网页采集程序（超级简单版）

网页采集程序（超级简单版）

& d( d( d- g( U

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

$ g6 I# d; l, H% ]* c ^

02         { 

03             //方法一： 

3 `5 }2 r' d, r2 o. `1 v3 E

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

- S6 [/ Z; c( D$ E% U8 {

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

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

& |' k" B5 g4 @% S7 u: p! t

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); 

10   

6 R8 g: [7 `! h4 m: t. ?: B

11             //方法二： 

( ?! d9 z$ {/ p$ F! U, t

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"); 

2 g ]4 f# P; l2 F: \* L

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

$ q0 D1 f3 X# O* G' s

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

4 Z/ |8 \9 H4 z

18             //根据规则获取想要的内容 

7 W) j3 ~# d6 c

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

, d6 `# \3 X! i$ _4 W, H

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

21             Response.Write(html); 

1 A2 Q0 m3 Q9 O, h) X. W

22         }

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