C#中获取以下<a></a>标签中除了标签的所有文本的正则表达式怎么写?急急急!!!
最好把百度搜索链接
<a href="http://www.cnblogs.com/deerchao/archive/2006/08/24/zhengzhe30fengzhongjiaocheng.html" data-tp="kvdb" data-stp="blog" data-st="0" data-e="1" data-pos="4" data-m="52cc105bacc99c4b333c813cec3a0d44" data-extargs='[]' target="_blank"><em>正则表达式</em>30分钟入门教程 - deerchao - 博客园</a>
<a href="http://www.williamlong.info/archives/433.html" data-tp="kvdb" data-stp="blog" data-st="0" data-e="1" data-pos="8" data-m="bca755d9b3ddf06f8e5e1c2691027f97" data-extargs='[]' target="_blank">常用<em>正则表达式</em>-月光博客</a>
<a href="http://tool.chinaz.com/regex" data-tp="kvdb" data-stp="" data-extargs='[]' data-st="0" data-e="1" data-pos="5" data-m="f452b6e878562f4c47867724762ab0fb" target="_blank"><em>正则表达式</em>在线测试 - 站长工具</a>
<a href="http://www.jb51.net/tools/zhengze.html" data-tp="kvdb" data-stp="" data-extargs='[]' data-st="0" data-e="1" data-pos="6" data-m="40b30124ec8426fe4ff25780889ab957" target="_blank"><em>正则表达式</em>30分钟入门教程_脚本之家</a>
public List<Keyword> GetKeywords(string html, string word)
{
#region beifen
int i = 1;
List<Keyword> keywords = new List<Keyword>();
string ss = "<h3 class=\"t\"><a.*?href=\"(?<url>.*?)\".*?>(?<content>.*?)</a>";
MatchCollection mcTable = Regex.Matches(html, ss);
foreach (Match mTable in mcTable)
{
if (mTable.Success)
{
Keyword keyword = new Keyword();
keyword.ID = i++;
keyword.Title = Regex.Replace(mTable.Groups["content"].Value, "<[^>]*>", string.Empty);
keyword.Link = mTable.Groups["url"].Value;
keywords.Add(keyword);
}
}
#endregion
return keywords;
}
------解决方案--------------------
最好把百度搜索链接
<a href="http://www.cnblogs.com/deerchao/archive/2006/08/24/zhengzhe30fengzhongjiaocheng.html" data-tp="kvdb" data-stp="blog" data-st="0" data-e="1" data-pos="4" data-m="52cc105bacc99c4b333c813cec3a0d44" data-extargs='[]' target="_blank"><em>正则表达式</em>30分钟入门教程 - deerchao - 博客园</a>
<a href="http://www.williamlong.info/archives/433.html" data-tp="kvdb" data-stp="blog" data-st="0" data-e="1" data-pos="8" data-m="bca755d9b3ddf06f8e5e1c2691027f97" data-extargs='[]' target="_blank">常用<em>正则表达式</em>-月光博客</a>
<a href="http://tool.chinaz.com/regex" data-tp="kvdb" data-stp="" data-extargs='[]' data-st="0" data-e="1" data-pos="5" data-m="f452b6e878562f4c47867724762ab0fb" target="_blank"><em>正则表达式</em>在线测试 - 站长工具</a>
<a href="http://www.jb51.net/tools/zhengze.html" data-tp="kvdb" data-stp="" data-extargs='[]' data-st="0" data-e="1" data-pos="6" data-m="40b30124ec8426fe4ff25780889ab957" target="_blank"><em>正则表达式</em>30分钟入门教程_脚本之家</a>
public List<Keyword> GetKeywords(string html, string word)
{
#region beifen
int i = 1;
List<Keyword> keywords = new List<Keyword>();
string ss = "<h3 class=\"t\"><a.*?href=\"(?<url>.*?)\".*?>(?<content>.*?)</a>";
MatchCollection mcTable = Regex.Matches(html, ss);
foreach (Match mTable in mcTable)
{
if (mTable.Success)
{
Keyword keyword = new Keyword();
keyword.ID = i++;
keyword.Title = Regex.Replace(mTable.Groups["content"].Value, "<[^>]*>", string.Empty);
keyword.Link = mTable.Groups["url"].Value;
keywords.Add(keyword);
}
}
#endregion
return keywords;
}
------解决方案--------------------
public static string RegStr(string objStr)
{
string returnStr = "";
MatchCollection ml = Regex.Matches(objStr, "<a(?:\\s+.+?)*?\\s+href=\"([^\"]*?)\".*?>(.*?)</a>");
foreach (Match m in ml)
{
string str = m.Value.Replace("</td></tr>", ",");
str = str.Replace("</td>", "");
str = str.Replace(" ", "");
str = Regex.Replace(str, "<.*?>", "");
returnStr += str;
}
return returnStr;
}
string html = "<a href=\"http://www.cnblogs.com/deerchao/archive/2006/08/24/zhengzhe30fengzhongjiaocheng.html\" data-tp=\"kvdb\" data-stp=\"blog\" data-st=\"0\" data-e=\"1\" data-pos=\"4\" data-m=\"52cc105bacc99c4b333c813cec3a0d44\" data-extargs='[]' target=\"_blank\"><em>正则表达式</em>30分钟入门教程 - deerchao - 博客园</a>";