网页采集程序（超级简单版）

3 l! B+ o, j7 L, Q9 t# z9 G! C

网页采集程序（超级简单版）

) v" v7 {1 E# W8 c3 X4 i* q! C

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

02         { 

# T( w! n8 B7 L7 u

03             //方法一： 

4 \9 q Z3 j Y; B& O3 D

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

. U; `, j# b! @3 u. p

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); 

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

09             //Response.Write(html); 

1 a8 h, A8 f2 d) p& Y" m O

10   

11             //方法二： 

% Z+ h; w2 L! M5 k4 `

12         //获取整个网页 

" a4 L7 H7 M6 W, O* c* h% p' W. [

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

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

; d9 z2 b1 ]/ K' s$ ]& ^: e S

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

16             string html = sr.ReadToEnd(); 

+ T& @2 x v' D T

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); 

* B' {) D7 o+ e8 h9 k8 ?

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

21             Response.Write(html); 

22         }

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