网页采集程序（超级简单版）

6 \# Y. w7 R$ d* [; z

网页采集程序（超级简单版）

$ O% \! w$ @; t& G9 d7 e0 F2 X' J

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

3 O3 [9 O4 ?5 k2 J% X, b4 ^

02         { 

6 S" a7 W& v2 J1 M* l+ A

03             //方法一： 

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

6 E( `$ ~ K) s/ ?

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

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

5 `% L' a' q3 [, f+ ?

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

5 m. Y' c! A# H4 @

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

: I6 _: y. s) w

09             //Response.Write(html); 

0 A; E5 n- t% D& i% o; _

10   

+ a5 ~! p( d. h( U& d. q" L

11             //方法二： 

1 F, k6 }, e; y3 b6 {" _7 Z* M2 ]/ }

12         //获取整个网页 

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

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

8 {- N) H7 \1 B

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

# y; s) H4 w6 E8 v% f3 g, s& [

16             string html = sr.ReadToEnd(); 

9 c0 U4 R9 b* } i" l

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); 

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

' ^1 O# \8 X% N" \7 F Q: l; k: W

21             Response.Write(html); 

+ y& K7 U, |9 V( i- ~7 V

22         }

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