网页采集程序（超级简单版）

网页采集程序（超级简单版）

: G1 q' } U1 v8 D! C4 |# ^

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

02         { 

+ z9 X! w; p4 w

03             //方法一： 

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

; H1 d7 x" w& V ^5 b5 J

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

0 j+ R' P8 T0 d, o% k

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

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

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

& L* Y5 a. T; X3 N. F' O5 W+ [& V2 ^

09             //Response.Write(html); 

' `+ Q; P7 Y2 S

10   

3 z y+ }9 C( G9 V

11             //方法二： 

# Y1 W8 p& a. p1 P+ h: u( g

12         //获取整个网页 

1 q, f. t$ [& H* W% |+ F

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

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

0 E: k- L% b9 V5 ]( r; f1 T

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

8 m. O$ P( ?0 v; i5 b5 t

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

18             //根据规则获取想要的内容 

6 g& b8 o- |* M! y) f. e3 y

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

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

3 ~# s9 H! M. `

21             Response.Write(html); 

4 {; ?' M, Y0 {, e6 Y

22         }

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