正则表达式 获取网页
在做某个winform获取网页的指定位置内容时，要用到正则表达式，无奈正则不精通啊，，，，发个模版，求大哥吧正则表达式写下，最好来个c#代码，嘻嘻，，，
<tr> <td class="number"> <div class="consumeBizNo"> 2012102800001000310009864627 </div> </td> <td class="time">2012-10-28 20:20:16</td> <td class="info"> <ul> <li class="name"> 支付-139-8215-0805 四川移动50元自动快充 自动充值 移动话... </li> </ul> </td> <td class="amount"> </td> <td class="amount outlay">- 49.80</td> <td class="balance">20.00</td> <td class="from"><ul> <li class="name">支付宝</li> </ul> </td> <td class="detail"> <a href="https://lab.alipay.com/consume/queryTradeDetail.htm?tradeNo=2012102800001000310009864627" target="_blank" seed="detail-link" smartracker="on">查看</a> </td> </tr> <tr class="split"> <td class="number"> <div class="consumeBizNo"> 2012102800000000008046766***09 </div> </td> <td class="time">2012-10-28 20:20:16</td> <td class="info"> <ul> <li class="name"> 充值 </li> <li class="name-no"><span class="ft-gray">交易成功</span></li> </ul> </td> <td class="amount income">49.80</td> <td class="amount"> </td> <td class="balance">69.80</td> <td class="from"><ul> <li class="name">中国农业银行</li> </ul> </td> <td class="detail"> </td> </tr> <tr> <td class="number"> <div class="consumeBizNo"> 2012102000001000310008079726 </div> </td> <td class="time">2012-10-20 10:16:36</td> <td class="info"> <ul> <li class="name"> 支付-182-0038-1757 全国移动50元 JYT自动充值 快速到账... </li> </ul> </td> <td class="amount"> </td> <td class="amount outlay">- 49.55</td> <td class="balance">20.00</td> <td class="from"><ul> <li class="name">支付宝</li> </ul> </td> <td class="detail"> <a href="https://lab.alipay.com/consume/queryTradeDetail.htm?tradeNo=2012102000001000310008079726" target="_blank" seed="detail-linkT1" smartracker="on">查看</a> </td> </tr>
string html = System.IO.File.ReadAllText(@"C:\1.txt", Encoding.GetEncoding("GB2312")); string pattern1 = @"(?is)(?<=<td\s*class=""[^""]*?"">).*?(?=</td>)"; string pattern2 = @"(?is)<(div|ul)[^>]*?>\s*(<li[^>]*?>)?(.*?)(</li>\s*)?</\1>"; List<string> list1 = new List<string>(); List<string> list2 = new List<string>(); foreach (System.Text.RegularExpressions.Match m in System.Text.RegularExpressions.Regex.Matches(html, pattern1)) { list1.Add(m.Value); } string ss = ""; foreach (string l in list1) { if (Regex.IsMatch(l, pattern2)) { ss = Regex.Match(l, pattern2).Groups[3].Value; } else ss = l; list2.Add(ss); } list2.ForEach(x => Console.WriteLine(x));
[解决办法]
这儿有两个方法。。你可以试试。 全部封装好了。不用导入任何东西。直接拷进去引用就行了
public static string NoHTML(string Htmlstring)
{
//删除脚本
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
//删除HTML
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"<(.[^>]*)>", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"-->", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"<!--.*", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(quot|#34);", "\"", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(amp|#38);", "&", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(lt|#60);", "<", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(gt|#62);", ">", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(nbsp|#160);", " ", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(iexcl|#161);", "\xa1", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(cent|#162);", "\xa2", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(pound|#163);", "\xa3", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(copy|#169);", "\xa9", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&#(\d+);", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring.Replace("<", "");
Htmlstring.Replace(">", "");
Htmlstring.Replace("\r\n", "");
Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
return Htmlstring;
}
public string StripHTML(string strHtml)
{
string[] aryReg ={
@"<script[^>]*?>.*?</script>",
@"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(file://[""'tbnr]|[^/7])*?/7|/w+)|.{0})|/s)*?(///s*)?>",
@"([\r\n])[\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),
"",
"\r\n",
""
};
string newReg = aryReg[0];
string strOutput = strHtml;
for (int i = 0; i < aryReg.Length; i++)
{
System.Text.RegularExpressions.Regex regex = new System.Text.RegularExpressions.Regex(aryReg[i], System.Text.RegularExpressions.RegexOptions.IgnoreCase);
strOutput = regex.Replace(strOutput, aryRep[i]);
}
strOutput.Replace("<", "");
strOutput.Replace(">", "");
strOutput.Replace("\r\n", "");
return strOutput;
}