网页采集程序（超级简单版）

2 v5 X% b9 K, ~# j ]% |! ]

, l( d# L/ e* Q

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         { 

v" Q6 [' A2 z/ y7 A3 p

03             //方法一： 

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

4 s0 p2 p, v _* d4 ^. ~

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); 

# G3 n& r! t3 O% ]

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

09             //Response.Write(html); 

; j1 z8 F* t6 U( O: c5 \

10   

11             //方法二： 

12         //获取整个网页 

( K& @' y( ?; F# v

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

: s s1 B0 a# I3 h6 h

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

* V1 Q- _, X; | n2 z

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

+ V9 k& O5 Q, D5 E! u9 Q7 K! J

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

' N+ G# ^) C% H! G0 Y# @

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>")); 

8 x* ^/ B' U2 P5 i" |, N

21             Response.Write(html); 

22         }

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