网页采集程序（超级简单版）

0 B, W9 V1 ?7 K" _

网页采集程序（超级简单版）

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

02         { 

4 r* V0 `, c5 I/ w

03             //方法一： 

3 M9 h0 K1 i* T+ w* R

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

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

9 M- ?/ k# d9 E/ @

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

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

5 {' W; f- `% C* m3 R, d; D2 q

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

/ Z" c8 D$ |# J8 U# P" T/ ^

09             //Response.Write(html); 

+ J3 I% P! ]4 @& Q: l1 R. t. C

10   

4 T6 H. n# j( u) _+ v

11             //方法二： 

- A/ w t3 T; ^

12         //获取整个网页 

3 I! N& F" a" s: O4 _

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

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

4 e' Z S" r/ q7 N |- w

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

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

, r, L& v& e; R7 Z9 O) s4 |

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); 

' I, W) H$ N, P

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

( F7 O- j9 f2 z

21             Response.Write(html); 

22         }

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