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-442760.htm" class="s-card"> <div class="s-card-l"> <p class="tit">幻想生活i飞空艇坐骑如何获取</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-07-04</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250704/logo_686729d0afe551.jpg" alt="幻想生活i飞空艇坐骑如何获取" /> </div> </a> </li> <li> <a href="/art-344920.htm" class="s-card"> <div class="s-card-l"> <p class="tit">PS图片怎么打散? ps制作碎片图片效果的教程</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-07-04</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20230816/logo_64dc9f917f65c1.jpg" alt="PS图片怎么打散? ps制作碎片图片效果的教程" /> </div> </a> </li> <li> <a href="/art-441962.htm" class="s-card"> <div class="s-card-l"> <p class="tit">全解析:加密货币交易者的5种退场策略</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-07-04</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250701/logo_6863b567e946c1.png" alt="全解析:加密货币交易者的5种退场策略" /> </div> </a> </li> <li> <a href="/art-442761.htm" class="s-card"> <div class="s-card-l"> <p class="tit">炉石传说火凤凰尤朵拉贼卡组构筑指南</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-07-04</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250704/logo_686729d145f5b1.jpg" alt="炉石传说火凤凰尤朵拉贼卡组构筑指南" /> </div> </a> </li> <li> <a href="/art-344547.htm" class="s-card"> <div class="s-card-l"> <p class="tit">JSP静态导入与动态导入使用详解</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-07-04</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20230816/logo_64dc98f6341571.jpg" alt="JSP静态导入与动态导入使用详解" /> </div> </a> </li> <li> <a href="/art-441975.htm" class="s-card"> <div class="s-card-l"> <p class="tit">一文盘点2025年最佳的6个SocialFi 项目</p> <div class="info"> <span class="person">游戏攻略</span> <span class="time">2025-07-04</span> </div> </div> <div class="s-card-pic"> <img src="/images/lazy.gif" data-src="/uploads/20250701/logo_6863b57029ae41.png" alt="一文盘点2025年最佳的6个SocialFi 项目" /> </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/118133.htm" target="_self" class="figure"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250701/logo_6863432ccba171.png" alt="蛆虫进化" /> </div> <p class="figure-head">蛆虫进化</p> <span class="figure-btn">下载</span> </a> </li> <li class="card3"> <a href="/app/119582.htm" target="_self" class="figure"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250703/logo_68662af9570221.jpg" alt="一个大魔王" /> </div> <p class="figure-head">一个大魔王</p> <span class="figure-btn">下载</span> </a> </li> <li class="card3"> <a href="/app/119583.htm" target="_self" class="figure"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250703/logo_68662afab08041.jpg" alt="减压火柴人" /> </div> <p class="figure-head">减压火柴人</p> <span class="figure-btn">下载</span> </a> </li> <li class="card3"> <a href="/app/119589.htm" target="_self" class="figure"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250703/logo_68662b05ca4bd1.jpg" alt="大圣取经路" /> </div> <p class="figure-head">大圣取经路</p> <span class="figure-btn">下载</span> </a> </li> </ul> <ul class="card-box-b"> <li class="card10"> <a href="/app/118113.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250701/logo_686342f5124db1.png" alt="挖矿大亨模拟器" /> </div> <div class="figure-cont"> <p class="figure-head">挖矿大亨模拟器</p> <div class="figure-desc"> <span>模拟经营</span> <span>挖矿大亨模拟器</span> </div> <div class="figure-desc"> <p>挖矿大亨模拟器让你扛起探测器开始寻宝冒险!跟着信号一点点挖掘</p> </div> </div> <span class="figure-btn">下载</span> </a> </li> <li class="card10"> <a href="/app/119585.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250703/logo_68662afd528fe1.jpg" alt="沙威餐传奇" /> </div> <div class="figure-cont"> <p class="figure-head">沙威餐传奇</p> <div class="figure-desc"> <span>模拟经营</span> <span>沙威餐传奇</span> </div> <div class="figure-desc"> <p>沙威餐传奇这个游戏挺有意思,让你当个哪吒主题餐厅的老板。每天</p> </div> </div> <span class="figure-btn">下载</span> </a> </li> <li class="card10"> <a href="/app/119591.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250703/logo_68662b093d8cf1.jpg" alt="鉴车大师" /> </div> <div class="figure-cont"> <p class="figure-head">鉴车大师</p> <div class="figure-desc"> <span>模拟经营</span> <span>鉴车大师</span> </div> <div class="figure-desc"> <p>鉴车大师让你体验当二手车商的乐趣。开局就个小车行,靠倒卖旧车</p> </div> </div> <span class="figure-btn">下载</span> </a> </li> <li class="card10"> <a href="/app/119593.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250703/logo_68662b0c7d5d81.jpg" alt="真香夜市摊" /> </div> <div class="figure-cont"> <p class="figure-head">真香夜市摊</p> <div class="figure-desc"> <span>模拟经营</span> <span>真香夜市摊</span> </div> <div class="figure-desc"> <p>真香夜市摊让你当个夜市小吃摊老板,从零开始搞自己的美食小摊。</p> </div> </div> <span class="figure-btn">下载</span> </a> </li> <li class="card10"> <a href="/app/119595.htm" target="_self" class="figure2"> <div class="figure-box"> <img src="/images/lazy.gif" data-src="https://img.111cn.net/uploads/20250703/logo_68662b0f55cbe1.jpg" alt="赶海生活日记" /> </div> <div class="figure-cont"> <p class="figure-head">赶海生活日记</p> <div class="figure-desc"> <span>模拟经营</span> <span>赶海生活日记</span> </div> <div class="figure-desc"> <p>赶海生活日记让你体验海边捡宝的乐趣。每天潮水退了就去沙滩翻找</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>