C#.Net基于正则表达式抓取百度百家文章列表的方法示例

作者:袖梨 2022-06-25

工作之余,学习了一下正则表达式,鉴于实践是检验真理的唯一标准,于是便写了一个利用正则表达式抓取百度百家文章的例子,具体过程请看下面源码:

一、获取百度百家网页内容

publicList GetUrl()
{
  try
  {
    stringurl ="http://baijia.baidu.com/";
    WebRequest webRequest = WebRequest.Create(url);
    WebResponse webResponse = webRequest.GetResponse();
    StreamReader reader =newStreamReader(webResponse.GetResponseStream());
    stringresult = reader.ReadToEnd();
    reader.Close();
    webResponse.Close();
    returnAnalysisHtml(result);
  }
  catch(Exception ex)
  {
    throwex;
  }
}

二、通过正则表达式筛选

publicList AnalysisHtml(stringhtmlContent)
{
  List list =newList();
  stringstrPattern ="

(?[^<]+)</a></h3>.*s*<ps*class="feeds-item-text">(?<Abstract>[^<]+)<as*href="(?<Url>.*)"s*target="_blank"s*class="feeds-item-more"s*mon=".*s*">.*s*</a></p>"; Regex regex =newRegex(strPattern, RegexOptions.IgnoreCase | RegexOptions.Multiline | RegexOptions.CultureInvariant); if(regex.IsMatch(htmlContent)) { MatchCollection matchCollection = regex.Matches(htmlContent); foreach(Match matchinmatchCollection) { string[] str =newstring[3]; str[0] = match.Groups[1].Value;//获取到的是列表数据的标题 str[1] = match.Groups[2].Value;//获取到的是内容 str[2] = match.Groups[3].Value;//获取到的是链接到的地址 list.Add(str); } } returnlist; }</pre> </div> </div> </div> </div> </section> <section class="wrap-box"> <div class="g-tit"> <h2>相关文章</h2> </div> <ul class="s-list nobord notop"> <li> <a href="/art-450122.htm" class="s-card"> <div class="s-card-l"> <p class="tit">远光84步枪怎么选 步枪选择推荐</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-08-13</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250724/logo_6881afb2b12b91.jpg" alt="远光84步枪怎么选 步枪选择推荐" /> </div> </a> </li> <li> <a href="/art-450123.htm" class="s-card"> <div class="s-card-l"> <p class="tit">远光84桃桃怎么玩 桃桃技能玩法教学</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-08-13</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250724/logo_6881afb3865a11.jpg" alt="远光84桃桃怎么玩 桃桃技能玩法教学" /> </div> </a> </li> <li> <a href="/art-450124.htm" class="s-card"> <div class="s-card-l"> <p class="tit">星痕共鸣怎么漂浮 漂浮操作方法</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-08-13</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250724/logo_6881afb4084921.png" alt="星痕共鸣怎么漂浮 漂浮操作方法" /> </div> </a> </li> <li> <a href="/art-450125.htm" class="s-card"> <div class="s-card-l"> <p class="tit">绝区零爱丽丝什么时候出 爱丽丝卡池时间一览</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-08-13</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250724/logo_6881afb4d1b391.jpg" alt="绝区零爱丽丝什么时候出 爱丽丝卡池时间一览" /> </div> </a> </li> <li> <a href="/art-450126.htm" class="s-card"> <div class="s-card-l"> <p class="tit">原神6.0新角色立绘 6.0新角色爆料介绍</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-08-13</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250724/logo_6881afb519ca31.jpg" alt="原神6.0新角色立绘 6.0新角色爆料介绍" /> </div> </a> </li> <li> <a href="/art-450127.htm" class="s-card"> <div class="s-card-l"> <p class="tit">七日世界自动拾取怎么设置 自动拾取开启方法</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-08-13</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250724/logo_6881afb620d821.png" alt="七日世界自动拾取怎么设置 自动拾取开启方法" /> </div> </a> </li> </ul> </section> <section class="wrap-box"> <div class="g-tit"> <h2>精彩推荐</h2> </div> <ul class="card-box"> <li class="card3"> <a href="/app/125959.htm" target="_self" class="figure"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250722/logo_687ef204d4e3e1.png" alt="趣玩解压乐园" /> </div> <p class="figure-head">趣玩解压乐园</p> <span class="figure-btn">下载</span> </a> </li> <li class="card3"> <a href="/app/133730.htm" target="_self" class="figure"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250813/logo_689bf2e656aef1.jpg" alt="无敌宝贝" /> </div> <p class="figure-head">无敌宝贝</p> <span class="figure-btn">下载</span> </a> </li> <li class="card3"> <a href="/app/130723.htm" target="_self" class="figure"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250805/logo_689166f5ace081.jpg" alt="超能小特工" /> </div> <p class="figure-head">超能小特工</p> <span class="figure-btn">下载</span> </a> </li> <li class="card3"> <a href="/app/127716.htm" target="_self" class="figure"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250728/logo_6886ce00dc15c1.jpg" alt="蜘蛛人大逃亡" /> </div> <p class="figure-head">蜘蛛人大逃亡</p> <span class="figure-btn">下载</span> </a> </li> </ul> <ul class="card-box-b"> <li class="card10"> <a href="/app/133426.