index.html

<!--      　　　___           ___           ___           ___           ___                    ___           ___       ___           ___     
　　　　　　   /\  \         /\  \         /\__\         |\__\         /\  \                  /\  \         /\__\     /\  \         /\  \    
  　　　　　　 \:\  \       /::\  \       /:/  /         |:|  |       /::\  \                /::\  \       /:/  /    /::\  \       /::\  \   
          　　  \:\  \     /:/\:\  \     /:/__/          |:|  |      /:/\ \  \              /:/\:\  \     /:/  /    /:/\:\  \     /:/\:\  \  
          　　  /::\  \   /::\~\:\  \   /::\  \ ___      |:|__|__   _\:\~\ \  \            /::\~\:\__\   /:/  /    /:/  \:\  \   /:/  \:\  \ 
          　　 /:/\:\__\ /:/\:\ \:\__\ /:/\:\  /\__\ ____/::::\__\ /\ \:\ \ \__\          /:/\:\ \:|__| /:/__/    /:/__/ \:\__\ /:/__/_\:\__\
        　　  /:/  \/__/ \/_|::\/:/  / \/__\:\/:/  / \::::/~~/~    \:\ \:\ \/__/          \:\~\:\/:/  / \:\  \    \:\  \ /:/  / \:\  /\ \/__/
        　　 /:/  /         |:|::/  /       \::/  /   ~~|:|~~|      \:\ \:\__\             \:\ \::/  /   \:\  \    \:\  /:/  /   \:\ \:\__\  
        　　 \/__/          |:|\/__/        /:/  /      |:|  |       \:\/:/  /              \:\/:/  /     \:\  \    \:\/:/  /     \:\/:/  /  
        　　                |:|  |         /:/  /       |:|  |        \::/  /                \::/__/       \:\__\    \::/  /       \::/  /   
        　　                 \|__|         \/__/         \|__|         \/__/                  ~~            \/__/     \/__/         \/__/    

   ┌───┐   ┌───┬───┬───┬───┐   ┌───┬───┬───┬───┐   ┌───┬───┬───┬───┐  ┌───┬───┬───┐
   │ Esc  │   │  F1  │  F2  │  F3  │  F4  │   │  F5  │  F6  │  F7  │  F8  │   │  F9  │ F10  │ F11  │ F12  │  │ P/S  │ S L  │ P/B  │
   └───┘   └───┴───┴───┴───┘   └───┴───┴───┴───┘   └───┴───┴───┴───┘  └───┴───┴───┘
   ┌───┬───┬───┬───┬───┬───┬───┬───┬───┬───┬───┬───┬───┬───────┐ ┌───┬───┬───┐
   │ ~ `  │ ! 1  │ @ 2  │ # 3  │ $ 4  │ % 5  │ ^ 6  │ & 7  │ * 8  │ ( 9  │ ) 0  │ _ -  │ + =  │    BacSp     │ │ Ins  │ Hom  │ PUp  │
   ├───┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─────┤ ├───┼───┼───┤
   │   Tab    │  Q   │  W   │  E   │  R   │  T   │  Y   │  U   │  I   │  O   │  P   │ { [  │ } ]  │   | \    │ │ Del  │ End  │ PDn  │
   ├─────┴┬──┴┬──┴┬──┴┬──┴┬──┴┬──┴┬──┴┬──┴┬──┴┬──┴┬──┴┬──┴─────┤ └───┴───┴───┘
   │    Caps    │  A   │  S   │  D   │  F   │  G   │  H   │  J   │  K   │  L   │ : ;  │ " '  │     Enter      │
   ├──────┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴─┬─┴────────┤         ┌───┐
   │     Shift      │  Z   │  X   │  C   │  V   │  B   │  N   │  M   │ < ,  │ > .  │ ? /  │       Shift        │         │  ↑  │
   ├─────┬──┴─┬─┴──┬┴───┴───┴───┴───┴───┴──┬┴───┼───┴┬────┬────┤ ┌───┼───┼───┐
   │   Ctrl   │        │  Alt   │                     Space                    │   Alt  │   Fn   │   ＝   │  Ctrl  │ │  ←  │  ↓  │  →  │
   └─────┴────┴────┴───────────────────────┴────┴────┴────┴────┘ └───┴───┴───┘

              写字楼里写字间，写字间里程序员；程序人员写程序，又拿程序换酒钱。酒醒只在网上坐，酒醉还来网下眠；酒醉酒醒日复日，网上网下年复年。
              但愿老死电脑间，不愿鞠躬老板前；奔驰宝马贵者趣，公交自行程序员。别人笑我忒疯癫，我笑自己命太贱；不见满街漂亮妹，哪个归得程序员？
-->
<!DOCTYPE html>
<html>
<head>
  <meta charset="utf-8">
  <meta http-equiv="X-UA-Compatible" content="IE=edge" />
  
  <title>Python3 爬虫学习笔记 C15 | TRHX&#39;S BLOG</title>
  
  <meta name="keywords" content="Python爬虫,数据分析,数据可视化,web前端,Java,Python,HTML,软件工程,大学生,hexo,GitHubPages,CodingPages">
  
  
  <meta name="description" content="TRHX 的个人博客；主攻 Python、爬虫、WEB前端、大数据、数据分析、数据可视化；求知若饥，虚心若愚，一入 IT 深似海，从此学习无绝期，记录毕生所学！">
  

  <link rel="alternate" href="/atom.xml" title="TRHX'S BLOG">
  

  <meta name="HandheldFriendly" content="True" />
  <meta name="apple-mobile-web-app-capable" content="yes">
  <meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1">
  <!-- meta -->
  
  
  <meta name='theme-color' content='#f24e32'>
  <meta name='msapplication-TileColor' content='#f24e32'>
  <meta name='msapplication-config' content='https://cdn.jsdelivr.net/gh/xaoxuu/assets@master/favicon/favicons/browserconfig.xml'>
  
  <!-- 360 -->
  <meta name="360-site-verification" content="d98acd5dccc92e495179410dd58186be" />
  <!-- 360自动收录 -->
  <script>
    (function () {
      var src = "https://jspassport.ssl.qhimg.com/11.0.1.js?d182b3f28525f2db83acfaaf6e696dba";
      document.write('<script src="' + src + '" id="sozz"><\/script>');
    })();
  </script>
  <!-- sogou -->
  <meta name="sogou_site_verification" content="l0yGeAV56W" />
  <!-- link -->
  <link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/fancyapps/fancybox@3.5.7/dist/jquery.fancybox.min.css" />
  
  <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/node-waves@0.7.6/dist/waves.min.css">
  
  <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/@fortawesome/fontawesome-free@5.6.3/css/all.min.css">
  
  
  <link rel='shortcut icon' type='image/x-icon' href='https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.4/images/favicon.ico'>
  <link rel='icon' type='image/x-icon' sizes='32x32' href='https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.4/images/favicon-32x32.png'>
  <link rel='apple-touch-icon' type='image/png' sizes='180x180' href='https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.4/images/apple-touch-icon.png'>
  <link rel='mask-icon' color='#f24e32' href='https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.4/images/safari-pinned-tab.svg'>
  <link rel='manifest' href='https://cdn.jsdelivr.net/gh/xaoxuu/cdn-favicon@19.9.7/site.webmanifest'>
  

  <link rel="shortcut icon" type='image/x-icon' href="https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.4/images/favicon.ico">
  

  <link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.1.0/css/style.css">
  

  <script>
    function setLoadingBarProgress(num) {
      document.getElementById('loading-bar').style.width = num + "%";
    }
  </script>

  
  <!-- ba -->
  <script>
    var _hmt = _hmt || [];
    (function () {
      var hm = document.createElement("script");
      hm.src = "https://hm.baidu.com/hm.js?df0bc7c6bdbd80356ba4db429724ccad";
      var s = document.getElementsByTagName("script")[0];
      s.parentNode.insertBefore(hm, s);
    })();
  </script>
  
  <!-- Google Adsense -->
  <!--<script data-ad-client="ca-pub-1913211097936916" async src="https://pagead2.googlesyndication.com/pagead/js/adsbygoogle.js"></script>-->
</head>
<body>
  
  
<div class="cover-wrapper">
  <cover class='cover post half'>
    
    
  <img class='logo' src='https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.1.0/images/logo.png'/>


  <div class="m_search">
    <form name="searchform" class="form u-search-form">
      <input type="text" class="input u-search-input" placeholder="世界之大，探索一下！" />
      <i class="icon fas fa-search fa-fw"></i>
    </form>
  </div>

<div class='menu navgation'>
  <ul class='h-list'>
    
      
        <li>
          <a class="nav home" href="/"
            
            
            id="home">
            <i class='fas fa-home fa-fw'></i>&nbsp;主页
          </a>
        </li>
      
        <li>
          <a class="nav home" href="/categories/"
            
            
            id="categories">
            <i class='fas fa-folder-open fa-fw'></i>&nbsp;分类
          </a>
        </li>
      
        <li>
          <a class="nav home" href="/tags/"
            
            
            id="tags">
            <i class='fas fa-tags fa-fw'></i>&nbsp;标签
          </a>
        </li>
      
        <li>
          <a class="nav home" href="/friends/"
            
            
            id="friends">
            <i class='fas fa-users fa-fw'></i>&nbsp;朋友
          </a>
        </li>
      
        <li>
          <a class="nav home" href="/comments/"
            
            
            id="comments">
            <i class='fas fa-comments fa-fw'></i>&nbsp;留言
          </a>
        </li>
      
    
  </ul>
</div>

    
    <br>
    <!-- Hitokoto 一言 -->
    <!--<p id="hitokoto"></p>
			<script src="https://cdn.jsdelivr.net/npm/bluebird@3/js/browser/bluebird.min.js"></script>
			<script src="https://cdn.jsdelivr.net/npm/whatwg-fetch@2.0.3/fetch.min.js"></script>
      <script src="https://v1.hitokoto.cn/?encode=js&select=%23hitokoto" defer></script>-->
    <!-- 打字特效 -->
    <script src="https://cdn.jsdelivr.net/npm/typed.js@2.0.11"></script>
    <div style="text-align: center;font-weight: bold;color: #1BC3FB;">
      <span id="subtitle"></span>
      <span id="typed-cursor"></span>
    </div>
    <script>
      var typed = new Typed("#subtitle", { strings: ["Live a good life, write some good code !!!", "愿自己的努力终将获得回报。", "花开不是为了花落，而是为了开的更加灿烂。", "没有伞的孩子必须努力奔跑！", "欲望以提升热忱，毅力以磨平高山。", "如果放弃太早，你永远都不知道自己会错过什么。", "没有礁石，就没有美丽的浪花；没有挫折，就没有壮丽的人生。"], startDelay: 1000, typeSpeed: 100, loop: !0, backSpeed: 60, backDelay: 2000, showCursor: !0 })
    </script>
  </cover>
  <header class="l_header pure">
  <div id="loading-bar-wrapper">
    <div id="loading-bar" class="pure"></div>
  </div>

