网页采集程序（超级简单版）

( q" l$ \# ~ a

网页采集程序（超级简单版）

$ l1 s' y1 j3 ~

5 |" R7 O' i; E/ B# ]: w( Q

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

. r4 e, e$ ?' n0 ~" _

02         { 

. W- I9 L5 o$ ^" g

03             //方法一： 

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

1 F- O/ `1 c4 B1 V# b* t

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

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

: h, W6 H0 J9 I# e2 u3 I* c

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

( W4 ^; M% R+ t8 D+ v& w X) W9 x

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

09             //Response.Write(html); 

, @9 T2 j' ~: b7 m2 R

10   

8 t, i/ j- U7 m1 J

11             //方法二： 

12         //获取整个网页 

# R" G7 p3 p# n* A2 H4 O$ v

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

1 Q& k2 o% \. }1 ?

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

2 ~1 h! I* w4 T7 R: V" E6 H, T

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

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

18             //根据规则获取想要的内容 

9 x& b. U5 m7 L* Z, C

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

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

* \, G+ ]$ t6 p. x2 T; h

21             Response.Write(html); 

22         }

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