winform 逐个获取网页的标题代码,CSharp代码库,德仔网

代码语言
代码分类
【CSharp】 winform 逐个获取网页的标题
作者:Dezai.CN / 发布于2011/9/21/ 694
<div><span style="color: rgb(0,0,255)">using</span><span style="color: rgb(0,0,0)"> System;
</span><span style="color: rgb(0,0,255)">using</span><span style="color: rgb(0,0,0)"> System.Net;
</span><span style="color: rgb(0,0,255)">using</span><span style="color: rgb(0,0,0)"> System.Text;
</span><span style="color: rgb(0,0,255)">using</span><span style="color: rgb(0,0,0)"> System.Text.RegularExpressions;

</span><span style="color: rgb(0,0,255)">class</span><span style="color: rgb(0,0,0)"> Program
{
 </span><span style="color: rgb(0,128,0)">//</span><span style="color: rgb(0,128,0)"> 获取网页的HTML内容，根据网页的charset自动判断Encoding</span><span style="color: rgb(0,128,0)">
</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">static</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">string</span><span style="color: rgb(0,0,0)"> GetHtml(</span><span style="color: rgb(0,0,255)">string</span><span style="color: rgb(0,0,0)"> url)
 {
 </span><span style="color: rgb(0,0,255)">return</span><span style="color: rgb(0,0,0)"> GetHtml(url, </span><span style="color: rgb(0,0,255)">null</span><span style="color: rgb(0,0,0)">);
 }

 </span><span style="color: rgb(0,128,0)">//</span><span style="color: rgb(0,128,0)"> 获取网页的HTML内容，指定Encoding</span><span style="color: rgb(0,128,0)">
</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">static</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">string</span><span style="color: rgb(0,0,0)"> GetHtml(</span><span style="color: rgb(0,0,255)">string</span><span style="color: rgb(0,0,0)"> url, Encoding encoding)
 {
 </span><span style="color: rgb(0,0,255)">byte</span><span style="color: rgb(0,0,0)">[] buf </span><span style="color: rgb(0,0,0)">=</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">new</span><span style="color: rgb(0,0,0)"> WebClient().DownloadData(url);
 </span><span style="color: rgb(0,0,255)">if</span><span style="color: rgb(0,0,0)"> (encoding </span><span style="color: rgb(0,0,0)">!=</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">null</span><span style="color: rgb(0,0,0)">) </span><span style="color: rgb(0,0,255)">return</span><span style="color: rgb(0,0,0)"> encoding.GetString(buf);
 </span><span style="color: rgb(0,0,255)">string</span><span style="color: rgb(0,0,0)"> html </span><span style="color: rgb(0,0,0)">=</span><span style="color: rgb(0,0,0)"> Encoding.UTF8.GetString(buf);
 encoding </span><span style="color: rgb(0,0,0)">=</span><span style="color: rgb(0,0,0)"> GetEncoding(html);
 </span><span style="color: rgb(0,0,255)">if</span><span style="color: rgb(0,0,0)"> (encoding </span><span style="color: rgb(0,0,0)">==</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">null</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,0)">||</span><span style="color: rgb(0,0,0)"> encoding </span><span style="color: rgb(0,0,0)">==</span><span style="color: rgb(0,0,0)"> Encoding.UTF8) </span><span style="color: rgb(0,0,255)">return</span><span style="color: rgb(0,0,0)"> html;
 </span><span style="color: rgb(0,0,255)">return</span><span style="color: rgb(0,0,0)"> encoding.GetString(buf);
 }

 </span><span style="color: rgb(0,128,0)">//</span><span style="color: rgb(0,128,0)"> 根据网页的HTML内容提取网页的Encoding</span><span style="color: rgb(0,128,0)">
</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">static</span><span style="color: rgb(0,0,0)"> Encoding GetEncoding(</span><span style="color: rgb(0,0,255)">string</span><span style="color: rgb(0,0,0)"> html)
 {
 </span><span style="color: rgb(0,0,255)">string</span><span style="color: rgb(0,0,0)"> pattern </span><span style="color: rgb(0,0,0)">=</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(128,0,0)">@"</span><span style="color: rgb(128,0,0)">(?i)\bcharset=(?<charset>[-a-zA-Z_0-9]+)</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(0,0,0)">;
 </span><span style="color: rgb(0,0,255)">string</span><span style="color: rgb(0,0,0)"> charset </span><span style="color: rgb(0,0,0)">=</span><span style="color: rgb(0,0,0)"> Regex.Match(html, pattern).Groups[</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(128,0,0)">charset</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(0,0,0)">].Value;
 </span><span style="color: rgb(0,0,255)">try</span><span style="color: rgb(0,0,0)"> { </span><span style="color: rgb(0,0,255)">return</span><span style="color: rgb(0,0,0)"> Encoding.GetEncoding(charset); }
 </span><span style="color: rgb(0,0,255)">catch</span><span style="color: rgb(0,0,0)"> (ArgumentException) { </span><span style="color: rgb(0,0,255)">return</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">null</span><span style="color: rgb(0,0,0)">; }
 }

