C#.Net基于正则表达式抓取百度百家文章列表的方法示例

public List<string[]> GetUrl(){  try  {    string url = "http://baijia.baidu.com/";    WebRequest webRequest = WebRequest.Create(url);    WebResponse webResponse = webRequest.GetResponse();    StreamReader reader = new StreamReader(webResponse.GetResponseStream());    string result = reader.ReadToEnd();    reader.Close();    webResponse.Close();    return AnalysisHtml(result);  }  catch (Exception ex)  {    throw ex;  }}

public List<string[]> AnalysisHtml(string htmlContent){  List<string[]> list = new List<string[]>();  string strPattern = "<h3><a//s*.*>(?<Title>[^<]+)</a></h3>.*//s*<p//s*class=/"feeds-item-text/">(?<Abstract>[^<]+)<a//s*href=/"(?<Url>.*)/"//s*target=/"_blank/"//s*class=/"feeds-item-more/"//s*mon=/".*//s*/">.*//s*</a></p>";  Regex regex = new Regex(strPattern, RegexOptions.IgnoreCase | RegexOptions.Multiline | RegexOptions.CultureInvariant);  if (regex.IsMatch(htmlContent))  {    MatchCollection matchCollection = regex.Matches(htmlContent);    foreach (Match match in matchCollection)    {      string[] str = new string[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);    }  }  return list;}