网页采集程序（超级简单版）

% Y/ h l# X8 o. ?( {! d

网页采集程序（超级简单版）

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

02         { 

8 r/ H& l1 t: [$ _. ^/ h2 e: {3 V

03             //方法一： 

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

2 p/ p! L! X. @3 B

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); 

* M# d! _; s- ~7 A

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

09             //Response.Write(html); 

. q/ ?& c* Q1 q, I- C; c

10   

) K+ {, v H' O

11             //方法二： 

]4 {& Y3 X$ m% W/ d3 Z2 D

12         //获取整个网页 

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

+ i, ~% t& ^& n: n( T8 J& X' d8 Y T

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

, b2 D4 k% T _0 Z& Z

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

5 k# I4 e6 I5 [( B

16             string html = sr.ReadToEnd(); 

0 D( j: a9 _0 w" [$ w. `

17             sr.Close(); 

( G) S, e& R" B9 J$ m# Z- F7 D5 O

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>")); 

21             Response.Write(html); 

( S" M7 X4 U6 F3 B" [$ d4 U

22         }

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