	<div class='wrapper'>
		<div class="nav-main container container--flex">
      <a class="logo flat-box" href='/' >
        
          TRHX'S BLOG
        
      </a>
			<div class='menu navgation'>
				<ul class='h-list'>
          
  					
  						<li>
								<a class="nav flat-box" href="/"
                  
                  
                  id="home">
									<i class='fas fa-home fa-fw'></i>&nbsp;主页
								</a>
							</li>
      			
  						<li>
								<a class="nav flat-box" href="/archives/"
                  
                  
                  id="archives">
									<i class='fas fa-archive fa-fw'></i>&nbsp;归档
								</a>
							</li>
      			
  						<li>
								<a class="nav flat-box" href="/friends/"
                  
                  
                  id="friends">
									<i class='fas fa-users fa-fw'></i>&nbsp;朋友
								</a>
							</li>
      			
  						<li>
								<a class="nav flat-box" href="/comments/"
                  
                  
                  id="comments">
									<i class='fas fa-comments fa-fw'></i>&nbsp;留言
								</a>
							</li>
      			
  						<li>
								<a class="nav flat-box" href="/about/"
                  
                  
                    target="_blank"
                  
                  id="about">
									<i class='fas fa-info-circle fa-fw'></i>&nbsp;关于
								</a>
							</li>
      			
  						<li>
								<a class="nav flat-box" href="/box/"
                  
                  
                    target="_blank"
                  
                  id="box">
									<i class='fas fa-tools fa-fw'></i>&nbsp;百宝箱
								</a>
							</li>
      			
  						<li>
								<a class="nav flat-box" href="https://mi.aliyun.com/shop/40012"
                  
                  
                    target="_blank"
                  
                  id="https:mi.aliyun.comshop40012">
									<i class='fas fa-link fa-fw'></i>&nbsp;米店
								</a>
							</li>
      			
  						<li>
								<a class="nav flat-box" href="http://covid-19.itrhx.com/"
                  
                  
                    target="_blank"
                  
                  id="http:covid-19.itrhx.com">
									<i class='fas fa-heart fa-fw'></i>&nbsp;肺炎疫情图
								</a>
							</li>
      			
      		
				</ul>
			</div>

			
				<div class="m_search">
					<form name="searchform" class="form u-search-form">
						<input type="text" class="input u-search-input" placeholder="搜索" />
						<i class="icon fas fa-search fa-fw"></i>
					</form>
				</div>
			
			<ul class='switcher h-list'>
				
					<li class='s-search'><a class="fas fa-search fa-fw" href='javascript:void(0)'></a></li>
				
				<li class='s-menu'><a class="fas fa-bars fa-fw" href='javascript:void(0)'></a></li>
			</ul>
		</div>

		<div class='nav-sub container container--flex'>
			<a class="logo flat-box"></a>
			<ul class='switcher h-list'>
				<li class='s-comment'><a class="flat-btn fas fa-comments fa-fw" href='javascript:void(0)'></a></li>
        
          <li class='s-toc'><a class="flat-btn fas fa-list fa-fw" href='javascript:void(0)'></a></li>
        
			</ul>
		</div>
	</div>
</header>
	<aside class="menu-phone">
    <header>
		<nav class="menu navgation">
      <ul>
        
          
            <li>
							<a class="nav flat-box" href="/"
                
                
                id="home">
								<i class='fas fa-home fa-fw'></i>&nbsp;主页
							</a>
            </li>
          
            <li>
							<a class="nav flat-box" href="/archives/"
                
                
                id="archives">
								<i class='fas fa-archive fa-fw'></i>&nbsp;归档
							</a>
            </li>
          
            <li>
							<a class="nav flat-box" href="/friends/"
                
                
                id="friends">
								<i class='fas fa-users fa-fw'></i>&nbsp;朋友
							</a>
            </li>
          
            <li>
							<a class="nav flat-box" href="/comments/"
                
                
                id="comments">
								<i class='fas fa-comments fa-fw'></i>&nbsp;留言
							</a>
            </li>
          
            <li>
							<a class="nav flat-box" href="https://mi.aliyun.com/shop/40012"
                
                
                id="https:mi.aliyun.comshop40012">
								<i class='fas fa-link fa-fw'></i>&nbsp;米店
							</a>
            </li>
          
            <li>
							<a class="nav flat-box" href="/box/"
                
                
                id="box">
								<i class='fas fa-tools fa-fw'></i>&nbsp;百宝箱
							</a>
            </li>
          
            <li>
							<a class="nav flat-box" href="https://itrhx.blog.csdn.net/"
                
                
                id="https:itrhx.blog.csdn.net">
								<i class='fab fa-cuttlefish fa-fw'></i>&nbsp;CSDN
							</a>
            </li>
          
            <li>
							<a class="nav flat-box" href="http://covid-19.itrhx.com/"
                
                
                id="http:covid-19.itrhx.com">
								<i class='fas fa-heart fa-fw'></i>&nbsp;肺炎疫情图
							</a>
            </li>
          
       
      </ul>
		</nav>
    </header>
	</aside>
<script>setLoadingBarProgress(40);</script>

</div>

  <div class="l_body">
    <div class='body-wrapper'>
      <div class='l_main'>
  

    <article id="post" class="post white-box article-type-post" itemscope itemprop="blogPost">
      

  <section class='meta'>
    
    
      <a title='Python3 爬虫学习笔记 C15' href='/2019/09/10/A45-Python3-spider-C15/'><img class='thumbnail' src='https://cdn.jsdelivr.net/gh/TRHX/ImageHosting/ITRHX-PIC/thumbnail/spider.png'></a>
    
    <div class="meta" id="header-meta">
      
        
    <h1 class="title">
      <a href="/2019/09/10/A45-Python3-spider-C15/">
        Python3 爬虫学习笔记 C15
      </a>
    </h1>
  

      <div class='new-meta-box'>
        
          
  <div class='new-meta-item author'>
    <a href="https://www.itrhx.com" rel="nofollow">
      
        <img src="https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@2.1.9/images/trhx.png">
      
      <p>TRHX</p>
    </a>
  </div>


            <div class="new-meta-item date">
  <a class='notlink'>
    <i class="fas fa-calendar-alt" aria-hidden="true"></i>
    <p>2019-09-10</p>
  </a>
</div>

          
  <div class='new-meta-item category'>
    <a href='/categories/Python3-学习笔记/爬虫学习/' rel="nofollow">
      <i class="fas fa-folder-open" aria-hidden="true"></i>
      <p>Python3 学习笔记&nbsp;/&nbsp;爬虫学习</p>
    </a>
  </div>


    <div class="new-meta-item browse busuanzi">
      <a class='notlink'>
        <i class="fas fa-eye" aria-hidden="true"></i>
        <p>
          <span id="busuanzi_value_page_pv">
            <i class="fas fa-spinner fa-spin fa-fw" aria-hidden="true"></i>
          </span>
        </p>
      </a>
    </div>
  

    <div class="new-meta-item wordcount">
      <a class='notlink'>
        <i class="fas fa-keyboard" aria-hidden="true"></i>
        <p>字数统计:</p>
        <p>1,826字</p>
      </a>
    </div>
    <div class="new-meta-item readtime">
      <a class='notlink'>
        <i class="fas fa-hourglass-half" aria-hidden="true"></i>
        <p>阅读时长≈</p>
        <p>9分</p>
      </a>
    </div>
  

