网页采集程序（超级简单版）

G' X1 v, N, Y: n" o/ W4 X; _

: q4 Y. T0 A" n/ J3 `8 A; w

网页采集程序（超级简单版）

/ i. Y5 N( r" L

7 K+ e' h1 t+ o

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

02         { 

) A$ e/ t1 F' `

03             //方法一： 

a5 ^- G2 E: v8 Z& ~, P9 I4 K

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

5 m& G/ f: L& Q, B

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

( j% x2 h: H! k6 m, J! s

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

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

! U- [7 f: o( u* u' k

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

; v8 o4 |' q+ H( k5 I, {

09             //Response.Write(html); 

10   

8 k. M" ?; C2 i# q; H! w

11             //方法二： 

12         //获取整个网页 

# K0 G( q$ l$ C0 C

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); 

# c$ M, T6 v3 ^ l8 G/ [6 l

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); 

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

21             Response.Write(html); 

1 a4 A! \& s$ g* [

22         }

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