网页采集程序（超级简单版）

网页采集程序（超级简单版）

$ b& z7 M9 f9 N/ h3 x& t/ _

; ?% h6 d7 u' m5 f ^

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

+ m$ ~# g2 p0 @8 d2 ]

02         { 

03             //方法一： 

# ]5 y* v" c# F4 W5 N

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

9 X( ]. u) W5 r* n% v2 `! [

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); 

% K3 t7 \* `) @2 \& f! ]- r

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

* g- P5 a) g( g; z5 ]: W

09             //Response.Write(html); 

7 i6 \! ?* Y5 A P5 R/ Z2 K+ K

10   

11             //方法二： 

7 f) s8 v& l! W+ f) H: }7 V

12         //获取整个网页 

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

# S- ^4 [, H4 r" o

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); 

( i6 @$ P7 s' x1 m; j& y6 E1 c5 n

16             string html = sr.ReadToEnd(); 

7 m) z3 n6 G1 j

17             sr.Close(); 

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); 

* {; y/ \+ }: {7 }/ i

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

) U M4 r% e* k. \/ O" U

21             Response.Write(html); 

2 g ?4 D: U. [) K, y" N

22         }

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