      </div>
      
        <hr>
      
    </div>
  </section>


      <section class="article typo">
        <div class="article-entry" itemprop="articleBody">
          <blockquote>
<center><font color="#1BC3FB" size="4">Python3 爬虫学习笔记第十五章 —— 【代理的基本使用】</font></center>
</blockquote>
<a id="more"></a>
<hr>
<h1 id="【15-1】代理初识"><a href="#【15-1】代理初识" class="headerlink" title="【15.1】代理初识"></a><font color="#ff0000">【15.1】代理初识</font></h1><p>大多数网站都有反爬虫机制，如果一段时间内同一个 IP 发送的请求过多，服务器就会拒绝访问，直接禁封该 IP，此时，设置代理即可解决这个问题，网络上有许多免费代理和付费代理，比如<a href="https://www.xicidaili.com/" target="_blank" rel="noopener">西刺代理</a>，<a href="http://www.goubanjia.com/" target="_blank" rel="noopener">全网代理 IP</a>，<a href="https://www.kuaidaili.com/" target="_blank" rel="noopener">快代理</a>等，设置代理需要用到的就是代理 IP 地址和端口号，如果电脑上装有代理软件（例如：酸酸乳SSR），软件一般会在本机创建 HTTP 或 SOCKS 代理服务，直接使用此代理也可以</p>
<h1 id="【15-2】urllib-库使用代理"><a href="#【15-2】urllib-库使用代理" class="headerlink" title="【15.2】urllib 库使用代理"></a><font color="#ff0000">【15.2】urllib 库使用代理</font></h1><figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br></pre></td><td class="code"><pre><span class="line"><span class="keyword">from</span> urllib.error <span class="keyword">import</span> URLError</span><br><span class="line"><span class="keyword">from</span> urllib.request <span class="keyword">import</span> ProxyHandler, build_opener</span><br><span class="line"></span><br><span class="line">proxy = <span class="string">'127.0.0.1:1080'</span></span><br><span class="line">proxy_handler = ProxyHandler(&#123;</span><br><span class="line">    <span class="string">'http'</span>: <span class="string">'http://'</span> + proxy,</span><br><span class="line">    <span class="string">'https'</span>: <span class="string">'https://'</span> + proxy</span><br><span class="line">&#125;)</span><br><span class="line">opener = build_opener(proxy_handler)</span><br><span class="line"><span class="keyword">try</span>:</span><br><span class="line">    response = opener.open(<span class="string">'http://httpbin.org/get'</span>)</span><br><span class="line">    print(response.read().decode(<span class="string">'utf8'</span>))</span><br><span class="line"><span class="keyword">except</span> URLError <span class="keyword">as</span> e:</span><br><span class="line">    print(e.reason)</span><br></pre></td></tr></table></figure>
<p><a href="http://httpbin.org/get" target="_blank" rel="noopener">http://httpbin.org/get</a> 是一个请求测试站点，借助 ProxyHandler 设置代理，参数为字典类型，键名为协议类型，键值为代理，代理的写法：<code>proxy = &#39;127.0.0.1:1080&#39;</code>，其中 127.0.0.1 为 IP 地址，1080 为端口号，这里表示本机的代理软件已经在本地 1080 端口创建了代理服务，代理前面需要加上 http 或者 https 协议，当请求的链接为 http 协议时，ProxyHandler 会自动调用 http 代理，同理，当请求的链接为 https 协议时，ProxyHandler 会自动调用 https 代理，<code>build_opener()</code> 方法传入 ProxyHandler 对象来创建一个 opener，调用 <code>open()</code> 方法传入一个 url 即可通过代理访问该链接，运行结果为一个 JSON，origin 字段为此时客户端的 IP</p>
<figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br></pre></td><td class="code"><pre><span class="line">&#123;</span><br><span class="line">  <span class="string">"args"</span>: &#123;&#125;, </span><br><span class="line">  <span class="string">"headers"</span>: &#123;</span><br><span class="line">    <span class="string">"Accept-Encoding"</span>: <span class="string">"identity"</span>, </span><br><span class="line">    <span class="string">"Host"</span>: <span class="string">"httpbin.org"</span>, </span><br><span class="line">    <span class="string">"User-Agent"</span>: <span class="string">"Python-urllib/3.6"</span></span><br><span class="line">  &#125;, </span><br><span class="line">  <span class="string">"origin"</span>: <span class="string">"168.70.60.141, 168.70.60.141"</span>, </span><br><span class="line">  <span class="string">"url"</span>: <span class="string">"https://httpbin.org/get"</span></span><br><span class="line">&#125;</span><br></pre></td></tr></table></figure>
<p>如果是需要认证的代理，只需要在代理前面加入代理认证的用户名密码即可：</p>
<figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br></pre></td><td class="code"><pre><span class="line"><span class="keyword">from</span> urllib.error <span class="keyword">import</span> URLError</span><br><span class="line"><span class="keyword">from</span> urllib.request <span class="keyword">import</span> ProxyHandler, build_opener</span><br><span class="line"></span><br><span class="line">proxy = <span class="string">'username:password@127.0.0.1:1080'</span></span><br><span class="line">proxy_handler = ProxyHandler(&#123;</span><br><span class="line">    <span class="string">'http'</span>: <span class="string">'http://'</span> + proxy,</span><br><span class="line">    <span class="string">'https'</span>: <span class="string">'https://'</span> + proxy</span><br><span class="line">&#125;)</span><br><span class="line">opener = build_opener(proxy_handler)</span><br><span class="line"><span class="keyword">try</span>:</span><br><span class="line">    response = opener.open(<span class="string">'http://httpbin.org/get'</span>)</span><br><span class="line">    print(response.read().decode(<span class="string">'utf8'</span>))</span><br><span class="line"><span class="keyword">except</span> URLError <span class="keyword">as</span> e:</span><br><span class="line">    print(e.reason)</span><br></pre></td></tr></table></figure>
<p>如果代理是 SOCKS5 类型，需要用到 <code>socks</code> 模块，设置代理方法如下：</p>
<blockquote>
<p>扩展：SOCKS5 是一个代理协议，它在使用TCP/IP协议通讯的前端机器和服务器机器之间扮演一个中介角色，使得内部网中的前端机器变得能够访问 Internet 网中的服务器，或者使通讯更加安全</p>
</blockquote>
<figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br></pre></td><td class="code"><pre><span class="line"><span class="keyword">import</span> socks</span><br><span class="line"><span class="keyword">import</span> socket</span><br><span class="line"><span class="keyword">from</span> urllib <span class="keyword">import</span> request</span><br><span class="line"><span class="keyword">from</span> urllib.error <span class="keyword">import</span> URLError</span><br><span class="line"></span><br><span class="line">socks.set_default_proxy(socks.SOCKS5, <span class="string">'127.0.0.1'</span>, <span class="number">1080</span>)</span><br><span class="line">socket.socket = socks.socksocket</span><br><span class="line"><span class="keyword">try</span>:</span><br><span class="line">    response = request.urlopen(<span class="string">'http://httpbin.org/get'</span>)</span><br><span class="line">    print(response.read().decode(<span class="string">'utf-8'</span>))</span><br><span class="line"><span class="keyword">except</span> URLError <span class="keyword">as</span> e:</span><br><span class="line">    print(e.reason)</span><br></pre></td></tr></table></figure>
<h1 id="【15-3】requests-库使用代理"><a href="#【15-3】requests-库使用代理" class="headerlink" title="【15.3】requests 库使用代理"></a><font color="#ff0000">【15.3】requests 库使用代理</font></h1><p>requests 库使用代理只需要传入 proxies 参数即可：</p>
<figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br></pre></td><td class="code"><pre><span class="line"><span class="keyword">import</span> requests</span><br><span class="line"></span><br><span class="line">proxy = <span class="string">'127.0.0.1:1080'</span></span><br><span class="line">proxies = (&#123;</span><br><span class="line">    <span class="string">'http'</span>: <span class="string">'http://'</span> + proxy,</span><br><span class="line">    <span class="string">'https'</span>: <span class="string">'https://'</span> + proxy</span><br><span class="line">&#125;)</span><br><span class="line"><span class="keyword">try</span>:</span><br><span class="line">    response = requests.get(<span class="string">'http://httpbin.org/get'</span>, proxies=proxies)</span><br><span class="line">    print(response.text)</span><br><span class="line"><span class="keyword">except</span> requests.exceptions.ChunkedEncodingError <span class="keyword">as</span> e:</span><br><span class="line">    print(<span class="string">'Error'</span>, e.args)</span><br></pre></td></tr></table></figure>
<p>输出结果：</p>
<figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br></pre></td><td class="code"><pre><span class="line">&#123;</span><br><span class="line">  <span class="string">"args"</span>: &#123;&#125;, </span><br><span class="line">  <span class="string">"headers"</span>: &#123;</span><br><span class="line">    <span class="string">"Accept"</span>: <span class="string">"*/*"</span>, </span><br><span class="line">    <span class="string">"Accept-Encoding"</span>: <span class="string">"gzip, deflate"</span>, </span><br><span class="line">    <span class="string">"Host"</span>: <span class="string">"httpbin.org"</span>, </span><br><span class="line">    <span class="string">"User-Agent"</span>: <span class="string">"python-requests/2.22.0"</span></span><br><span class="line">  &#125;, </span><br><span class="line">  <span class="string">"origin"</span>: <span class="string">"168.70.60.141, 168.70.60.141"</span>, </span><br><span class="line">  <span class="string">"url"</span>: <span class="string">"https://httpbin.org/get"</span></span><br><span class="line">&#125;</span><br></pre></td></tr></table></figure>
<p>同样的，如果是需要认证的代理，也只需要在代理前面加入代理认证的用户名密码即可：</p>
<figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br></pre></td><td class="code"><pre><span class="line"><span class="keyword">import</span> requests</span><br><span class="line"></span><br><span class="line">proxy = <span class="string">'username:password@127.0.0.1:1080'</span></span><br><span class="line">proxies = (&#123;</span><br><span class="line">    <span class="string">'http'</span>: <span class="string">'http://'</span> + proxy,</span><br><span class="line">    <span class="string">'https'</span>: <span class="string">'https://'</span> + proxy</span><br><span class="line">&#125;)</span><br><span class="line"><span class="keyword">try</span>:</span><br><span class="line">    response = requests.get(<span class="string">'http://httpbin.org/get'</span>, proxies=proxies)</span><br><span class="line">    print(response.text)</span><br><span class="line"><span class="keyword">except</span> requests.exceptions.ChunkedEncodingError <span class="keyword">as</span> e:</span><br><span class="line">    print(<span class="string">'Error'</span>, e.args)</span><br></pre></td></tr></table></figure>
<p>如果代理是 SOCKS5 类型，需要用到  <code>requests[socks]</code> 模块或者 <code>socks</code> 模块，使用 <code>requests[socks]</code> 模块时设置代理方法如下：</p>
<figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br></pre></td><td class="code"><pre><span class="line"><span class="keyword">import</span> requests</span><br><span class="line"></span><br><span class="line">proxy = <span class="string">'127.0.0.1:1080'</span></span><br><span class="line">proxies = &#123;</span><br><span class="line">    <span class="string">'http'</span>: <span class="string">'socks5://'</span> + proxy,</span><br><span class="line">    <span class="string">'https'</span>: <span class="string">'socks5://'</span> + proxy</span><br><span class="line">&#125;</span><br><span class="line"><span class="keyword">try</span>:</span><br><span class="line">    response = requests.get(<span class="string">'http://httpbin.org/get'</span>, proxies=proxies)</span><br><span class="line">    print(response.text)</span><br><span class="line"><span class="keyword">except</span> requests.exceptions.ConnectionError <span class="keyword">as</span> e:</span><br><span class="line">    print(<span class="string">'Error'</span>, e.args)</span><br></pre></td></tr></table></figure>
<p>使用 <code>socks</code> 模块时设置代理方法如下（此类方法为全局设置）：</p>
<figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br></pre></td><td class="code"><pre><span class="line"><span class="keyword">import</span> requests</span><br><span class="line"><span class="keyword">import</span> socks</span><br><span class="line"><span class="keyword">import</span> socket</span><br><span class="line"></span><br><span class="line">socks.set_default_proxy(socks.SOCKS5, <span class="string">'127.0.0.1'</span>, <span class="number">1080</span>)</span><br><span class="line">socket.socket = socks.socksocket</span><br><span class="line"><span class="keyword">try</span>:</span><br><span class="line">    response = requests.get(<span class="string">'http://httpbin.org/get'</span>)</span><br><span class="line">    print(response.text)</span><br><span class="line"><span class="keyword">except</span> requests.exceptions.ConnectionError <span class="keyword">as</span> e:</span><br><span class="line">    print(<span class="string">'Error'</span>, e.args)</span><br></pre></td></tr></table></figure>
