matlab抓取网页数据

happy

1. clc;
   
2. clear;
   
3. warning off;
   
4. % [sourcefile, status] = urlread(sprintf('http://trend.baidu.lecai.com/fc3d/baseTrend.action?recentPhase=30&onlyBody=false&phaseOrder=up&coldHotOrder=number'));
   
5. %这个是彩票数据的网址
   
6. [sourcefile, status] =urlread(sprintf('http://888.qq.com/static/chart/fc3d/'));
   
7. if ~status
   
8.     error('读取错误\n')
   
9. end
   
10. %获取日期
    
11. expr1='<td align="center">(\d\d\d\d-\d\d-\d\d)</td>';
    
12. [datefile, date_tokens]= regexp(sourcefile, expr1, 'match', 'tokens');
    
13. date = cell(size(date_tokens));
    
14. for idx = 1:length(date_tokens)
    
15.     date{idx} = date_tokens{idx}{1};    %length(date_tokens)行1列
    
16. end
    
17. 
    
18. %%获取3D的三位数字
    
19. expr2='<td class="chartBall01" width=18>(\d)</td>';
    
20. [datafile, data_tokens] = regexp(sourcefile, expr2, 'match', 'tokens');
    
21. data = zeros(size(data_tokens));
    
22. for idx = 1:length(data_tokens)
    
23.     data(idx) = str2double(data_tokens{idx}{1});  
    
24. end
    
25. 
    
26. data1=reshape(data,3,length(data)/3)';
    
27. %%%数据存储外部文件
    
28. fprintf('完成！\n')

复制代码

转自：http://blog.163.com/zzz216@yeah/ ... 684201412091844681/