正则表达式获取HTML标记中的内容（C#）
//=====================Begin1======================== //试验字符串 string strTmp = string.Empty; //正则表达式 string tmpStr = string.Empty; //取出指定HTML标记中的匹配项的值RegexOptions.IgnoreCase忽略大小写，RegexOptions.Multiline忽略多行显示， //tmpStr = “<title>([^<]*)</title>” //获取<title>之间内容 strTmp = @”<add key=’ConnectionString’ value=’server=localhost;database=数据库名;uid=sa;pwd=;pooling=true’/>“; //获取“database=”与“;”号之间的字符串：database=(.*); tmpStr = “database=([^;]*);“; Match TitleMatch = Regex.Match(strTmp, tmpStr ,RegexOptions.IgnoreCase | RegexOptions.Multiline ); //如下例子作语法参考用获取size的值，实际应用可能不会如此复杂 strTmp = “><font color=’red’ size=6>WebForm3</font><“ ; tmpStr = @”<(w+s+w+[=]+[‘]+w+[‘]+s+[size=]+d)>“; Match TitleMatch = Regex.Match(strTmp ,tmpStr , RegexOptions.IgnoreCase | RegexOptions.Multiline ); //取出匹配项的值 string tmpStrTitle = TitleMatch.Groups[1].Value; //替换掉HTML页中所有HTML标记 Label1.Text=Regex.Replace(Label1.Text.Trim(),“<.+?>“,“”)+“*********“+TitleMatch.Groups[1].Value; //判断匹配正则表达式是否成功 if(Regex.Match(tmpStr,“<.+?>“).Success)
…{
//操作
} //=====================End1======================== //=====================Begin2======================== string webDocContent=“<a href=http://www.xxx.xxx/college/pages/default.htm target=_blank>师资队伍</A>“; //解释下面正则表达式：[s]表示匹配空格字符，”+” 表示连接 string strPattern=@”a[s]+href=(?<Link>[^s>]+)[^>]*>(?<Text>[^<]*)</a>“; //获取链接显示的文字 MatchCollection Matches=Regex.Matches(webDocContent,strPattern,RegexOptions.IgnoreCase|RegexOptions.Compiled); foreach(Match NextMatch in Matches) …{ string URL=NextMatch.Groups[“Link“].Value.ToString().Trim(); string URLText=NextMatch.Groups[“Text“].Value.ToString().Trim(); Response.Write(URL+“****“); Response.Write(URLText); } //=====================End2======================== //=====================Begin3======================== string strPageContent = string.Empty; StreamReader srPage = new StreamReader(@”e:save.txt“,System.Text.Encoding.GetEncoding(“gb2312“)); strPageContent = srPage.ReadToEnd(); srPage.Close(); //(s)*表示0或多个空格符、回车符等，*表示比配0或多个。(.*?)表示除回车符外的所有信息 MatchCollection TitleMatchs = Regex.Matches(strPageContent, “<td width=”85%” class=”common_text”>((s)*(.*?)(s)*(.*?)(s)*(.*?)(s)*(.*?)(s)*)</td>“, RegexOptions.IgnoreCase | RegexOptions.Multiline ); int tmpNum = 0; //循环正则表达式所获取的，满足表达式的内容集合 foreach(Match NextMatch in TitleMatchs) …{ ++tmpNum; Label1.Text += tmpNum + “<br>****“ + NextMatch.Groups[1].Value; } //=====================End3========================