网页采集程序（超级简单版）

3 t6 E& L/ O5 {6 B

网页采集程序（超级简单版）

8 \3 K7 v# R+ B* D2 A% Q: i

. {. D& {) z, [: [& `% F8 v0 X

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

02         { 

# d1 i, b! S8 X" I% f' u

03             //方法一： 

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

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

+ K, c" S& O! y/ E

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

0 o4 N% g `# u, p/ U

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

2 {0 z2 G4 w. k* A1 D1 A

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

$ f( F/ l9 N, {6 j! N9 n3 X

09             //Response.Write(html); 

) Y- I$ S* a, z0 Y5 C

10   

7 q' t! H# D* C0 r

11             //方法二： 

12         //获取整个网页 

5 m: Y: t7 I( ~5 z) Y- ^

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

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

# A$ R& d: u+ S- u" p* b

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

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

18             //根据规则获取想要的内容 

/ E$ k# Z7 f4 G' L/ o* d$ {6 ]' d

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 a3 J5 ]8 _# Y: ]7 D& C, A

22         }

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