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250812/logo_689aa135d93e41.jpg" alt="来个甜甜圈" /> </div> <div class="figure-cont"> <p class="figure-head">来个甜甜圈</p> <div class="figure-desc"> <span>模拟经营</span> <span>来个甜甜圈</span> </div> <div class="figure-desc"> <p>甜甜圈乐园带你体验开甜品店的快乐!开一家自己的小店,从零开始</p> </div> </div> <span class="figure-btn">下载</span> </a> </li> <li class="card10"> <a href="/app/133429.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250812/logo_689aa13b3a9fa1.png" alt="等你来挑战" /> </div> <div class="figure-cont"> <p class="figure-head">等你来挑战</p> <div class="figure-desc"> <span>模拟经营</span> <span>等你来挑战</span> </div> <div class="figure-desc"> <p>等你来挑战带你进入由方块构成的立体世界,泥土、石头、木头等材</p> </div> </div> <span class="figure-btn">下载</span> </a> </li> <li class="card10"> <a href="/app/133438.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250812/logo_689aa149db1dc1.jpg" alt="打工模拟器" /> </div> <div class="figure-cont"> <p class="figure-head">打工模拟器</p> <div class="figure-desc"> <span>模拟经营</span> <span>打工模拟器</span> </div> <div class="figure-desc"> <p>打工模拟器这游戏挺有意思,让你体验超市收银员的日常。不仅要给</p> </div> </div> <span class="figure-btn">下载</span> </a> </li> <li class="card10"> <a href="/app/133446.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250812/logo_689aa156403af1.jpg" alt="快速农场" /> </div> <div class="figure-cont"> <p class="figure-head">快速农场</p> <div class="figure-desc"> <span>模拟经营</span> <span>快速农场</span> </div> <div class="figure-desc"> <p>快速农场玩起来特别省事,不用一直盯着也能经营好农场。任务可以</p> </div> </div> <span class="figure-btn">下载</span> </a> </li> <li class="card10"> <a href="/app/127689.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250728/logo_6886cdd5aca291.jpg" alt="健身点击器2" /> </div> <div class="figure-cont"> <p class="figure-head">健身点击器2</p> <div class="figure-desc"> <span>模拟经营</span> <span>健身点击器2</span> </div> <div class="figure-desc"> <p>健身点击器2这个游戏挺有意思的,主要就是控制做各种锻炼动作。</p> </div> </div> <span class="figure-btn">下载</span> </a> </li> </ul> </section> <footer class="foot"> <a href="/" class="logo-icon"> <img src="/mobile/images/logo2.png" alt="一聚教程网"> </a> <p>Copyright © 2010-2022</p> <p>111cn.net All Rights Reserved</p> </footer> <script> var advData = {"img_fixed_pc_adv":"https:\/\/img.111cn.net\/uploads\/20240509\/663c2e9729f58.jpg","img_fixed_mob_adv":"https:\/\/img.111cn.net\/uploads\/20240509\/663c2e8793225.jpg","url_adv":"http:\/\/shop.hushen.cn\/shop\/c\/baojianpin.html","str_adv":"\u864e\u795e\u5546\u57ce\uff1a\u5173\u7231\u7537\u6027\uff0c\u66f4\u61c2\u7537\u4eba\u3002\u89e3\u51b3\u5927\u4f17\u7684\u7537\u8a00\u4e4b\u9690","img_popup_adv":"https:\/\/img.111cn.net\/uploads\/20240509\/663c2e748238d.png","pc_show_img":"2","pc_show_popup":"2","pc_show_video":"2","mob_show_img":"2","mob_show_popup":"2","mob_show_video":"2","close_adv":"https:\/\/img.111cn.net\/uploads\/20240508\/663b20650801e.png","video_adv":"\/pc\/images\/pc-adv.mp4"}; </script> <script src="/jspc/funcmob.js" type="text/javascript"></script> <!-- Google tag (gtag.js) --> <script async src="https://www.googletagmanager.com/gtag/js?id=G-DSRRGRV1TL"></script> <script> window.dataLayer = window.dataLayer || []; function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); gtag('config', 'G-DSRRGRV1TL'); </script> <div class="back-top" style="display: block;"> <span class="icon-box"> <svg class="icon" viewBox="0 0 1024 1024"> <path d="M213.333333 640h170.666667v256h256v-256h170.666667l-298.666667-341.333333zM170.666667 128h682.666666v85.333333H170.666667z" fill="#0374f3"></path> </svg> </span> </div> </div> <script src="/js/stat.js"></script> </body> </html>