网页采集程序（超级简单版）

2 W0 [- H- l& \9 V5 R

i5 t2 z# k+ j8 |1 E; `

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) 

; Q6 R9 h2 M2 j* X2 S5 l

02         { 

% d+ x" C6 n; O* Q2 `7 [* P) 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>")); 

09             //Response.Write(html); 

7 c m" v8 o' {

10   

2 ]4 k A) N. e, O# `) E

11             //方法二： 

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"); 

6 j" ?: k/ {$ `5 v4 F9 B

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

16             string html = sr.ReadToEnd(); 

8 a! o$ I( O/ U7 X `3 N" O

17             sr.Close(); 

5 E: ]/ w1 J9 B3 ?/ S

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); 

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

/ i6 q! A) z: J4 U s2 J( w

21             Response.Write(html); 

+ H; A( L: X7 b( m

22         }

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