网页采集程序（超级简单版）

6 s2 K" p' u" S. ~; G4 ]) l

3 l+ q' V2 ]3 I- P' o3 B

网页采集程序（超级简单版）

# Z! Y* s" @1 C& L

% Y+ ^ j0 K W& o3 S. x9 K

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

02         { 

03             //方法一： 

7 Q3 k3 m3 \' I3 Z' |

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

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

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

. E( v5 T. I: ^# J* i& V

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

' Y$ }! M) @& c' e5 w0 x! T

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

2 R* \, l( U5 ^/ _6 I0 @$ m, q

09             //Response.Write(html); 

10   

11             //方法二： 

+ L$ [- p q1 o& U5 F# B

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. o! M, m9 G& t; }8 J# B; |

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); 

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

21             Response.Write(html); 

3 u# I9 K+ D& n- i# X' M

22         }

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