网页采集程序（超级简单版）

网页采集程序（超级简单版）

5 g$ X4 B: N( ]" O& A

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

^' j$ m- b1 `& z0 e' ~4 A6 v

02         { 

8 O# }+ ?. [; @& I6 E. ~! m# @

03             //方法一： 

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

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); 

) @7 j2 _, u3 j9 ^5 q

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

$ O1 V3 Q) I5 x4 D

09             //Response.Write(html); 

10   

. m% A* K* x L b! k# B

11             //方法二： 

12         //获取整个网页 

- I% s! R5 z0 p6 J3 O! z

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); 

5 h4 Z) A t" f- g$ }

16             string html = sr.ReadToEnd(); 

5 E' x1 k0 I' R6 |+ J; E* }6 i& K

17             sr.Close(); 

18             //根据规则获取想要的内容 

* I9 \" O0 W( A/ ^; D2 Z. `

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

/ s5 ^. F1 a- w! ^

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

# D' |0 Y. }5 X# F- x

21             Response.Write(html); 

8 [. m7 z9 N V: i, h) M# f

22         }

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