<h1 id="【15-4】Selenium-使用代理"><a href="#【15-4】Selenium-使用代理" class="headerlink" title="【15.4】Selenium 使用代理"></a><font color="#ff0000">【15.4】Selenium 使用代理</font></h1><h2 id="【15-4-1】Chrome"><a href="#【15-4-1】Chrome" class="headerlink" title="【15.4.1】Chrome"></a><font color="#1BC3FB">【15.4.1】Chrome</font></h2><figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br></pre></td><td class="code"><pre><span class="line"><span class="keyword">from</span> selenium <span class="keyword">import</span> webdriver</span><br><span class="line"></span><br><span class="line">proxy = <span class="string">'127.0.0.1:1080'</span></span><br><span class="line">chrome_options = webdriver.ChromeOptions()</span><br><span class="line">chrome_options.add_argument(<span class="string">'--proxy-server=http://'</span> + proxy)</span><br><span class="line">path = <span class="string">r'F:\PycharmProjects\Python3爬虫\chromedriver.exe'</span></span><br><span class="line">browser = webdriver.Chrome(executable_path=path, chrome_options=chrome_options)</span><br><span class="line">browser.get(<span class="string">'http://httpbin.org/get'</span>)</span><br></pre></td></tr></table></figure>
<p>通过 ChromeOptions 来设置代理，在创建 Chrome 对象的时候用 chrome_options 参数传递即可，访问目标链接后显示如下信息：</p>
<figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br></pre></td><td class="code"><pre><span class="line">&#123;</span><br><span class="line">  <span class="string">"args"</span>: &#123;&#125;, </span><br><span class="line">  <span class="string">"headers"</span>: &#123;</span><br><span class="line">    <span class="string">"Accept"</span>: <span class="string">"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3"</span>, </span><br><span class="line">    <span class="string">"Accept-Encoding"</span>: <span class="string">"gzip, deflate"</span>, </span><br><span class="line">    <span class="string">"Accept-Language"</span>: <span class="string">"zh-CN,zh;q=0.9"</span>, </span><br><span class="line">    <span class="string">"Host"</span>: <span class="string">"httpbin.org"</span>, </span><br><span class="line">    <span class="string">"Upgrade-Insecure-Requests"</span>: <span class="string">"1"</span>, </span><br><span class="line">    <span class="string">"User-Agent"</span>: <span class="string">"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"</span></span><br><span class="line">  &#125;, </span><br><span class="line">  <span class="string">"origin"</span>: <span class="string">"168.70.60.141, 168.70.60.141"</span>, </span><br><span class="line">  <span class="string">"url"</span>: <span class="string">"https://httpbin.org/get"</span></span><br><span class="line">&#125;</span><br></pre></td></tr></table></figure>
<p>如果是认证代理，则设置方法如下：</p>
<figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br><span class="line">15</span><br><span class="line">16</span><br><span class="line">17</span><br><span class="line">18</span><br><span class="line">19</span><br><span class="line">20</span><br><span class="line">21</span><br><span class="line">22</span><br><span class="line">23</span><br><span class="line">24</span><br><span class="line">25</span><br><span class="line">26</span><br><span class="line">27</span><br><span class="line">28</span><br><span class="line">29</span><br><span class="line">30</span><br><span class="line">31</span><br><span class="line">32</span><br><span class="line">33</span><br><span class="line">34</span><br><span class="line">35</span><br><span class="line">36</span><br><span class="line">37</span><br><span class="line">38</span><br><span class="line">39</span><br><span class="line">40</span><br><span class="line">41</span><br><span class="line">42</span><br><span class="line">43</span><br><span class="line">44</span><br><span class="line">45</span><br><span class="line">46</span><br><span class="line">47</span><br><span class="line">48</span><br><span class="line">49</span><br><span class="line">50</span><br><span class="line">51</span><br><span class="line">52</span><br><span class="line">53</span><br></pre></td><td class="code"><pre><span class="line"><span class="keyword">from</span> selenium <span class="keyword">import</span> webdriver</span><br><span class="line"><span class="keyword">from</span> selenium.webdriver.chrome.options <span class="keyword">import</span> Options</span><br><span class="line"><span class="keyword">import</span> zipfile</span><br><span class="line"></span><br><span class="line">ip = <span class="string">'127.0.0.1'</span></span><br><span class="line">port = <span class="number">1080</span></span><br><span class="line">username = <span class="string">'username'</span></span><br><span class="line">password = <span class="string">'password'</span></span><br><span class="line"></span><br><span class="line">manifest_json = <span class="string">"""&#123;"version":"1.0.0","manifest_version": 2,"name":"Chrome Proxy","permissions": ["proxy","tabs","unlimitedStorage","storage","&lt;all_urls&gt;","webRequest","webRequestBlocking"],"background": &#123;"scripts": ["background.js"]</span></span><br><span class="line"><span class="string">    &#125;</span></span><br><span class="line"><span class="string">&#125;</span></span><br><span class="line"><span class="string">"""</span></span><br><span class="line"></span><br><span class="line">background_js =<span class="string">"""</span></span><br><span class="line"><span class="string">var config = &#123;</span></span><br><span class="line"><span class="string">        mode: "fixed_servers",</span></span><br><span class="line"><span class="string">        rules: &#123;</span></span><br><span class="line"><span class="string">          singleProxy: &#123;</span></span><br><span class="line"><span class="string">            scheme: "http",</span></span><br><span class="line"><span class="string">            host: "%(ip) s",</span></span><br><span class="line"><span class="string">            port: %(port) s</span></span><br><span class="line"><span class="string">          &#125;</span></span><br><span class="line"><span class="string">        &#125;</span></span><br><span class="line"><span class="string">      &#125;</span></span><br><span class="line"><span class="string"></span></span><br><span class="line"><span class="string">chrome.proxy.settings.set(&#123;value: config, scope: "regular"&#125;, function() &#123;&#125;);</span></span><br><span class="line"><span class="string"></span></span><br><span class="line"><span class="string">function callbackFn(details) &#123;</span></span><br><span class="line"><span class="string">    return &#123;</span></span><br><span class="line"><span class="string">        authCredentials: &#123;username: "%(username) s",</span></span><br><span class="line"><span class="string">            password: "%(password) s"</span></span><br><span class="line"><span class="string">        &#125;</span></span><br><span class="line"><span class="string">    &#125;</span></span><br><span class="line"><span class="string">&#125;</span></span><br><span class="line"><span class="string"></span></span><br><span class="line"><span class="string">chrome.webRequest.onAuthRequired.addListener(</span></span><br><span class="line"><span class="string">            callbackFn,</span></span><br><span class="line"><span class="string">            &#123;urls: ["&lt;all_urls&gt;"]&#125;,</span></span><br><span class="line"><span class="string">            ['blocking']</span></span><br><span class="line"><span class="string">)</span></span><br><span class="line"><span class="string">"""</span> % &#123;<span class="string">'ip'</span>: ip, <span class="string">'port'</span>: port, <span class="string">'username'</span>: username, <span class="string">'password'</span>: password&#125;</span><br><span class="line"></span><br><span class="line">plugin_file = <span class="string">'proxy_auth_plugin.zip'</span></span><br><span class="line"><span class="keyword">with</span> zipfile.ZipFile(plugin_file, <span class="string">'w'</span>) <span class="keyword">as</span> zp:</span><br><span class="line">    zp.writestr(<span class="string">"manifest.json"</span>, manifest_json)</span><br><span class="line">    zp.writestr(<span class="string">"background.js"</span>, background_js)</span><br><span class="line">chrome_options = Options()</span><br><span class="line">chrome_options.add_argument(<span class="string">"--start-maximized"</span>)</span><br><span class="line">path = <span class="string">r'F:\PycharmProjects\Python3爬虫\chromedriver.exe'</span></span><br><span class="line">chrome_options.add_extension(plugin_file)</span><br><span class="line">browser = webdriver.Chrome(executable_path=path, chrome_options=chrome_options)</span><br><span class="line">browser.get(<span class="string">'http://httpbin.org/get'</span>)</span><br></pre></td></tr></table></figure>
<p>需要在本地创建一个 manifest.json 配置文件和 background.js 脚本来设置认证代理。运行代码之后本地会生成一个 proxy_auth_plugin.zip 文件来保存当前配置</p>
<h2 id="【15-4-1】PhantomJS"><a href="#【15-4-1】PhantomJS" class="headerlink" title="【15.4.1】PhantomJS"></a><font color="#1BC3FB">【15.4.1】PhantomJS</font></h2><p>借助 service_args 参数，也就是命令行参数即可设置代理：</p>
<figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br></pre></td><td class="code"><pre><span class="line"><span class="keyword">from</span> selenium <span class="keyword">import</span> webdriver</span><br><span class="line"></span><br><span class="line">service_args = [</span><br><span class="line">    <span class="string">'--proxy=127.0.0.1:1080'</span>,</span><br><span class="line">    <span class="string">'--proxy-type=http'</span></span><br><span class="line">]</span><br><span class="line">path = <span class="string">r'F:\PycharmProjects\Python3爬虫\phantomjs-2.1.1\bin\phantomjs.exe'</span></span><br><span class="line">browser = webdriver.PhantomJS(executable_path=path, service_args=service_args)</span><br><span class="line">browser.get(<span class="string">'http://httpbin.org/get'</span>)</span><br><span class="line">print(browser.page_source)</span><br></pre></td></tr></table></figure>
<p>运行结果：</p>
<figure class="highlight"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br></pre></td><td class="code"><pre><span class="line">&lt;html&gt;&lt;head&gt;&lt;/head&gt;&lt;body&gt;&lt;pre style="word-wrap: break-word; white-space: pre-wrap;"&gt;&#123;</span><br><span class="line">  <span class="string">"args"</span>: &#123;&#125;, </span><br><span class="line">  <span class="string">"headers"</span>: &#123;</span><br><span class="line">    <span class="string">"Accept"</span>: <span class="string">"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"</span>, </span><br><span class="line">    <span class="string">"Accept-Encoding"</span>: <span class="string">"gzip, deflate"</span>, </span><br><span class="line">    <span class="string">"Accept-Language"</span>: <span class="string">"zh-CN,en,*"</span>, </span><br><span class="line">    <span class="string">"Host"</span>: <span class="string">"httpbin.org"</span>, </span><br><span class="line">    <span class="string">"User-Agent"</span>: <span class="string">"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/538.1 (KHTML, like Gecko) PhantomJS/2.1.1 Safari/538.1"</span></span><br><span class="line">  &#125;, </span><br><span class="line">  <span class="string">"origin"</span>: <span class="string">"168.70.60.141, 168.70.60.141"</span>, </span><br><span class="line">  <span class="string">"url"</span>: <span class="string">"https://httpbin.org/get"</span></span><br><span class="line">&#125;</span><br><span class="line">&lt;/pre&gt;&lt;/body&gt;&lt;/html&gt;</span><br></pre></td></tr></table></figure>
<p>如果是需要认证的代理，只需要在 service_args 参数加入 –proxy-auth 选项即可：</p>
<figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br></pre></td><td class="code"><pre><span class="line"><span class="keyword">from</span> selenium <span class="keyword">import</span> webdriver</span><br><span class="line"></span><br><span class="line">service_args = [</span><br><span class="line">    <span class="string">'--proxy=127.0.0.1:1080'</span>,</span><br><span class="line">    <span class="string">'--proxy-type=http'</span>,</span><br><span class="line">    <span class="string">'--proxy-auth=username:password'</span></span><br><span class="line">]</span><br><span class="line">path = <span class="string">r'F:\PycharmProjects\Python3爬虫\phantomjs-2.1.1\bin\phantomjs.exe'</span></span><br><span class="line">browser = webdriver.PhantomJS(executable_path=path, service_args=service_args)</span><br><span class="line">browser.get(<span class="string">'http://httpbin.org/get'</span>)</span><br><span class="line">print(browser.page_source)</span><br></pre></td></tr></table></figure>
        </div>
        <hr /><br>
        
