网页采集程序（超级简单版）

; \% C% l/ F" ]( e* b

网页采集程序（超级简单版）

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

, E8 u: G5 E: h& o/ B

02         { 

2 f4 w, `" }: C3 t; ]

03             //方法一： 

( I! s. _0 ~5 }8 j9 ^; b+ |

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

8 M& m# v* }2 S/ K2 \

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

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

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

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

09             //Response.Write(html); 

. g: t0 F$ X2 O1 W# Y

10   

11             //方法二： 

6 m3 A+ O! ~1 G% j0 J

12         //获取整个网页 

5 i, q8 q- n# [0 U% i/ I

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

! ^- X3 }( Q- W; r. z

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

$ ~! N$ T2 u, k" Z

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

2 |3 s I0 r A3 u2 g. |; y

16             string html = sr.ReadToEnd(); 

& Q7 E- F/ W1 l+ m9 u) |

17             sr.Close(); 

8 E5 R% t) r& F: ?4 H4 E

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! V5 x, g K% {, k* R8 {9 @

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

2 c4 o8 m% \% _3 v$ R( c. q! f8 C

21             Response.Write(html); 

`; D& w$ a4 s3 V/ m3 O0 B2 }+ ~

22         }

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