网页采集程序（超级简单版）

8 l! f9 s" X2 ]& A+ m* {0 _

网页采集程序（超级简单版）

- M+ D4 o- O. X; S

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

4 {1 m. m7 { P) v4 {) ?

02         { 

03             //方法一： 

, j% a- Q( ?. b6 ~0 d8 Q2 w

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

7 ~& f6 \0 X8 Y3 c/ D' \" U

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

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

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

$ V. j- _ @) Q# j0 b: u

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

: @, ^/ O5 y8 k7 z9 m

09             //Response.Write(html); 

10   

) i( I. y2 Z* ?" S9 K% ], R. _

11             //方法二： 

5 m0 a& R6 L) S; X: G# l

12         //获取整个网页 

# v/ w" ^& t& I9 H; j+ Q3 L: n

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

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

- a1 ]) X2 e( M9 X& j. K

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

1 h5 ^; ^7 f' ^7 @

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

" G: w) d& ~0 a: \" W

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); 

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

( o9 B0 B+ {/ B" ~% E% y

21             Response.Write(html); 

22         }

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