          <div class="img_container"><a href="https://www.courseduck.com/programming/python/" target="_blank"><img src="https://www.courseduck.com/global/images/Python_header.jpg" class="img-responsive" alt="CourseDuck Python Banner"></a></div>
        
        
          <div id="reward">
  
  <div>您的喜欢是作者写作最大的动力！❤️</div>
  
  <div class="reward">
    <a href="https://github.com/Kaiyuan/donate-page" target="_blank" class=" tr3" title="Github"><span
        id="github"></span></a>
    <ul id="RewardBox" class="list pos-f tr3">
      
      <li id="PayPal" title="PayPal打赏"><a href="https://paypal.me/trhx" target="_blank">PayPal</a></li>
      
      
      <li id="AliPayOR" title="支付宝打赏">AliPay</li>
      
      
      <li id="WeChatPayOR" title="微信打赏">WeChatPay</li>
      
      
      <li id="QQPayOR" title="QQ打赏">QQPay</li>
      
    </ul>
    <div id="RewardText" class="tr3">Donate</div>
    <div id="QRBox" class="pos-f left-100">
      <div id="MainBox"></div>
    </div>
  </div>
</div>
<script src="https://ajax.aspnetcdn.com/ajax/jQuery/jquery-2.0.3.min.js"></script>
<script>
  jQuery(document).ready(function () {
    var QRBox = $('#QRBox');
    var MainBox = $('#MainBox');
    var AliPayOR = 'https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.1.0/images/reward/AliPayQR.png';
    var WeChatPayOR = 'https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.1.0/images/reward/WeChatQR.png';
    var QQPayOR = 'https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.1.0/images/reward/QQPayQR.png';

    function showQR(QR) {
      if (QR) {
        MainBox.css('background-image', 'url(' + QR + ')');
      }
      $('#RewardText,#RewardBox,#github').addClass('blur');
      QRBox.fadeIn(300, function (argument) {
        MainBox.addClass('showQR');
      });
    }

    $('#RewardBox>li').click(function (event) {
      var thisID = $(this).attr('id');
      if (thisID === 'AliPayOR') {
        showQR(AliPayOR);
      } else if (thisID === 'WeChatPayOR') {
        showQR(WeChatPayOR);
      } else if (thisID === 'QQPayOR') {
        showQR(QQPayOR);
      }
    });

    MainBox.click(function (event) {
      MainBox.removeClass('showQR').addClass('hideQR');
      setTimeout(function (a) {
        QRBox.fadeOut(300, function (argument) {
          MainBox.removeClass('hideQR');
        });
        $('#RewardText,#RewardBox,#github').removeClass('blur');
      }, 600);

    });
  });
</script>

        
  <section class='meta' id="footer-meta">
    <hr>
    <div class='new-meta-box'>
      
        
          <div class="new-meta-item date" itemprop="dateUpdated" datetime="2019-09-24T20:41:02+08:00">
  <a class='notlink'>
    <i class="fas fa-clock" aria-hidden="true"></i>
    <p>最后更新于 2019年9月24日</p>
  </a>
</div>

        
  <div class="new-meta-item meta-tags"><a class="tag" href="/tags/爬虫/" rel="nofollow"><i class="fas fa-tags" aria-hidden="true"></i>&nbsp;<p>爬虫</p></a></div> <div class="new-meta-item meta-tags"><a class="tag" href="/tags/代理/" rel="nofollow"><i class="fas fa-tags" aria-hidden="true"></i>&nbsp;<p>代理</p></a></div>


  <div class="new-meta-item share -mob-share-list">
  <div class="-mob-share-list share-body">
    
      
        <a class="-mob-share-qq" title="QQ好友" rel="external nofollow noopener noreferrer"
          
          href="http://connect.qq.com/widget/shareqq/index.html?url=https://www.itrhx.com/2019/09/10/A45-Python3-spider-C15/&title=Python3 爬虫学习笔记 C15 | TRHX'S BLOG&pics=https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.4/images/trhx.png&summary=
Python3 爬虫学习笔记第十五章 —— 【代理的基本使用】
"
          
          >
          
            <img src="https://cdn.jsdelivr.net/gh/xaoxuu/assets@19.1.9/logo/128/qq.png">
          
        </a>
      
    
        <a class="-mob-share-qzone" title="QQ空间" rel="external nofollow noopener noreferrer"
          
          href="https://sns.qzone.qq.com/cgi-bin/qzshare/cgi_qzshare_onekey?url=https://www.itrhx.com/2019/09/10/A45-Python3-spider-C15/&title=Python3 爬虫学习笔记 C15 | TRHX'S BLOG&pics=https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.4/images/trhx.png&summary=
Python3 爬虫学习笔记第十五章 —— 【代理的基本使用】
"
          
          >
          
            <img src="https://cdn.jsdelivr.net/gh/xaoxuu/assets@19.1.9/logo/128/qzone.png">
          
        </a>
      
    
        <a class='qrcode' rel="external nofollow noopener noreferrer" href='data:image/png;base64,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'>
        
          <img src="https://cdn.jsdelivr.net/gh/xaoxuu/assets@19.1.9/logo/128/wechat.png">
        
        </a>
      
    
        <a class="-mob-share-weibo" title="微博" rel="external nofollow noopener noreferrer"
          
          href="http://service.weibo.com/share/share.php?url=https://www.itrhx.com/2019/09/10/A45-Python3-spider-C15/&title=Python3 爬虫学习笔记 C15 | TRHX'S BLOG&pics=https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.4/images/trhx.png&summary=
Python3 爬虫学习笔记第十五章 —— 【代理的基本使用】
"
          
          >
          
            <img src="https://cdn.jsdelivr.net/gh/xaoxuu/assets@19.1.9/logo/128/weibo.png">
          
        </a>
      
    
        <a class='qrcode' rel="external nofollow noopener noreferrer" href='data:image/png;base64,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'>
        
          <img src="https://cdn.jsdelivr.net/gh/xaoxuu/assets@19.1.9/logo/128/qrcode.png">
        
        </a>
      
    
  </div>
</div>


    </div>
  </section>


            <div class="prev-next">
                
                    <section class="prev">
                        <span class="art-item-left">
                            <h6><i class="fas fa-chevron-left" aria-hidden="true"></i>&nbsp;上一页</h6>
                            <h4>
                                <a href="/2019/09/14/A46-Python3-spider-C16/" rel="prev" title="Python3 爬虫学习笔记 C16">
                                  
                                      Python3 爬虫学习笔记 C16
                                  
                                </a>
                            </h4>
                            
                                
                                <h6 class="tags">
                                    <a class="tag" href="/tags/爬虫/"><i class="fas fa-tags fa-fw" aria-hidden="true"></i>&nbsp;爬虫</a> <a class="tag" href="/tags/Redis/"><i class="fas fa-tags fa-fw" aria-hidden="true"></i>&nbsp;Redis</a>
                                </h6>
                            
                        </span>
                    </section>
                
                
                    <section class="next">
                        <span class="art-item-right" aria-hidden="true">
                            <h6>下一页&nbsp;<i class="fas fa-chevron-right" aria-hidden="true"></i></h6>
                            <h4>
                                <a href="/2019/09/08/A44-Python3-spider-C14/" rel="prev" title="Python3 爬虫学习笔记 C14">
                                    
                                        Python3 爬虫学习笔记 C14
                                    
                                </a>
                            </h4>
                            
                                
                                <h6 class="tags">
                                    <a class="tag" href="/tags/爬虫/"><i class="fas fa-tags fa-fw" aria-hidden="true"></i>&nbsp;爬虫</a> <a class="tag" href="/tags/点触验证码/"><i class="fas fa-tags fa-fw" aria-hidden="true"></i>&nbsp;点触验证码</a>
                                </h6>
                            
                        </span>
                    </section>
                
            </div>
        
      </section>
    </article>
  

    <!-- 显示推荐文章和评论 -->


  <article class="post white-box comments">
    <section class="article typo">
      <h4><i class="fas fa-comments fa-fw" aria-hidden="true"></i>&nbsp;评论</h4>
      
      
        <section id="comments">
          <div id="gitalk-container"></div>
        </section>
      
      
    </section>
  </article>


<!-- 根据页面mathjax变量决定是否加载MathJax数学公式js -->


  <script>
    window.subData = {
      title: 'Python3 爬虫学习笔记 C15',
      tools: true
    }
  </script>


</div>
<aside class='l_side'>
  
    
            <section class='widget author'>
  <div class='content pure'>
    
      <div class='avatar'>
        <img class='avatar' src='https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.1.0/images/trhx.png'/>
      </div>
    
    
      <div class='text'>
        
          <h2>๑۩ﺴ&nbsp;&nbsp;TRHX&nbsp;&nbsp;ﺴ۩๑</h2>
        
        
      </div>
    
    <!-- 彩色滚动字体 -->
    <div id="binft" align="center"></div>
    <script>
      var binft = function (r) {
        function t() {
          return b[Math.floor(Math.random() * b.length)]
        }  
        function e() {
          return String.fromCharCode(94 * Math.random() + 33)
        }
        function n(r) {
          for (var n = document.createDocumentFragment(), i = 0; r > i; i++) {
            var l = document.createElement("span");
            l.textContent = e(), l.style.color = t(), n.appendChild(l)
          }
          return n
        }
        function i() {
          var t = o[c.skillI];
          c.step ? c.step-- : (c.step = g, c.prefixP < l.length ? (c.prefixP >= 0 && (c.text += l[c.prefixP]), c.prefixP++) : "forward" === c.direction ? c.skillP < t.length ? (c.text += t[c.skillP], c.skillP++) : c.delay ? c.delay-- : (c.direction = "backward", c.delay = a) : c.skillP > 0 ? (c.text = c.text.slice(0, -1), c.skillP--) : (c.skillI = (c.skillI + 1) % o.length, c.direction = "forward")), r.textContent = c.text, r.appendChild(n(c.prefixP < l.length ? Math.min(s, s + c.prefixP) : Math.min(s, t.length - c.skillP))), setTimeout(i, d)
        }
        var l = "",
        o = ["Stay Hungry, Stay Foolish!"].map(function (r) {
        return r + ""
        }),
        a = 2,
        g = 1,
        s = 5,
        d = 75,
        b = ["rgb(110,64,170)", "rgb(150,61,179)", "rgb(191,60,175)", "rgb(228,65,157)", "rgb(254,75,131)", "rgb(255,94,99)", "rgb(255,120,71)", "rgb(251,150,51)", "rgb(226,183,47)", "rgb(198,214,60)", "rgb(175,240,91)", "rgb(127,246,88)", "rgb(82,246,103)", "rgb(48,239,130)", "rgb(29,223,163)", "rgb(26,199,194)", "rgb(35,171,216)", "rgb(54,140,225)", "rgb(76,110,219)", "rgb(96,84,200)"],
        c = {
          text: "",
          prefixP: -s,
          skillI: 0,
          skillP: 0,
          direction: "forward",
          delay: a,
          step: g
        };
        i()
        };
        binft(document.getElementById('binft'));
    </script>
    
