网页采集程序（超级简单版）

) L! i6 m8 T$ g7 c; f$ I0 |

网页采集程序（超级简单版）

4 y( A4 y* x7 \3 X. x( h

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： 

) v; y* w. S7 r

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

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

6 {. C* N% Y* x9 @; |# Y" s5 o% i

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

- O3 f, ]8 g6 o$ J2 L9 `# b3 h

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

6 V0 l( E0 k) x) C9 }$ z- r

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

09             //Response.Write(html); 

- j8 C/ z/ T1 n3 `8 T& D8 D& {6 F' a

10   

' f1 u" P3 O8 g2 }. H% d* b, M

11             //方法二： 

8 S# N+ m: n( W% _3 C

12         //获取整个网页 

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

- H: p8 T3 a3 c2 k

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

4 g5 j T4 W$ G0 p' _6 u

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

' a9 R5 @/ h( Q" W

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

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); 

# m- S( m7 \* d+ L

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

; p# v% ]7 l5 n f5 e

21             Response.Write(html); 

( r8 r! j* P$ V4 B* F" e

22         }

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