网页采集程序（超级简单版）

# _, t t, G! A& C0 Y- }3 J, J

网页采集程序（超级简单版）

' `' |) b" X( @

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

) O- M2 k9 B+ `, t

02         { 

03             //方法一： 

: |# L$ c" T; I9 ?

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

1 `* B2 h w) k8 g e. _

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

7 I. |- [( f- |+ B: T- G& U% M

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

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

' j: z; G7 ]1 t2 }2 F5 ~

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

# n8 e* Z8 |+ i6 s3 r$ m4 s

09             //Response.Write(html); 

10   

& B; F# U, K2 D

11             //方法二： 

12         //获取整个网页 

# u- R4 ~; g7 D$ n( A$ f

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

' ?5 g9 ]3 d: ?0 S- D9 r

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); 

* m4 n5 N* M. @: Y$ Z( s

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

18             //根据规则获取想要的内容 

+ z9 v+ |# I+ K; r" L# d

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

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

7 _$ X( c5 ^- i/ L) l

21             Response.Write(html); 

22         }

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