过滤HTML tag,提取HTML正文
绝对是非常非常有用的东西~~~!!!
这是数据挖掘的研究范围,要做到横完善,还有横长的路要走。目前微软亚洲研究院,由相关课题。
但是,如果HTML文件结构比较简单,那么完全可以尝试使用网络上已有正则表达式过滤法,基本能达到你需要的效果。
下面贴出关键代码:
……
using System.Text.RegularExpressions;
……
public static string StripHTML(string strHtml)
{
string [] aryReg ={
@"<script[^>]*?>.*?</script>",
{
string [] aryReg ={
@"<script[^>]*?>.*?</script>",
@"<(/s*)?!?((w+:)?w+)(w+(s*=?s*(([""’])([""’tbnr]|[^7])*?7|w+)|.{0})|s)*?(/s*)?>",
@"([rn])[s]+",
@"&(quot|#34);",
@"&(amp|#38);",
@"&(lt|#60);",
@"&(gt|#62);",
@"&(nbsp|#160);",
@"&(iexcl|#161);",
@"&(cent|#162);",
@"&(pound|#163);",
@"&(copy|#169);",
@"&#(d+);",
@"–>",
@"<!–.*n"
};
@"([rn])[s]+",
@"&(quot|#34);",
@"&(amp|#38);",
@"&(lt|#60);",
@"&(gt|#62);",
@"&(nbsp|#160);",
@"&(iexcl|#161);",
@"&(cent|#162);",
@"&(pound|#163);",
@"&(copy|#169);",
@"&#(d+);",
@"–>",
@"<!–.*n"
};
string [] aryRep = {
"",
"",
"",
""",
"&",
"<",
">",
" ",
"xa1",//chr(161),
"xa2",//chr(162),
"xa3",//chr(163),
"xa9",//chr(169),
"",
"rn",
""
};
"",
"",
"",
""",
"&",
"<",
">",
" ",
"xa1",//chr(161),
"xa2",//chr(162),
"xa3",//chr(163),
"xa9",//chr(169),
"",
"rn",
""
};
string newReg =aryReg[0];
string strOutput=strHtml;
for(int i = 0;i<aryReg.Length;i++)
{
Regex regex = new Regex(aryReg[i],RegexOptions.IgnoreCase );
strOutput = regex.Replace(strOutput,aryRep[i]);
}
string strOutput=strHtml;
for(int i = 0;i<aryReg.Length;i++)
{
Regex regex = new Regex(aryReg[i],RegexOptions.IgnoreCase );
strOutput = regex.Replace(strOutput,aryRep[i]);
}
strOutput.Replace("<","");
strOutput.Replace(">","");
strOutput.Replace("rn","");
strOutput.Replace(">","");
strOutput.Replace("rn","");
return strOutput;
}
}
……