网页采集程序（超级简单版）

! O2 O# V# w8 w# ]# t4 T

网页采集程序（超级简单版）

# e) {9 X6 H- S

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

# ?9 _8 H7 @1 w

02         { 

% }! Q z, a$ U2 j5 r% ^

03             //方法一： 

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

0 a- B- P, ]' O. l

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

, M. ]# {7 H% k% k: B* i6 f: L

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

$ y S, Q' `. K, P* y% Z" Z

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

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

e# z( U5 R% U

09             //Response.Write(html); 

: N& l& ]% f) { {

10   

# {; l( q0 H' d

11             //方法二： 

& b- X( K7 h- A

12         //获取整个网页 

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

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

5 O. y" V7 }% j% R2 k

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

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

, ~4 s0 {4 O5 P/ M* D! Z1 a4 E# B

18             //根据规则获取想要的内容 

4 A0 m w2 A2 w9 R

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

- T. ?% |" F" \9 F, d, w* x& _

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

21             Response.Write(html); 

22         }

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