110,556
社区成员
发帖
与我相关
我的任务
分享
<tr class="test">
<td>111</td>
</tr>
<tr class="test" style="width:100%;">
<td>
<table>
<tr>
<td>222</td>
</tr>
</table>
</td>
</tr>
<tr class="test" align="center">
<td>333</td>
</tr>
<tr class="test">
<td>444</td>
</tr>
<tr class="test" id="55555">
<td>555555555asd</td>
</tr>
StreamReader sr = new StreamReader(@"C:\temp.html", Encoding.Default);
string HtmlCode = sr.ReadToEnd();
Regex r = new Regex(@"/<tr(.*)/>(.*)/<\/tr/>");
string[] s = r.Split(HtmlCode);
for(int i=0;i<s.Length;i++)
{
Console.WriteLine(s[i]);
Console.WriteLine("节点 "+i.ToString());
}
StreamReader sr = new StreamReader(@"C:\temp.txt", Encoding.Default);
string html = sr.ReadToEnd();
foreach(Match m in Regex.Matches(html, @"<tr.+?[\s\S]*?</tr>"))
{
if (m.Length > 2000)
{
Console.WriteLine(m.Length.ToString());
Console.WriteLine(m.Value.ToString());
}
}