网页采集程序（超级简单版）

! Q4 i9 W1 O8 V

4 S. }% z+ }; m0 _3 q& g

网页采集程序（超级简单版）

& v) s4 n' L$ G1 S' G) ~

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

* r* O8 d3 k- W4 n+ ~

02         { 

03             //方法一： 

* I/ N4 L4 q3 W! X" W8 d& s; U }

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); 

/ |6 `4 d. E7 G* }4 r# A1 H

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

6 T" d4 Y1 m7 S# }9 I2 F

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

1 l; G; S$ ~8 e7 F" n) n/ J

09             //Response.Write(html); 

+ F8 v0 `+ p% k+ M3 C% N$ `

10   

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"); 

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

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

* i" k4 W/ k/ c, X \

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); 

: r# }, l c7 _$ m6 j) V- j

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

0 ^# ?5 z/ A: \% o7 @

21             Response.Write(html); 

/ y1 J x& } J/ }% t) E

22         }

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