网页采集程序（超级简单版）

+ ~; U! Y* ^! @6 W

2 |' b! a; ~5 T

网页采集程序（超级简单版）

8 v1 S2 Y6 s+ L8 C

9 f6 I7 T. A5 |4 I$ t# E( Y

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

% k$ d9 k: E0 c n1 g& d

02         { 

03             //方法一： 

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

# |' W$ W/ I' ^4 Y( _' E& q

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

3 z* W Z$ g" D" v( R( {7 B

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

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

+ v3 N' f _ _' J3 C4 [/ Z& Q" ~/ R$ Y

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

09             //Response.Write(html); 

10   

/ Y0 s `* V2 W1 g2 Y( a5 D# W

11             //方法二： 

12         //获取整个网页 

6 d/ Z$ R* E- n! k8 U

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

: V9 q( W* q" \; l n

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(); 

17             sr.Close(); 

9 o8 N9 g' L& [+ ^

18             //根据规则获取想要的内容 

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

5 G" b: A- t+ Y- c! {

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

21             Response.Write(html); 

22         }

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