python爬取豆瓣影评,涉及知识点:bs4,requests、time、random

页面源代码:


<!DOCTYPE html>
<html lang="zh-CN" class="ua-windows ua-webkit">
<head>
    <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
    <meta name="renderer" content="webkit">
    <meta name="referrer" content="always">
    <meta name="google-site-verification" content="ok0wCgT20tBBgo9_zat2iAcimtN4Ftf5ccsh092Xeyw" />
    <title>
  
  豆瓣最受欢迎的影评
</title>
    
  <meta name="baidu-site-verification" content="cZdR4xxR7RxmM4zE" />
  <meta http-equiv="Pragma" content="no-cache">
  <meta http-equiv="Expires" content="Sun, 6 Mar 2005 01:00:00 GMT">
  
  
  <meta name="keywords" content="影评,热门影评,最新影评"/>
  <meta name="description" content="豆瓣最受欢迎的影评,发表你的影评"/>
  <link rel="alternate" href="/feed/review/best" type="application/rss+xml" title="RSS">

  <link href="https://img1.doubanio.com/f/vendors/02814fbb5bee25484516bd0a642af695f7ec5a83/css/douban.css" rel="stylesheet" type="text/css">
  <link href="https://img1.doubanio.com/f/vendors/ee6598d46af0bc554cecec9bcbf525b9b0582cb0/css/separation/_all.css" rel="stylesheet" type="text/css">
  <link href="https://img1.doubanio.com/f/zerkalo/4b7b75331a86c9c8275ac6b7306e820fc072e09a/css/init.css" rel="stylesheet" type="text/css">
  <link rel="stylesheet" href="https://img1.doubanio.com/misc/mixed_static/610438fbda6eb614.css">
  <style type="text/css"></style>

  <script type="text/javascript">var _head_start = new Date();</script>

  <script type="text/javascript" src="https://img1.doubanio.com/f/vendors/6931d89467c7bd3bb6cd748c05cae22368989aea/js/jquery-1.9.1.min.js"></script>

  <script type="text/javascript" src="https://img1.doubanio.com/f/vendors/aa9559674f2476cdc16f755b3cdc4ebc478db669/js/douban.js"></script>
  <script type="text/javascript" src="https://img1.doubanio.com/f/vendors/e38c65a87555287f5fb7c997e41b908d72ff9731/js/lib/moreurl.js"></script>
  <script type="text/javascript" src="https://img1.doubanio.com/f/vendors/b0d3faaf7a432605add54908e39e17746824d6cc/js/separation/_all.js"></script>
  <script type="text/javascript" src="https://img1.doubanio.com/f/zerkalo/8f98eaec1c9c779076c24b46fe052ee9c2dd52d8/dist/js/base.js"></script>
  <script type="text/javascript"></script>
  


    <link rel="shortcut icon" href="https://img1.doubanio.com/favicon.ico" type="image/x-icon">
</head>

<body>
  
  
  <script type="text/javascript">var _body_start = new Date();</script>

  

    



    <link href="//img3.doubanio.com/dae/accounts/resources/ded47ae/shire/bundle.css" rel="stylesheet" type="text/css">



<div id="db-global-nav" class="global-nav">
  <div class="bd">
    
<div class="top-nav-info">
  <a href="https://accounts.douban.com/passport/login?source=main" class="nav-login" rel="nofollow">登录/注册</a>
</div>


    <div class="top-nav-doubanapp">
  <a href="https://www.douban.com/doubanapp/app?channel=top-nav" class="lnk-doubanapp">下载豆瓣客户端</a>
  <div id="doubanapp-tip">
    <a href="https://www.douban.com/doubanapp/app?channel=qipao" class="tip-link">豆瓣 <span class="version">6.0</span> 全新发布</a>
    <a href="javascript: void 0;" class="tip-close">×</a>
  </div>
  <div id="top-nav-appintro" class="more-items">
    <p class="appintro-title">豆瓣</p>
    <p class="qrcode">扫码直接下载</p>
    <div class="download">
      <a href="https://www.douban.com/doubanapp/redirect?channel=top-nav&direct_dl=1&download=iOS">iPhone</a>
      <span>·</span>
      <a href="https://www.douban.com/doubanapp/redirect?channel=top-nav&direct_dl=1&download=Android" class="download-android">Android</a>
    </div>
  </div>
</div>

    


