网页采集程序（超级简单版）

& F4 c! a1 k. {4 M

网页采集程序（超级简单版）

- X- o5 X$ {" I8 C6 B' a

q! x! ^$ ?9 ]0 J) {* o" |& X* G

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

$ k. ~: U: `( `/ `! J) y6 Y# m y' l

02         { 

. r% {8 m% G7 K8 c% C

03             //方法一： 

& Z# T M0 @/ \- M6 I0 V

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

/ I1 K) P+ A* w1 ?/ |' c( D

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

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

& F" e/ B! `' ^) L: a4 P$ X

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

; E2 L3 D9 w+ K m

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

09             //Response.Write(html); 

10   

' V3 M2 K- M. m( B. g& J# i- a

11             //方法二： 

12         //获取整个网页 

- Z. P3 f% a9 k! l

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

8 k; z# g+ l d6 t8 b- g, M

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(); 

5 Y( _7 M3 _+ L" h

17             sr.Close(); 

" V5 R9 y4 N- L) A2 }5 E

18             //根据规则获取想要的内容 

* m* p( f/ G7 q0 f. V+ ?

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); 

22         }

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