      <div class="social-wrapper">
        
          
            <a href="https://github.com/TRHX"
              class="social fab fa-github flat-btn"
              target="_blank"
              rel="external nofollow noopener noreferrer">
            </a>
          
        
            <a href="https://itrhx.blog.csdn.net/"
              class="social fab fa-cuttlefish flat-btn"
              target="_blank"
              rel="external nofollow noopener noreferrer">
            </a>
          
        
            <a href="https://www.zhihu.com/people/itrhx"
              class="social fab fa-zhihu flat-btn"
              target="_blank"
              rel="external nofollow noopener noreferrer">
            </a>
          
        
            <a href="mailto:admin@itrhx.com"
              class="social fas fa-envelope flat-btn"
              target="_blank"
              rel="external nofollow noopener noreferrer">
            </a>
          
        
            <a href="http://wpa.qq.com/msgrd?v=3&uin=2273902448&site=qq&menu=yes"
              class="social fab fa-qq flat-btn"
              target="_blank"
              rel="external nofollow noopener noreferrer">
            </a>
          
        
      </div>
    
  </div>
</section>

          
  <section class='widget toc-wrapper'>
    
<header class='pure'>
  <div><i class="fas fa-list fa-fw" aria-hidden="true"></i>&nbsp;&nbsp;本文目录</div>
  
    <div class='wrapper'><a class="s-toc rightBtn" rel="external nofollow noopener noreferrer" href="javascript:void(0)"><i class="fas fa-thumbtack fa-fw"></i></a></div>
  
</header>

    <div class='content pure'>
      <ol class="toc"><li class="toc-item toc-level-1"><a class="toc-link" href="#【15-1】代理初识"><span class="toc-text">【15.1】代理初识</span></a></li><li class="toc-item toc-level-1"><a class="toc-link" href="#【15-2】urllib-库使用代理"><span class="toc-text">【15.2】urllib 库使用代理</span></a></li><li class="toc-item toc-level-1"><a class="toc-link" href="#【15-3】requests-库使用代理"><span class="toc-text">【15.3】requests 库使用代理</span></a></li><li class="toc-item toc-level-1"><a class="toc-link" href="#【15-4】Selenium-使用代理"><span class="toc-text">【15.4】Selenium 使用代理</span></a><ol class="toc-child"><li class="toc-item toc-level-2"><a class="toc-link" href="#【15-4-1】Chrome"><span class="toc-text">【15.4.1】Chrome</span></a></li><li class="toc-item toc-level-2"><a class="toc-link" href="#【15-4-1】PhantomJS"><span class="toc-text">【15.4.1】PhantomJS</span></a></li></ol></li></ol>
    </div>
  </section>


            <section class='widget plain'>
  
<header class='pure'>
  <div><i class="fas fa-handshake fa-fw" aria-hidden="true"></i>&nbsp;&nbsp;欢迎光临</div>
  
    <a class="rightBtn"
    
      rel="external nofollow noopener noreferrer"
    
    
      target="_blank"
    
    href="https://www.revolvermaps.com/"
    title="https://www.revolvermaps.com/">
    <i class="fas fa-info-circle fa-fw"></i></a>
  
</header>

  <div class='content pure'>
    <p><script type="text/javascript" src="//rf.revolvermaps.com/0/0/4.js?i=5eyl60h41k1&amp;m=6&amp;h=122&amp;c=ff0000&amp;r=30" async="async"></script><a id="goroups_button" class="goroups_button_new" target="_blank" href="https://jq.qq.com/?_wv=1027&k=5L7nNUS">Hexo QQ 交流群</a><a id="goroups_button" class="goroups_button_new" target="_blank" href="https://t.me/joinchat/Mro2h0uVt0DpDvOofWG65A">Telegram 交流群</a></p>

  </div>
</section>

          
            <section class='widget plain'>
  
<header class='pure'>
  <div><i class="fas fa-blog fa-fw" aria-hidden="true"></i>&nbsp;&nbsp;CSDN 内容合伙人</div>
  
    <a class="rightBtn"
    
      rel="external nofollow noopener noreferrer"
    
    
      target="_blank"
    
    href="https://itrhx.blog.csdn.net/"
    title="https://itrhx.blog.csdn.net/">
    <i class="fas fa-info-circle fa-fw"></i></a>
  
</header>

  <div class='content pure'>
    <p><a href="https://itrhx.blog.csdn.net/" title="微信扫描二维码添加好友"><img src="https://img-blog.csdnimg.cn/20200610152107390.png"></a></p>

  </div>
</section>

          
  <section class='widget category'>
    
<header class='pure'>
  <div><i class="fas fa-folder-open fa-fw" aria-hidden="true"></i>&nbsp;&nbsp;文章分类</div>
  
    <a class="rightBtn"
    
      rel="nofollow"
    
    
    href="/categories/"
    title="categories/">
    <i class="fas fa-expand-arrows-alt fa-fw"></i></a>
  
</header>

    <div class='content pure'>
      <ul class="entry">
        
          <li><a class="flat-box" title="/categories/BLOG/" href="/categories/BLOG/"><div class='name'>BLOG</div><div class='badge'>(4)</div></a></li>
        
          <li><a class="flat-box" title="/categories/CDN/" href="/categories/CDN/"><div class='name'>CDN</div><div class='badge'>(1)</div></a></li>
        
          <li><a class="flat-box" title="/categories/Hexo/" href="/categories/Hexo/"><div class='name'>Hexo</div><div class='badge'>(9)</div></a></li>
        
          <li><a class="flat-box" title="/categories/Java/" href="/categories/Java/"><div class='name'>Java</div><div class='badge'>(1)</div></a></li>
        
          <li><a class="flat-box" title="/categories/Linux/" href="/categories/Linux/"><div class='name'>Linux</div><div class='badge'>(2)</div></a></li>
        
          <li><a class="flat-box" title="/categories/Markdown/" href="/categories/Markdown/"><div class='name'>Markdown</div><div class='badge'>(2)</div></a></li>
        
          <li><a class="flat-box" title="/categories/Python3-学习笔记/" href="/categories/Python3-学习笔记/"><div class='name'>Python3 学习笔记</div><div class='badge'>(39)</div></a></li>
        
          <li><a class="flat-box child" title="/categories/Python3-学习笔记/基础学习/" href="/categories/Python3-学习笔记/基础学习/"><div class='name'>基础学习</div><div class='badge'>(9)</div></a></li>
        
          <li><a class="flat-box child" title="/categories/Python3-学习笔记/学习经验/" href="/categories/Python3-学习笔记/学习经验/"><div class='name'>学习经验</div><div class='badge'>(4)</div></a></li>
        
          <li><a class="flat-box child" title="/categories/Python3-学习笔记/爬虫学习/" href="/categories/Python3-学习笔记/爬虫学习/"><div class='name'>爬虫学习</div><div class='badge'>(18)</div></a></li>
        
          <li><a class="flat-box child" title="/categories/Python3-学习笔记/爬虫实战/" href="/categories/Python3-学习笔记/爬虫实战/"><div class='name'>爬虫实战</div><div class='badge'>(8)</div></a></li>
        
          <li><a class="flat-box" title="/categories/VPS/" href="/categories/VPS/"><div class='name'>VPS</div><div class='badge'>(1)</div></a></li>
        
          <li><a class="flat-box" title="/categories/WEB前端/" href="/categories/WEB前端/"><div class='name'>WEB前端</div><div class='badge'>(2)</div></a></li>
        
          <li><a class="flat-box" title="/categories/图床/" href="/categories/图床/"><div class='name'>图床</div><div class='badge'>(1)</div></a></li>
        
      </ul>
    </div>
  </section>


  <section class='widget tagcloud'>
    
<header class='pure'>
  <div><i class="fas fa-fire fa-fw" aria-hidden="true"></i>&nbsp;&nbsp;热门标签</div>
  
    <a class="rightBtn"
    
      rel="nofollow"
    
    
    href="/tags/"
    title="tags/">
    <i class="fas fa-expand-arrows-alt fa-fw"></i></a>
  
