网页采集程序（超级简单版）

网页采集程序（超级简单版）

+ c$ Y0 m/ G3 H: c; i; K9 l

网页采集程序（超级简单版）
01 protected void btn_click(object sender, EventArgs e) 

02         { 

03             //方法一： 

04             //System.Net.WebClient wc = new System.Net.WebClient(); 

4 m8 ^! O p& B

05             //byte[] b = wc.DownloadData("http://www.baidu.com"); 

. d7 T: Y! ~, l) B9 H( }- m2 _

06             //string html = System.Text.Encoding.GetEncoding("gb2312").GetString(b); 

07             //html = html.Substring(html.IndexOf("<p id=\"lg\">") + "<p id=\"lg\">".Length); 

! D' A3 Z" u: m P. U( _

08             //html = html.Substring(0, html.IndexOf("</p>")); 

# u% L9 ]6 B& |9 V2 G0 e

09             //Response.Write(html); 

& ]! J0 p2 i0 b8 n" Z

10   

5 c0 R r- ]+ w' a1 ?3 r! ?, y' B- Y

11             //方法二： 

12         //获取整个网页 

13             System.Net.WebClient wc = new System.Net.WebClient(); 

$ \3 q! r/ C/ ~" ~+ B

14             System.IO.Stream sm = wc.OpenRead("http://www.baidu.com"); 

15             System.IO.StreamReader sr = new System.IO.StreamReader(sm, System.Text.Encoding.Default, true, 256000); 

16             string html = sr.ReadToEnd(); 

4 t3 `- g( ]' [/ _ J

17             sr.Close(); 

18             //根据规则获取想要的内容 

! N8 N; h* _) H* D/ _

19             html = html.Substring(html.IndexOf("<p id=\"lg\">") + "<p id=\"lg\">".Length); 

20             html = html.Substring(0, html.IndexOf("</p>")); 

: v E* s. P0 x5 k G

21             Response.Write(html); 

, _, r+ s8 F8 H& e) g

22         }

http://hereson.javaeye.com/blog/207468