网页采集程序（超级简单版）

& x3 W' i1 }# `, q% `

' f" r( N1 r* ~+ }

网页采集程序（超级简单版）

9 |( [" q9 ?3 S. P9 P" N

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

02         { 

, L: P3 T# a4 @8 s! O2 V' ]

03             //方法一： 

; f7 h* j" Z$ \

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

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

3 U3 V/ k! v4 K" |, r

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

$ L/ r" c v% H( B S! |7 s

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

6 n/ [0 \0 Y+ @4 e4 ?- D+ C

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

; H1 N8 r. q+ a$ Y

09             //Response.Write(html); 

! g' o/ `! r. d \

10   

11             //方法二： 

12         //获取整个网页 

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

! V5 t* _4 V3 E z! B% @

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); 

; v5 p5 m- m" b6 c

16             string html = sr.ReadToEnd(); 

. r- z5 y% w5 m' J3 A+ {4 L

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); 

# ?% n( v6 _4 C; T" |, m

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

21             Response.Write(html); 

22         }

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