</header>

    <div class='content pure'>
      <a href="/tags/12306/" style="font-size: 14px; color: #999">12306</a> <a href="/tags/58同城/" style="font-size: 14px; color: #999">58同城</a> <a href="/tags/Ajax/" style="font-size: 14px; color: #999">Ajax</a> <a href="/tags/BLOG/" style="font-size: 16.5px; color: #888">BLOG</a> <a href="/tags/Beautiful-Soup/" style="font-size: 14px; color: #999">Beautiful Soup</a> <a href="/tags/CDN/" style="font-size: 14px; color: #999">CDN</a> <a href="/tags/Coding-Pages/" style="font-size: 14px; color: #999">Coding Pages</a> <a href="/tags/Deepin/" style="font-size: 14px; color: #999">Deepin</a> <a href="/tags/Elicpse/" style="font-size: 14px; color: #999">Elicpse</a> <a href="/tags/GitHub-Pages/" style="font-size: 14px; color: #999">GitHub Pages</a> <a href="/tags/Github/" style="font-size: 14px; color: #999">Github</a> <a href="/tags/Github-Pages/" style="font-size: 14px; color: #999">Github Pages</a> <a href="/tags/HTTPS/" style="font-size: 16.5px; color: #888">HTTPS</a> <a href="/tags/Hexo/" style="font-size: 21.5px; color: #666">Hexo</a> <a href="/tags/ICP备案/" style="font-size: 14px; color: #999">ICP备案</a> <a href="/tags/JDBC/" style="font-size: 14px; color: #999">JDBC</a> <a href="/tags/JS-预加载/" style="font-size: 14px; color: #999">JS 预加载</a> <a href="/tags/Markdown/" style="font-size: 16.5px; color: #888">Markdown</a> <a href="/tags/Material-X/" style="font-size: 14px; color: #999">Material X</a> <a href="/tags/MongoDB/" style="font-size: 14px; color: #999">MongoDB</a> <a href="/tags/MySQL/" style="font-size: 14px; color: #999">MySQL</a> <a href="/tags/PEP8/" style="font-size: 14px; color: #999">PEP8</a> <a href="/tags/PicGo/" style="font-size: 14px; color: #999">PicGo</a> <a href="/tags/Pygame/" style="font-size: 14px; color: #999">Pygame</a> <a href="/tags/Python/" style="font-size: 16.5px; color: #888">Python</a> <a href="/tags/Redis/" style="font-size: 14px; color: #999">Redis</a> <a href="/tags/SEO/" style="font-size: 14px; color: #999">SEO</a> <a href="/tags/SQL-Server-2012/" style="font-size: 14px; color: #999">SQL Server 2012</a> <a href="/tags/SSR/" style="font-size: 14px; color: #999">SSR</a> <a href="/tags/Selenium/" style="font-size: 19px; color: #777">Selenium</a> <a href="/tags/Ubuntu/" style="font-size: 14px; color: #999">Ubuntu</a> <a href="/tags/User-Agent/" style="font-size: 14px; color: #999">User-Agent</a> <a href="/tags/VMware/" style="font-size: 16.5px; color: #888">VMware</a> <a href="/tags/VPS/" style="font-size: 14px; color: #999">VPS</a> <a href="/tags/XPath/" style="font-size: 14px; color: #999">XPath</a> <a href="/tags/if语句/" style="font-size: 14px; color: #999">if语句</a> <a href="/tags/input-函数/" style="font-size: 14px; color: #999">input()函数</a> <a href="/tags/instant-page/" style="font-size: 14px; color: #999">instant.page</a> <a href="/tags/jsDelivr/" style="font-size: 16.5px; color: #888">jsDelivr</a> <a href="/tags/lxml/" style="font-size: 14px; color: #999">lxml</a> <a href="/tags/pyspider/" style="font-size: 16.5px; color: #888">pyspider</a> <a href="/tags/requests/" style="font-size: 14px; color: #999">requests</a> <a href="/tags/spfk/" style="font-size: 14px; color: #999">spfk</a> <a href="/tags/urllib/" style="font-size: 14px; color: #999">urllib</a> <a href="/tags/while循环/" style="font-size: 14px; color: #999">while循环</a> <a href="/tags/主题个性化/" style="font-size: 14px; color: #999">主题个性化</a> <a href="/tags/代理/" style="font-size: 14px; color: #999">代理</a> <a href="/tags/公安备案/" style="font-size: 14px; color: #999">公安备案</a> <a href="/tags/函数/" style="font-size: 14px; color: #999">函数</a> <a href="/tags/列表/" style="font-size: 14px; color: #999">列表</a> <a href="/tags/变量/" style="font-size: 14px; color: #999">变量</a> <a href="/tags/哔哩哔哩/" style="font-size: 14px; color: #999">哔哩哔哩</a> <a href="/tags/图床/" style="font-size: 14px; color: #999">图床</a> <a href="/tags/图形验证码/" style="font-size: 14px; color: #999">图形验证码</a> <a href="/tags/垃圾/" style="font-size: 14px; color: #999">垃圾</a> <a href="/tags/备份/" style="font-size: 14px; color: #999">备份</a> <a href="/tags/字典/" style="font-size: 14px; color: #999">字典</a> <a href="/tags/安居客/" style="font-size: 14px; color: #999">安居客</a> <a href="/tags/年终总结/" style="font-size: 14px; color: #999">年终总结</a> <a href="/tags/异常/" style="font-size: 14px; color: #999">异常</a> <a href="/tags/技巧/" style="font-size: 14px; color: #999">技巧</a> <a href="/tags/操作列表/" style="font-size: 14px; color: #999">操作列表</a> <a href="/tags/数据类型/" style="font-size: 14px; color: #999">数据类型</a> <a href="/tags/文件/" style="font-size: 14px; color: #999">文件</a> <a href="/tags/文件储存/" style="font-size: 14px; color: #999">文件储存</a> <a href="/tags/无界面浏览器/" style="font-size: 14px; color: #999">无界面浏览器</a> <a href="/tags/模块/" style="font-size: 14px; color: #999">模块</a> <a href="/tags/正则表达式/" style="font-size: 14px; color: #999">正则表达式</a> <a href="/tags/滑动验证码/" style="font-size: 14px; color: #999">滑动验证码</a> <a href="/tags/点触验证码/" style="font-size: 14px; color: #999">点触验证码</a> <a href="/tags/爬虫/" style="font-size: 24px; color: #555">爬虫</a> <a href="/tags/猫眼电影/" style="font-size: 14px; color: #999">猫眼电影</a> <a href="/tags/瓜子二手车/" style="font-size: 14px; color: #999">瓜子二手车</a> <a href="/tags/类/" style="font-size: 14px; color: #999">类</a> <a href="/tags/继承/" style="font-size: 14px; color: #999">继承</a> <a href="/tags/编辑器/" style="font-size: 14px; color: #999">编辑器</a> <a href="/tags/虎扑论坛/" style="font-size: 14px; color: #999">虎扑论坛</a> <a href="/tags/豆瓣电影/" style="font-size: 14px; color: #999">豆瓣电影</a>
    </div>
  </section>

          
  <section class='widget music'>
    
<header class='pure'>
  <div><i class="fas fa-compact-disc fa-fw" aria-hidden="true"></i>&nbsp;&nbsp;最近在听</div>
  
    <a class="rightBtn"
    
      rel="external nofollow noopener noreferrer"
    
    
      target="_blank"
    
    href="https://music.163.com/#/user/home?id=3019271605"
    title="https://music.163.com/#/user/home?id=3019271605">
    <i class="far fa-heart fa-fw"></i></a>
  
</header>

    <div class='content pure'>
      
  <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/aplayer@1.7.0/dist/APlayer.min.css">
  <div class="aplayer"
    data-theme="#1BCDFC"
    
    
    data-mode="circulation"
    data-server="netease"
    data-type="playlist"
    data-id="3019271605"
    data-volume="0.7">
  </div>
  <script src="https://cdn.jsdelivr.net/npm/aplayer@1.7.0/dist/APlayer.min.js"></script>
  <script src="https://cdn.jsdelivr.net/npm/meting@1.1.0/dist/Meting.min.js"></script>


    </div>
  </section>


</aside>

<footer id="footer" class="clearfix">
    
    
      <div class="social-wrapper">
        
          
            <a href="https://github.com/TRHX"
              class="social fab fa-github flat-btn"
              target="_blank"
              rel="external nofollow noopener noreferrer">
            </a>
          
        
            <a href="https://itrhx.blog.csdn.net/"
              class="social fab fa-cuttlefish flat-btn"
              target="_blank"
              rel="external nofollow noopener noreferrer">
            </a>
          
        
            <a href="https://www.zhihu.com/people/itrhx"
              class="social fab fa-zhihu flat-btn"
              target="_blank"
              rel="external nofollow noopener noreferrer">
            </a>
          
        
            <a href="mailto:admin@itrhx.com"
              class="social fas fa-envelope flat-btn"
              target="_blank"
              rel="external nofollow noopener noreferrer">
            </a>
          
        
            <a href="http://wpa.qq.com/msgrd?v=3&amp;uin=2273902448&amp;site=qq&amp;menu=yes"
              class="social fab fa-qq flat-btn"
              target="_blank"
              rel="external nofollow noopener noreferrer">
            </a>
          
        
      </div>
    
    <br>
    Copyright <i class="far fa-copyright"></i> 2018-2020
    <a href="https://www.itrhx.com/" target="_blank"> TRHX&#39;S BLOG </a>丨
    <img src="https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.9/images/icp.png" style="width:18px;height:18px;margin-bottom:-2px" alt="ICP">
    <a href="http://www.beian.miit.gov.cn/" target="_blank">鄂ICP备19003281号-4</a>丨
    <img src="https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.9/images/moeicp.png" style="width:18px;height:18px;margin-bottom:-3px" alt="MOE ICP">
    <a href="https://icp.gov.moe/" target="_blank">萌ICP备20202022号</a>丨
    <!-- 网站运行时间 -->
    <span id="timeDate">正在载入...</span><span id="times"><span><i class="fa fa-spinner fa-spin"> </i></span></span>
    <script>
    var now = new Date(); 
    function createtime() {
      var grt= new Date("08/10/2018 17:38:00");//建站时间2018-08-10
      now.setTime(now.getTime()+250); 
      days = (now - grt ) / 1000 / 60 / 60 / 24; dnum = Math.floor(days); 
      hours = (now - grt ) / 1000 / 60 / 60 - (24 * dnum); hnum = Math.floor(hours); 
      if(String(hnum).length ==1 ){hnum = "0" + hnum;} minutes = (now - grt ) / 1000 /60 - (24 * 60 * dnum) - (60 * hnum); 
      mnum = Math.floor(minutes); if(String(mnum).length ==1 ){mnum = "0" + mnum;} 
      seconds = (now - grt ) / 1000 - (24 * 60 * 60 * dnum) - (60 * 60 * hnum) - (60 * mnum); 
      snum = Math.round(seconds); if(String(snum).length ==1 ){snum = "0" + snum;} 
      document.getElementById("timeDate").innerHTML = "本站已运行 "
      document.getElementById("times").innerHTML = dnum +" 天 " + hnum + " 小时 " + mnum + " 分 " + snum + " 秒"; 
      /*document.getElementById("times").style.color="#0056FF";*/
      }
      setInterval("createtime()",250);
    </script>丨
    <!--<a href="/sitemap.xml" target="_blank">站点地图</a>丨-->
    <a href="https://tongji.baidu.com/web/welcome/ico?s=df0bc7c6bdbd80356ba4db429724ccad" target="_blank">百度统计</a>丨
    <script type="text/javascript">var cnzz_protocol = (("https:" == document.location.protocol) ? "https://" : "http://");document.write(unescape("%3Cspan id='cnzz_stat_icon_1275909280'%3E%3C/span%3E%3Cscript src='" + cnzz_protocol + "s23.cnzz.com/z_stat.php%3Fid%3D1275909280%26show%3Dpic' type='text/javascript'%3E%3C/script%3E"));</script><br><br>
    <div class="github-badge">
      <a style="color: #fff" rel="license" href="https://hexo.io/" target="_blank" title="由 Hexo 强力驱动">
      <span class="badge-subject">Powered</span><span class="badge-value bg-blue">Hexo</span></a>
    </div>
    <div class="github-badge">
      <a style="color: #fff" rel="license" href="https://github.com/" target="_blank" title="静态网页托管于 GitHub Pages 和 Coding Pages">
      <span class="badge-subject">Hosted</span><span class="badge-value bg-brightgreen">GitHub & Coding</span></a>
    </div>
    <div class="github-badge">
      <a style="color: #fff" rel="license" href="https://www.aliyun.com/" target="_blank" title="阿里云提供域名相关服务">
      <span class="badge-subject">DNS</span><span class="badge-value bg-blueviolet">Aliyun</span></a>
    </div>
    <div class="github-badge">
      <a style="color: #fff" rel="license" href="https://www.jsdelivr.com/" target="_blank" title="jsDelivr 提供 CDN 加速服务">
      <span class="badge-subject">CDN</span><span class="badge-value bg-orange">jsDelivr</span></a>
    </div>
    <div class="github-badge">
        <a style="color: #fff" rel="license" href="https://xaoxuu.com/wiki/material-x/" target="_blank" title="站点使用 Material X 主题">
      <span class="badge-subject">Theme</span><span class="badge-value bg-blue">Material X</span></a>
    </div>
    <div class="github-badge">
      <a style="color: #fff" rel="license" href="http://creativecommons.org/licenses/by-nc-sa/4.0/" target="_blank" title="本站点采用知识共享署名-非商业性使用-相同方式共享 4.0 国际许可协议进行许可">
      <span class="badge-subject"><i class="fa fa-copyright"></i></span><span class="badge-value bg-lightgrey">BY-NC-SA 4.0</span></a>
    </div>
    <div class="github-badge">
      <a style="color: #fff" rel="license" href="https://996.icu/" target="_blank" title="支持 996.ICU">
      <span class="badge-subject">Link</span><span class="badge-value bg-red">996.ICU</span></a>
    </div>
    <div class="github-badge">
      <span class="badge-subject">UV</span><span class="badge-value bg-orange" id="busuanzi_value_site_uv"></span>
    </div>
    <div class="github-badge">
      <span class="badge-subject">PV</span><span class="badge-value bg-brightgreen" id="busuanzi_value_site_pv"></span>
    </div>
    <div class="github-badge">
      <span class="badge-subject">WordCount</span><span class="badge-value bg-blueviolet">130.6k</span>
    </div>
</footer>


