c# 正则表达式对网页进行内容抓取

原文 c# 正则表达式对网页进行内容抓取

搜索引擎中一个比较重要的环节就是从网页中抽取出有效内容。简单来说，就是吧HTML文本中的HTML标记去掉,留下我们用IE等浏览器打开HTML文档看到的部分（我们这里不考虑图片）.

将HTML文本中的标记分为:注释,script ,style，以及其他标记分别去掉： 

1.去注释,正则为: 

output = Regex.Replace(input, @"<!--[^-]*-->", string.Empty, RegexOptions.IgnoreCase); 

2.去script,正则为: 

ouput = Regex.Replace(input, @"<script[^>]*?>.*?</script>", string.Empty, RegexOptions.IgnoreCase | RegexOptions.Singleline); 

output2 = Regex.Replace(ouput , @"<noscript[^>]*?>.*?</noscript>", string.Empty, RegexOptions.IgnoreCase | RegexOptions.Singleline); 

3.去style,正则为: 

output = Regex.Replace(input, @"<style[^>]*?>.*?</style>", string.Empty, RegexOptions.IgnoreCase | RegexOptions.Singleline); 

4.去其他HTML标记 

result = result.Replace(" ", " "); 

result = result.Replace(""", "\""); 

result = result.Replace("<", "<"); 

result = result.Replace(">", ">"); 

result = result.Replace("&", "&"); 

result = result.Replace("<br>", "\r\n"); 

result = Regex.Replace(result, @"<[\s\S]*?>", string.Empty, RegexOptions.IgnoreCase); 

以上的代码中大家可以看到,我使用了RegexOptions.Singleline参数，这个参数很重要，他主要是为了让"."(小圆点)可以匹配换行符.如果没有这个参数，大多数情况下，用上面列正则表达式来消除网页HTML标记是无效的. 

HTML发展至今，语法已经相当复杂,上面只列出了几种最主要的标记,更多的去HTML标记的正则我将在 

Rost WebSpider 的开发过程中补充进来。 

下面用c#实现了一个从HTML字符串中提取有效内容的类: 

using System; 

using System.Collections.Generic; 

using System.Text; 

using System.Text.RegularExpressions; 

class HtmlExtract 

{ 

#region private attributes 

private string _strHtml; 

#endregion 

#region public mehtods 

public HtmlExtract(string inStrHtml) 

{ 

_strHtml = inStrHtml 

} 

public override string ExtractText() 

{ 

string result = _strHtml; 

result = RemoveComment(result); 

result = RemoveScript(result); 

result = RemoveStyle(result); 

result = RemoveTags(result); 

return result.Trim(); 

} 

#endregion 

#region private methods 

private string RemoveComment(string input) 

{ 

string result = input; 

//remove comment 

result = Regex.Replace(result, @"<!--[^-]*-->", string.Empty, RegexOptions.IgnoreCase); 

return result; 

} 

private string RemoveStyle(string input) 

{ 

string result = input; 

//remove all styles 

result = Regex.Replace(result, @"<style[^>]*?>.*?</style>", string.Empty, RegexOptions.IgnoreCase | RegexOptions.Singleline); 

return result; 

} 

private string RemoveScript(string input) 

{ 

string result = input; 

result = Regex.Replace(result, @"<script[^>]*?>.*?</script>", string.Empty, RegexOptions.IgnoreCase | RegexOptions.Singleline); 

result = Regex.Replace(result, @"<noscript[^>]*?>.*?</noscript>", string.Empty, RegexOptions.IgnoreCase | RegexOptions.Singleline); 

return result; 

} 

private string RemoveTags(string input) 

{ 

string result = input; 

result = result.Replace(" ", " "); 

result = result.Replace(""", "\""); 

result = result.Replace("<", "<"); 

result = result.Replace(">", ">"); 

result = result.Replace("&", "&"); 

result = result.Replace("<br>", "\r\n"); 

result = Regex.Replace(result, @"<[\s\S]*?>", string.Empty, RegexOptions.IgnoreCase); 

return result; 

} 

#endregion