<div class="global-nav-items">
  <ul>
    <li class="on">
      <a href="https://www.douban.com"  data-moreurl-dict="{&quot;from&quot;:&quot;top-nav-click-main&quot;,&quot;uid&quot;:&quot;0&quot;}">豆瓣</a>
    </li>
    <li class="">
      <a href="https://book.douban.com" target="_blank" data-moreurl-dict="{&quot;from&quot;:&quot;top-nav-click-book&quot;,&quot;uid&quot;:&quot;0&quot;}">读书</a>
    </li>
    <li class="">
      <a href="https://movie.douban.com" target="_blank" data-moreurl-dict="{&quot;from&quot;:&quot;top-nav-click-movie&quot;,&quot;uid&quot;:&quot;0&quot;}">电影</a>
    </li>
    <li class="">
      <a href="https://music.douban.com" target="_blank" data-moreurl-dict="{&quot;from&quot;:&quot;top-nav-click-music&quot;,&quot;uid&quot;:&quot;0&quot;}">音乐</a>
    </li>
    <li class="">
      <a href="https://www.douban.com/location" target="_blank" data-moreurl-dict="{&quot;from&quot;:&quot;top-nav-click-location&quot;,&quot;uid&quot;:&quot;0&quot;}">同城</a>
    </li>
    <li class="">
      <a href="https://www.douban.com/group" target="_blank" data-moreurl-dict="{&quot;from&quot;:&quot;top-nav-click-group&quot;,&quot;uid&quot;:&quot;0&quot;}">小组</a>
    </li>
    <li class="">
      <a href="https://read.douban.com&#47;?dcs=top-nav&amp;dcm=douban" target="_blank" data-moreurl-dict="{&quot;from&quot;:&quot;top-nav-click-read&quot;,&quot;uid&quot;:&quot;0&quot;}">阅读</a>
    </li>
    <li class="">
      <a href="https://fm.douban.com&#47;?from_=shire_top_nav" target="_blank" data-moreurl-dict="{&quot;from&quot;:&quot;top-nav-click-fm&quot;,&quot;uid&quot;:&quot;0&quot;}">FM</a>
    </li>
    <li class="">
      <a href="https://time.douban.com&#47;?dt_time_source=douban-web_top_nav" target="_blank" data-moreurl-dict="{&quot;from&quot;:&quot;top-nav-click-time&quot;,&quot;uid&quot;:&quot;0&quot;}">时间</a>
    </li>
    <li class="">
      <a href="https://market.douban.com&#47;?utm_campaign=douban_top_nav&amp;utm_source=douban&amp;utm_medium=pc_web" target="_blank" data-moreurl-dict="{&quot;from&quot;:&quot;top-nav-click-market&quot;,&quot;uid&quot;:&quot;0&quot;}">豆品</a>
    </li>
  </ul>
</div>

  </div>
</div>
<script>
  ;window._GLOBAL_NAV = {
    DOUBAN_URL: "https://www.douban.com",
    N_NEW_NOTIS: 0,
    N_NEW_DOUMAIL: 0
  };
</script>



    <script src="//img3.doubanio.com/dae/accounts/resources/ded47ae/shire/bundle.js" defer="defer"></script>





      



    <link href="//img3.doubanio.com/dae/accounts/resources/ded47ae/movie/bundle.css" rel="stylesheet" type="text/css">




<div id="db-nav-movie" class="nav">
  <div class="nav-wrap">
  <div class="nav-primary">
    <div class="nav-logo">
      <a href="https:&#47;&#47;movie.douban.com">豆瓣电影</a>
    </div>
    <div class="nav-search">
      <form action="https:&#47;&#47;search.douban.com&#47;movie/subject_search" method="get">
        <fieldset>
          <legend>搜索:</legend>
          <label for="inp-query">
          </label>
          <div class="inp"><input id="inp-query" name="search_text" size="22" maxlength="60" placeholder="搜索电影、电视剧、综艺、影人" value=""></div>
          <div class="inp-btn"><input type="submit" value="搜索"></div>
          <input type="hidden" name="cat" value="1002" />
        </fieldset>
      </form>
    </div>
  </div>
  </div>
  <div class="nav-secondary">
    

<div class="nav-items">
  <ul>
    <li    ><a href="https://movie.douban.com/cinema/nowplaying/"
     >影讯&购票</a>
    </li>
    <li    ><a href="https://movie.douban.com/explore"
     >选电影</a>
    </li>
    <li    ><a href="https://movie.douban.com/tv/"
     >电视剧</a>
    </li>
    <li    ><a href="https://movie.douban.com/chart"
     >排行榜</a>
    </li>
    <li    ><a href="https://movie.douban.com/review/best/"
     >影评</a>
    </li>
    <li    ><a href="https://movie.douban.com/annual/2023/?fullscreen=1&source=navigation"
     >2023年度榜单</a>
    </li>
    <li    ><a href="https://c9.douban.com/app/standbyme-2023/?autorotate=false&fullscreen=true&hidenav=true&monitor_screenshot=true&source=web_navigation"
            target="_blank"
     >2023年度报告</a>
    </li>
  </ul>
</div>

    <a href="https://movie.douban.com/annual/2023/?fullscreen=1&source=movie_navigation" class="movieannual"></a>
  </div>
</div>

<script id="suggResult" type="text/x-jquery-tmpl">
  <li data-link="{
  {= url}}">
            <a href="{
  {= url}}" onclick="moreurl(this, {from:'movie_search_sugg', query:'{
  {= keyword }}', subject_id:'{
  {= id}}', i: '{
  {= index}}', type: '{
  {= type}}'})">
            <img src="{
  {= img}}" width="40" />
            <p>
                <em>{
  {= title}}</em>
                {
  {if year}}
                    <span>{
  {= year}}</span>
                {
  {/if}}
                {
  {if sub_title}}
                    <br /><span>{
  {= sub_title}}</span>
                {
  {/if}}
                {
  {if address}}
                    <br /><span>{
  {= address}}</span>
                {
  {/if}}
                {
  {if episode}}
                    {
  {if episode=="unknow"}}
                        <br /><span>集数未知</span>
                    {
  {else}}
                        <br /><span>共{
  {= episode}}集</span>
                    {
  {/if}}
                {
  {/if}}
            </p>
        </a>
        </li>
  </script>




    <script src="//img3.doubanio.com/dae/accounts/resources/ded47ae/movie/bundle.js" defer="defer"></script>






  
  <div id="wrapper" class="movie-content review-wrapper">
    

    
  <div id="content">
    
    <h1>豆瓣最受欢迎的影评</h1&
  • 6
    点赞
  • 8
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值