网页采集程序（超级简单版）

: w7 ^6 F; D+ x3 d) P1 O

网页采集程序（超级简单版）

7 W0 Y" m7 C& G3 Y# M. j

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

02         { 

, S) j* z& I& s

03             //方法一： 

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

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

7 | _- T) f1 [! ]. [2 V# ?

06             //string html = System.Text.Encoding.GetEncoding("gb2312").GetString(b); 

" s3 m# w+ U. q+ H) {

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

: M6 ?8 R* {) ]$ N! a# \

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

, Q: S6 ]/ u5 E' k; T- S: T% W

09             //Response.Write(html); 

10   

11             //方法二： 

12         //获取整个网页 

& h" {& T2 F; m- e4 r& c

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); 

- v, s/ u- R& ~1 R# e5 ]

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

' ~' P) z- u$ q$ A# F8 |

18             //根据规则获取想要的内容 

: n! L3 W* n. i3 g% M. g

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

+ x, B! ]% G, }, E& `% u- e

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

21             Response.Write(html); 

22         }

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