网页采集程序（超级简单版）

/ m6 [( c( j* e- Q4 D% g6 {: D

5 y# j. Y" e2 e5 E$ [- x% W- ~$ ^+ F

网页采集程序（超级简单版）

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： 

* l U8 l' U7 m8 G/ J

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

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

; V/ J, _# d. O0 H

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

1 n6 Y0 A' L' Z: T2 v3 J

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

- c2 f# D4 v# n* u6 x

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

09             //Response.Write(html); 

7 J& ?3 V. K& j/ [# k- Y

10   

11             //方法二： 

1 F$ ^- g' E. r; L7 Q

12         //获取整个网页 

5 }7 q5 q8 W D1 j2 E1 ^

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

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); 

" ]/ u6 k+ G! X/ V. L+ ~& m

16             string html = sr.ReadToEnd(); 

# O5 S2 x$ T! n7 j6 i* O: r0 C

17             sr.Close(); 

, q7 Y# P" r- ?1 G

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); 

; C0 F" V7 P8 H2 l. ~2 U* n, Y/ C

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

21             Response.Write(html); 

6 |6 F0 x, C- p3 B0 ]9 m2 G

22         }

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