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-456707.htm" class="s-card"> <div class="s-card-l"> <p class="tit">光遇双星季季节任务三完成攻略</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-09-07</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250814/logo_689d4c5b872041.png" alt="光遇双星季季节任务三完成攻略" /> </div> </a> </li> <li> <a href="/art-456708.htm" class="s-card"> <div class="s-card-l"> <p class="tit">鸣潮奥古斯塔技能爆料介绍</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-09-07</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250814/logo_689d4c5c2d56d1.jpg" alt="鸣潮奥古斯塔技能爆料介绍" /> </div> </a> </li> <li> <a href="/art-456709.htm" class="s-card"> <div class="s-card-l"> <p class="tit">鸣潮尤诺技能爆料介绍一览</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-09-07</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250814/logo_689d4c5c8b68c1.jpg" alt="鸣潮尤诺技能爆料介绍一览" /> </div> </a> </li> <li> <a href="/art-456710.htm" class="s-card"> <div class="s-card-l"> <p class="tit">阴阳师魔卡少女樱联动兑换码分享</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-09-07</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250814/logo_689d4c5d2b1941.jpg" alt="阴阳师魔卡少女樱联动兑换码分享" /> </div> </a> </li> <li> <a href="/art-456711.htm" class="s-card"> <div class="s-card-l"> <p class="tit">诛仙2新团本万蝠古窟副本打法攻略</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-09-07</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250814/logo_689d4c5e077e71.png" alt="诛仙2新团本万蝠古窟副本打法攻略" /> </div> </a> </li> <li> <a href="/art-456712.htm" class="s-card"> <div class="s-card-l"> <p class="tit">三国天下归心三分弓队阵容玩法教学</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-09-07</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250814/logo_689d4c5ed5e9f1.jpg" alt="三国天下归心三分弓队阵容玩法教学" /> </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/118587.htm" target="_self" class="figure"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250702/logo_68649348ce1451.png" alt="火柴人大挑战" /> </div> <p class="figure-head">火柴人大挑战</p> <span class="figure-btn">下载</span> </a> </li> <li class="card3"> <a href="/app/120195.htm" target="_self" class="figure"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250707/logo_686b1ef33fe091.jpg" alt="刺激天命圈" /> </div> <p class="figure-head">刺激天命圈</p> <span class="figure-btn">下载</span> </a> </li> <li class="card3"> <a href="/app/120215.htm" target="_self" class="figure"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250707/logo_686b1f04197c11.jpg" alt="火柴人超凡英雄" /> </div> <p class="figure-head">火柴人超凡英雄</p> <span class="figure-btn">下载</span> </a> </li> <li class="card3"> <a href="/app/120229.htm" target="_self" class="figure"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250707/logo_686b1f0f044bc1.png" alt="梗住我了" /> </div> <p class="figure-head">梗住我了</p> <span class="figure-btn">下载</span> </a> </li> </ul> <ul class="card-box-b"> <li class="card10"> <a href="/app/121844.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250710/logo_686f1f77cf77a1.png" alt="天才小当家" /> </div> <div class="figure-cont"> <p class="figure-head">天才小当家</p> <div class="figure-desc"> <span>模拟经营</span> <span>天才小当家</span> </div> <div class="figure-desc"> <p>天才小当家带你体验便利店老板的一天,玩家必须灵活处理货架陈列</p> </div> </div> <span class="figure-btn">下载</span> </a> </li> <li class="card10"> <a href="/app/123111.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250714/logo_68745a940ad6b1.png" alt="绝境孤岛" /> </div> <div class="figure-cont"> <p class="figure-head">绝境孤岛</p> <div class="figure-desc"> <span>模拟经营</span> <span>绝境孤岛</span> </div> <div class="figure-desc"> <p>绝境孤岛带你体验最硬核的荒岛求生挑战,白天搜集食物木材维持基</p> </div> </div> <span class="figure-btn">下载</span> </a> </li> <li class="card10"> <a href="/app/123119.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250714/logo_68745a9891d521.png" alt="我是小小警察" /> </div> <div class="figure-cont"> <p class="figure-head">我是小小警察</p> <div class="figure-desc"> <span>模拟经营</span> <span>我是小小警察</span> </div> <div class="figure-desc"> <p>我是小小警察带你体验守护城市的热血日常,执行任务、追捕坏人,</p> </div> </div> <span class="figure-btn">下载</span> </a> </li> <li class="card10"> <a href="/app/123169.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250714/logo_68745ab8e64a41.png" alt="有一家餐厅" /> </div> <div class="figure-cont"> <p class="figure-head">有一家餐厅</p> <div class="figure-desc"> <span>模拟经营</span> <span>有一家餐厅</span> </div> <div class="figure-desc"> <p>有一家餐厅带你体验真实又忙碌的店长日常,从进货上架到招呼客人</p> </div> </div> <span class="figure-btn">下载</span> </a> </li> <li class="card10"> <a href="/app/125302.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250721/logo_687d93238588f1.png" alt="像素生存逃生模拟" /> </div> <div class="figure-cont"> <p class="figure-head">像素生存逃生模拟</p> <div class="figure-desc"> <span>模拟经营</span> <span>像素生存逃生模拟</span> </div> <div class="figure-desc"> <p>像素生存逃生模拟让人彻底沉浸在像素荒野的紧张冒险里。玩家需要</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>