网页采集程序（超级简单版）

网页采集程序（超级简单版）

1 Y1 f6 Z7 f4 [* o8 W! ?, N% U

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

U {0 o: M' J4 G, C. Q9 z" P

02         { 

8 ]3 T/ F- L H3 V8 G! P

03             //方法一： 

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

7 c, ~: l0 P* V" F% ]1 Q

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

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

+ l% v: P" V8 j+ |

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

7 I$ m" z& z ^- T" h) f

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

09             //Response.Write(html); 

4 h" U d8 R8 C5 {3 x# Z7 D& U

10   

11             //方法二： 

12         //获取整个网页 

( ?( @+ M( n3 z( Q, f5 N

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); 

- i G( R; D% T+ X; Z0 I9 H

16             string html = sr.ReadToEnd(); 

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); 

& r+ J9 b" F# f' D$ r" O9 ~

22         }

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