      <script>setLoadingBarProgress(60);</script>
    </div>
    <a class="s-top fas fa-arrow-up fa-fw" href='javascript:void(0)'></a>
  </div>
  <script src="https://cdn.jsdelivr.net/npm/jquery@3.3.1/dist/jquery.min.js"></script>

  <script>
    var GOOGLE_CUSTOM_SEARCH_API_KEY = "";
    var GOOGLE_CUSTOM_SEARCH_ENGINE_ID = "";
    var ALGOLIA_API_KEY = "";
    var ALGOLIA_APP_ID = "";
    var ALGOLIA_INDEX_NAME = "";
    var AZURE_SERVICE_NAME = "";
    var AZURE_INDEX_NAME = "";
    var AZURE_QUERY_KEY = "";
    var BAIDU_API_ID = "";
    var SEARCH_SERVICE = "hexo" || "hexo";
    var ROOT = "/"||"/";
    if(!ROOT.endsWith('/'))ROOT += '/';
  </script>

<script src="//instant.page/1.2.2" type="module" integrity="sha384-2xV8M5griQmzyiY3CDqh1dn4z3llDVqZDqzjzcY+jCBCk/a5fXJmuZ/40JJAPeoU"></script>


  <script async src="https://cdn.jsdelivr.net/npm/scrollreveal@4.0.5/dist/scrollreveal.min.js"></script>
  <script type="text/javascript">
    $(function() {
      const $reveal = $('.reveal');
      if ($reveal.length === 0) return;
      const sr = ScrollReveal({ distance: 0 });
      sr.reveal('.reveal');
    });
  </script>


  <script src="https://cdn.jsdelivr.net/npm/node-waves@0.7.6/dist/waves.min.js"></script>
  <script type="text/javascript">
    $(function() {
      Waves.attach('.flat-btn', ['waves-button']);
      Waves.attach('.float-btn', ['waves-button', 'waves-float']);
      Waves.attach('.float-btn-light', ['waves-button', 'waves-float', 'waves-light']);
      Waves.attach('.flat-box', ['waves-block']);
      Waves.attach('.float-box', ['waves-block', 'waves-float']);
      Waves.attach('.waves-image');
      Waves.init();
    });
  </script>


  <script async src="https://cdn.jsdelivr.net/gh/xaoxuu/cdn-busuanzi@2.3/js/busuanzi.pure.mini.js"></script>


  <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/gitalk@1/dist/gitalk.css">
  <script src="https://cdn.jsdelivr.net/npm/gitalk@1.5.2/dist/gitalk.min.js"></script>
  <script src="https://cdn.bootcss.com/blueimp-md5/2.10.0/js/md5.min.js"></script>
  <script type="text/javascript">
    var gitalk = new Gitalk({
      clientID: "d19a84b9d9a2ddb2c6b9",
      clientSecret: "cec9feae5129a6106edc68ce06d167be8eb06021",
      repo: "trhx.github.io",
      owner: "TRHX",
      admin: "TRHX",
      
        id: md5(location.pathname),      // Ensure uniqueness and length less than 50
      
      distractionFreeMode: false  // Facebook-like distraction free mode
    });
    gitalk.render('gitalk-container');
  </script>


  <script src="https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.1.0/js/app.js"></script>


  <script src="https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.1.0/js/search.js"></script>


<!-- 复制 -->
<script src="https://cdn.jsdelivr.net/npm/clipboard@2/dist/clipboard.min.js"></script>
<script>
  let COPY_SUCCESS = "复制成功";
  let COPY_FAILURE = "复制失败";
  /*页面载入完成后，创建复制按钮*/
  !function (e, t, a) {
    /* code */
    var initCopyCode = function(){
      var copyHtml = '';
      copyHtml += '<button class="btn-copy" data-clipboard-snippet="">';
      copyHtml += '  <i class="fa fa-copy"></i><span>复制</span>';
      copyHtml += '</button>';
      $(".highlight .code pre").before(copyHtml);
      var clipboard = new ClipboardJS('.btn-copy', {
        target: function(trigger) {
          return trigger.nextElementSibling;
        }
      });

      clipboard.on('success', function(e) {
        //您可以加入成功提示
        console.info('Action:', e.action);
        console.info('Text:', e.text);
        console.info('Trigger:', e.trigger);
        success_prompt(COPY_SUCCESS);
        e.clearSelection();
      });
      clipboard.on('error', function(e) {
        //您可以加入失败提示
        console.error('Action:', e.action);
        console.error('Trigger:', e.trigger);
        fail_prompt(COPY_FAILURE);
      });
    }
    initCopyCode();

  }(window, document);

  /**
   * 弹出式提示框，默认1.5秒自动消失
   * @param message 提示信息
   * @param style 提示样式，有alert-success、alert-danger、alert-warning、alert-info
   * @param time 消失时间
   */
  var prompt = function (message, style, time)
  {
      style = (style === undefined) ? 'alert-success' : style;
      time = (time === undefined) ? 1500 : time*1000;
      $('<div>')
          .appendTo('body')
          .addClass('alert ' + style)
          .html(message)
          .show()
          .delay(time)
          .fadeOut();
  };

  // 成功提示
  var success_prompt = function(message, time)
  {
      prompt(message, 'alert-success', time);
  };

  // 失败提示
  var fail_prompt = function(message, time)
  {
      prompt(message, 'alert-danger', time);
  };

  // 提醒
  var warning_prompt = function(message, time)
  {
      prompt(message, 'alert-warning', time);
  };

  // 信息提示
  var info_prompt = function(message, time)
  {
      prompt(message, 'alert-info', time);
  };

</script>


<!-- fancybox -->
<script src="https://cdn.jsdelivr.net/gh/fancyapps/fancybox@3.5.7/dist/jquery.fancybox.min.js"></script>
<script>
  let LAZY_LOAD_IMAGE = "";
  $(".article-entry").find("fancybox").find("img").each(function () {
      var element = document.createElement("a");
      $(element).attr("data-fancybox", "gallery");
      $(element).attr("href", $(this).attr("src"));
      /* 图片采用懒加载处理时,
       * 一般图片标签内会有个属性名来存放图片的真实地址，比如 data-original,
       * 那么此处将原本的属性名src替换为对应属性名data-original,
       * 修改如下
       */
       if (LAZY_LOAD_IMAGE) {
         $(element).attr("href", $(this).attr("data-original"));
       }
      $(this).wrap(element);
  });
</script>


  <script>setLoadingBarProgress(100);</script>
  <!-- 单击显示文字 -->
  <!-- <script type="text/javascript" src="https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.8/js/ClickShowText.js"></script> -->
  <!-- 点击冒点 -->
  <canvas width="1777" height="841" style="position: fixed; left: 0px; top: 0px; z-index: 2147483647; pointer-events: none;"></canvas><script src="https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.8/js/maodian.js"></script>
  <!-- 浏览器搞笑标题 -->
  <script type="text/javascript" src="https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.8/js/FunnyTitle.js"></script>
  <!-- 样式一（鼠标点击更换样式） -->
  <!--<script src="https://g.joyinshare.com/hc/ribbon.min.js" type="text/javascript"></script>-->
  <!-- 样式二（飘动的彩带） -->
  <!--<script src="https://g.joyinshare.com/hc/piao.js" type="text/javascript"></script>-->
  <!-- 数字雨 -->
  <canvas id="canvas" width="1920" height="1080"></canvas>
  <script type="text/javascript" src="https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.8/js/DigitalRain.js"></script>
  <!--动态线条背景-->
  <!--<script type="text/javascript" color="27,195,251" opacity='0.7' zIndex="-5" count="200" src="//cdn.bootcss.com/canvas-nest.js/1.0.0/canvas-nest.min.js"></script>-->
  <!-- 速度优化脚本 -->
  <script src="https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.8/js/instantclick-1.2.2.js" type="module"></script>
  <!-- 悟空 -->
  <!--<div id="wukong"><marquee direction="right"><img src="https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.8/images/wukong.gif"></marquee></div>-->
  <!-- 雪花 -->
  <!--<script src="https://cdn.jsdelivr.net/gh/TRHX/CDN-for-itrhx.com@3.0.8/js/snow1.js"></script> -->
</body>
</html>