网页采集程序（超级简单版）

网页采集程序（超级简单版）

& Z3 N0 q, }/ h: }0 P/ c* T

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

2 |) J8 Q3 G& W/ m

02         { 

* s ^) _& E b0 _

03             //方法一： 

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

+ R. P( ^/ g0 J" O; U* s

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

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

% b8 T% Z3 E& b. L

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

* M, t* C& R8 }+ Q; ^& M! v

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

09             //Response.Write(html); 

, q4 i \. o+ k- `, {7 b6 ~

10   

11             //方法二： 

+ Z. ~% D7 v. B7 N7 W/ t

12         //获取整个网页 

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

8 E. {2 C3 G/ I) J2 _

14             System.IO.Stream sm = wc.OpenRead("http://www.baidu.com"); 

. S( w) d+ R* O7 x1 p; V( W) X W

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

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

18             //根据规则获取想要的内容 

. m. O; ?( `3 @) n

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

) y$ s/ z, N: @4 b1 S6 I1 C

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

" I! J" M9 F; ^5 u, _2 n% ~

21             Response.Write(html); 

1 [* ^/ L' c; c* L& t

22         }

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