 </span><span style="color: rgb(0,128,0)">//</span><span style="color: rgb(0,128,0)"> 根据网页的HTML内容提取网页的Title</span><span style="color: rgb(0,128,0)">
</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">static</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">string</span><span style="color: rgb(0,0,0)"> GetTitle(</span><span style="color: rgb(0,0,255)">string</span><span style="color: rgb(0,0,0)"> html)
 {
 </span><span style="color: rgb(0,0,255)">string</span><span style="color: rgb(0,0,0)"> pattern </span><span style="color: rgb(0,0,0)">=</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(128,0,0)">@"</span><span style="color: rgb(128,0,0)">(?si)<title(?:\s+(?:""[^""]*""|'[^']*'|[^""'>])*)?>(?<title>.*?)</title></span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(0,0,0)">;
 </span><span style="color: rgb(0,0,255)">return</span><span style="color: rgb(0,0,0)"> Regex.Match(html, pattern).Groups[</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(128,0,0)">title</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(0,0,0)">].Value.Trim();
 }

 </span><span style="color: rgb(0,128,0)">//</span><span style="color: rgb(0,128,0)"> 打印网页的Encoding和Title</span><span style="color: rgb(0,128,0)">
</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">static</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">void</span><span style="color: rgb(0,0,0)"> PrintEncodingAndTitle(</span><span style="color: rgb(0,0,255)">string</span><span style="color: rgb(0,0,0)"> url)
 {
 </span><span style="color: rgb(0,0,255)">string</span><span style="color: rgb(0,0,0)"> html </span><span style="color: rgb(0,0,0)">=</span><span style="color: rgb(0,0,0)"> GetHtml(url);
 Console.WriteLine(</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(128,0,0)">[{0}] [{1}]</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(0,0,0)">, GetEncoding(html), GetTitle(html));
 }

 </span><span style="color: rgb(0,128,0)">//</span><span style="color: rgb(0,128,0)"> 程序入口</span><span style="color: rgb(0,128,0)">
</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">static</span><span style="color: rgb(0,0,0)"> </span><span style="color: rgb(0,0,255)">void</span><span style="color: rgb(0,0,0)"> Main()
 {
 PrintEncodingAndTitle(</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(128,0,0)">http://www.msdn.net/</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(0,0,0)">);
 PrintEncodingAndTitle(</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(128,0,0)">http://www.cnblogs.com/</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(0,0,0)">);
 PrintEncodingAndTitle(</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(128,0,0)">http://www.cnblogs.com/skyiv/</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(0,0,0)">);
 PrintEncodingAndTitle(</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(128,0,0)">http://www.csdn.net/</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(0,0,0)">);
 PrintEncodingAndTitle(</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(128,0,0)">http://news.163.com/</span><span style="color: rgb(128,0,0)">"</span><span style="color: rgb(0,0,0)">);
 }
}
</span><span style="color: rgb(0,128,0)">/**//*</span><span style="color: rgb(0,128,0)"> 程序输出：
[] [MSDN: Microsoft Developer Network]
[System.Text.UTF8Encoding] [博客园 - 程序员的网上家园]
[System.Text.UTF8Encoding] [空间/IV - 博客园]
[System.Text.UTF8Encoding] [CSDN.NET - 中国最大的IT技术社区，为IT专业技术人员提供最全面的信息传播和服务平台]
[System.Text.DBCSCodePageEncoding] [新闻中心_网易新闻]
</span><span style="color: rgb(0,128,0)">*/</span></div>
试试其它关键字
　获取网页的标题　
同语言下
可能有用的
Dezai.CN贡献的其它代码(4037)