网页采集程序（超级简单版）

0 v% V8 w/ e2 x8 @; O

) e: n5 J9 N' l% n9 ^/ A

网页采集程序（超级简单版）

6 u3 o" `, H; h7 I$ R

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

02         { 

% o( U) C1 ~+ E2 V2 S; S

03             //方法一： 

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

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>")); 

4 @6 {9 j3 n. x- `! {8 {

09             //Response.Write(html); 

) u: _ S7 S- u$ w6 i$ r

10   

0 D8 i; E: V% v5 X

11             //方法二： 

* `% `. I V; [+ B

12         //获取整个网页 

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

& t; S# ] G- p# z) n3 k# r

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); 

2 E' D9 Y9 r6 k& i$ |

16             string html = sr.ReadToEnd(); 

; {4 c: \/ a/ Z' t

17             sr.Close(); 

18             //根据规则获取想要的内容 

7 ^% C, r) M' S" v

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

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

$ G' c, K, e, A: A4 i

21             Response.Write(html); 

22         }

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