网页采集程序（超级简单版）

3 ]9 L4 _1 U0 i; e, D- l6 {! e

网页采集程序（超级简单版）

. C8 H2 b: S; _- O

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

02         { 

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); 

. s) _4 @% n9 `. D2 k" S7 Z: I$ |- w

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

! I, }* S' i( W+ q& R5 J

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

& X% y6 {3 C8 U/ D/ O

09             //Response.Write(html); 

3 o" V8 f6 f# E5 O: z- b

10   

11             //方法二： 

+ u* A4 k) H# H# n/ o0 |

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"); 

7 s, r4 {: T* a9 T% @

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

- }$ c+ |# p# S: t m d$ h

16             string html = sr.ReadToEnd(); 

( T0 b: U9 W6 m

17             sr.Close(); 

' l; i% Z7 d1 {0 l/ H

18             //根据规则获取想要的内容 

( P3 o6 f6 s2 @ \

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

+ \$ @" P( s1 ?5 j4 i8 R

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

21             Response.Write(html); 

) `- P a; t0 K- |

22         }

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