网页采集程序（超级简单版）

网页采集程序（超级简单版）

& ]. C0 O+ d. f; f. Y$ h/ `

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

02         { 

03             //方法一： 

# j# \" G9 F/ I+ C4 d4 z( ]

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

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

% y, v! k; |5 C5 D/ q* B1 M

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

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

0 O# u9 H$ a5 E; c$ \: U8 f) {

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

* b% q* s: |4 Y6 M6 l

09             //Response.Write(html); 

10   

11             //方法二： 

, J( {% ?6 R' b! J1 f) P8 r: K

12         //获取整个网页 

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

, t M' _: L, V, C. U* y5 M* y

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

1 }' x1 C7 B6 g

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

# e7 _4 r6 H( \1 ]# V$ [7 O

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

1 L/ p- y( T7 x J; j: R( M

18             //根据规则获取想要的内容 

1 O1 `3 A5 O5 v N1 ^

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); 

E0 r9 v2 Y; {4 y+ w2 z

22         }

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