1 /// <summary>
2 /// 取得内容中所有匹配的 Email地址。
3 /// </summary>
4 /// <param name="sHtmlText">内容</param>
5 /// <returns>匹配列表</returns>
6 public static string[] GetContentList(string sHtmlText)
7 {
8 //string pattern = @"<div class=[^<>]+>(?<imgUrl>[^<>]+)</div>";
9 //邮箱匹配正则
10 string pattern = @"(?<Email>(?("")(""[^""]+?""@)|(([0-9a-z]((\.(?!\.))|[-!#\$%&'\*\+/=\?\^`\{\}\|~\w])*)(?<=[0-9a-z])@))(?(\[)(\[(\d{1,3}\.){3}\d{1,3}\])|(([0-9a-z][-\w]*[0-9a-z]*\.)+[a-z0-9]{2,17})))";
11 Regex regImg = new Regex(pattern, RegexOptions.IgnoreCase);
12 // 搜索匹配的字符串
13 MatchCollection matches = regImg.Matches(sHtmlText);
14 int i = 0;
15 string[] sUrlList = new string[matches.Count];
16 // 取得匹配项列表
17 foreach (Match match in matches)
18 sUrlList[i++] = match.Groups["Email"].Value;
19 return sUrlList;
20 }
//获取网页内容 传递url地址
private string GetWebRequest(string url)
{
WebRequest request = WebRequest.Create(url);
WebResponse response = request.GetResponse();
Stream resstream = response.GetResponseStream();
StreamReader srbname = new StreamReader(resstream, System.Text.Encoding.GetEncoding("UTF-8"));
return srbname.ReadToEnd();
}
