window.addEventListener(`resize`, setupCallout);
</script><script type="module">
import mermaid from 'https://cdn.jsdelivr.net/npm/mermaid/dist/mermaid.esm.min.mjs';
const darkMode = document.documentElement.getAttribute('saved-theme') === 'dark'
mermaid.initialize({
startOnLoad: false,
securityLevel: 'loose',
theme: darkMode ? 'dark' : 'default'
});
document.addEventListener('nav', async () => {
await mermaid.run({
querySelector: '.mermaid'
})
});
</script><script src="https://cdn.jsdelivr.net/npm/katex@0.16.7/dist/contrib/copy-tex.min.js" type="application/javascript"></script><script src="../../../../../postscript.js" type="module"></script></html>
Copy Permalink