C#.Net基于正則表達(dá)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 = "<h4><a\\s*.*>(?<Title>[^<]+)</a></h4>.*\\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;//獲取到的是列表數(shù)據(jù)的標(biāo)題
      str[1] = match.Groups[2].Value;//獲取到的是內(nèi)容
      str[2] = match.Groups[3].Value;//獲取到的是鏈接到的地址
      list.Add(str);
    }
  }
  return list;
}