网页采集程序（超级简单版）

网页采集程序（超级简单版）

) ~& v6 Q( R: T4 l; a( a

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

1 |/ p: V, r: y+ D: ]! v" s) g

02         { 

03             //方法一： 

6 C* x/ Q, x9 {/ x! z9 _

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

3 D6 ?3 f8 M- l T2 G+ C% L, s) L

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

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

9 k. `! g6 ~5 K+ w

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

6 I# d+ O8 P4 J, u# s1 M J! Q

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

09             //Response.Write(html); 

10   

# F! b: d* ^: B k

11             //方法二： 

3 U( b& j# l8 x9 J4 v+ y9 A3 t2 E

12         //获取整个网页 

6 L C6 @ S5 C/ v# w! C! E7 f

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

2 m' U5 ^5 C! @$ ?+ ~3 R

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); 

16             string html = sr.ReadToEnd(); 

, k# L [# y7 V+ ^6 B

17             sr.Close(); 

2 o5 R* Z0 m" H+ o

18             //根据规则获取想要的内容 

. i& M1 u0 u& m$ a0 U; r% I

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); 

22         }

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