网页采集程序（超级简单版）

* k/ \9 n2 g. U! n& F$ o: M( c

网页采集程序（超级简单版）

- e+ t4 L/ C9 W

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

02         { 

, m* O2 b7 s* `( q8 S

03             //方法一： 

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

4 \2 r E. j4 l4 Y! a6 t

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

' P# W1 S, M7 R) r/ _

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>")); 

2 q. a( c1 f, A7 w, C+ ?

09             //Response.Write(html); 

" l, v9 C% P5 z ^: \$ b" @# u1 S

10   

11             //方法二： 

12         //获取整个网页 

6 a, b3 b- o6 `, t( t3 ~7 Z

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

8 ?5 {0 H3 F& l- B

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

7 @# J$ j& ~1 C1 w7 _) j

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

16             string html = sr.ReadToEnd(); 

5 i6 | c% n+ N/ I4 Q

17             sr.Close(); 

18             //根据规则获取想要的内容 

7 O: E6 j; b! r7 Z) P

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

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

21             Response.Write(html); 

5 \, F. i% e% Q( Q4 [

22         }

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