正则问题_如何分别获取以下的link和中文标题

如果这样写，仅对单个有效，整体就不行了http://(?<port1>.+)?.+?target=_blank>(?<port2>.+)?

解决方案 »

免费领取超大流量手机卡，每月29元包185G流量+100分钟通话, 中国电信官方发货

存成.asp文件，执行，你用ASPHTTP抓内容的时候用这个很爽，当然自己要改进一下了<%
Option ExplicitFunction stripHTML(strHTML)
'Strips the HTML tags from strHTMLDim objRegExp, strOutput
Set objRegExp = New RegexpobjRegExp.IgnoreCase = True
objRegExp.Global = True
objRegExp.Pattern = "<.+?>"'Replace all HTML tag matches with the empty string
strOutput = objRegExp.Replace(strHTML, "")'Replace all < and > with < and >
strOutput = Replace(strOutput, "<", "<")
strOutput = Replace(strOutput, ">", ">")stripHTML = strOutput 'Return the value of strOutputSet objRegExp = Nothing
End Function
%><form method="post" id=form1 name=form1>
Enter an HTML String: 
<textarea name="txtHTML" cols="50" rows="8" wrap="virtual"><%=Request("txtHTML")%></textarea>

<input type="submit" value="Strip HTML Tags!" id=submit1 name=submit1>
</form><% if Len(Request("txtHTML")) > 0 then %>
<hr>
View of string with no HTML stripping: 
<xmp>
<%=Request("txtHTML")%>
</xmp>
View of string with HTML stripping: 
<pre>
<%=StripHTML(Request("txtHTML"))%>
</pre>
<% End If %>
Dim Titlehtml As String = "<tr><td width=5% height=19 align=center>·</td><td class=title14 height=20><a href= http://news1.jrj.com.cn/news/2005-01-19/000000999424.html target=_blank>项怀诚称社保基金境外投资首选港暂无时间表</a></td><td align=right class=title14>1月19日 15:43</td></tr><tr><td width=5% height=19 align=center>·</td><td class=title14 height=20><a href= http://news1.jrj.com.cn/news/2005-01-19/000000999413.html target=_blank>外汇储备高企年内有望注资工农二行启动股改</a>★</td><td align=right class=title14>1月19日 15:37</td></tr><tr><td width=5% height=19 align=center>·</td><td class=title14 height=20><a href= http://news1.jrj.com.cn/news/2005-01-19/000000999383.html target=_blank>证监会李青原表示:希望年内解决股权分置问题</a></td><td align=right class=title14>1月19日 15:16</td></tr><tr><td width=5% height=19 align=center>·</td><td class=title14 height=20><a href= http://news1.jrj.com.cn/news/2005-01-19/000000999105.html target=_blank>四大保障基金渐行渐近投资人须树立风险意识</a></td><td align=right class=title14>1月19日 09:46</td></tr><tr><td width=5% height=19 align=center>·</td><td class=title14 height=20>" Dim re As System.Text.RegularExpressions.Regex = New System.Text.RegularExpressions.Regex("<a href=\s*http://(?<url>[^\s]*?)\s+target=_blank>[\s\S]*?(?<title>[\s\S]*?)[\s\S]*?</a>", Text.RegularExpressions.RegexOptions.IgnoreCase And Text.RegularExpressions.RegexOptions.Multiline)
 Dim i As Integer = 1
 For Each mm As System.Text.RegularExpressions.Match In re.Matches(Titlehtml) Console.WriteLine("a" & i.ToString & "=" & mm.Groups("url").Value)
 Console.WriteLine("b" & i.ToString & "=" & mm.Groups("title").Value)
 i += 1
 Next
结果：
a1=news1.jrj.com.cn/news/2005-01-19/000000999424.html
b1=项怀诚称社保基金境外投资首选港暂无时间表
a2=news1.jrj.com.cn/news/2005-01-19/000000999413.html
b2=外汇储备高企年内有望注资工农二行启动股改
a3=news1.jrj.com.cn/news/2005-01-19/000000999383.html
b3=证监会李青原表示:希望年内解决股权分置问题
a4=news1.jrj.com.cn/news/2005-01-19/000000999105.html
b4=四大保障基金渐行渐近投资人须树立风险意识
正则：
<a href=\s*http://(?<url>[^\s]*?)\s+target=_blank>[\s\S]*?(?<title>[\s\S]*?)[\s\S]*?</a>
try string s = "........."; Regex re = new Regex(@"<a\s+href\s*=\s*('(?<href>[^']*)'|""(?<href>[^""]*)""|(?<href>[\S>]*))[^>]*>.*?(?<link>[^<]+).*?</a>", RegexOptions.IgnoreCase|RegexOptions.Singleline); foreach (Match m in re.Matches(s))
{
Console.WriteLine("**{0}-----{1}***",m.Groups["href"].Value, m.Groups["link"].Value);
}
saucer(思归) 又抢偶的！5555555555555555
saucer(思归) 来了,我便沉默;