网页采集程序（超级简单版）

: h9 I9 e3 N1 W7 K1 H0 j

网页采集程序（超级简单版）

4 c- w7 T! [# b: a, ]7 k

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

1 K |& |% S+ P. ^) E1 G

02         { 

7 W: w" Z9 ~4 V- i2 V! S

03             //方法一： 

6 r/ w1 T: h5 V3 x2 D& H1 f, j7 v, o

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

$ x7 n! |8 ]) G" D7 I

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

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

- p0 p. n' L/ Y- p; ^6 t

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

" v V& Q( z8 i2 D( H6 z, C8 I

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

09             //Response.Write(html); 

* l" R4 C7 \: g: f/ s

10   

$ v4 l* D" B+ R# S

11             //方法二： 

1 l8 `8 [; }' c, U. h5 v

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"); 

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

16             string html = sr.ReadToEnd(); 

+ z% m: d2 l. n/ w& { j7 X# ?

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); 

, ~" c- k4 j% @8 n3 d

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

21             Response.Write(html); 

22         }

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