PHP article content crawl

Ask God to help crawl this page http://sports.sohu.com/zhongchao.shtml data on the leaderboard (including the standings and Sagittarius)

Reply to discussion (solution)

Crawl Research Research Phpquery

$url = ' http://sports.sohu.com/zhongchao.shtml '; $s = file_get_contents ($url);p Reg_match_all ('/(? <=) \s
 
  
   
  /isu ', $s, $m);p Rint_r (Preg_grep ('/rank/', $m [0]));
 
  

Array ([2] = =
You can use Preg_match to crawl the corresponding HTML code and then filter the data you want.
Recommend a class for you simple_html_dom
  
  



  

 
Include "simple_html_dom.class.php"; $url = "http://sports.sohu.com/zhongchao.shtml"; $dom = new Simple_html_dom (); $ html = $dom->load (file_get_contents ($url)), $res = $html->find ("Div#turnidb Div.turn"); # standings echo $res [0]-> outertext;# Archer's list echo $res [1]->outertext;
$str =file_get_contents ("http://sports.sohu.com/zhongchao.shtml");p Reg_match_all ('/
 ...... Then do it yourself. Results  
   
     \s* 
    

  
  
 
   
 
    
Rank
 
    
Team
 
    
matches
 
    
points
 
   
 
   
 
    
01
 
    
Guangzhou Heng da
 
    
20
 
    
45
 
   
 
   
 
    
02
 
    
Beijing Guoan
 
   
(.+?) <\/td>\s*
 
    
(.+?) <\/td>\s*
 
    
(\d+) <\/td>\s*
 
    
(.+?) <\/td>\s*<\/tr>/i ', $str, $match 1), foreach ($match 1 as $k = + $v) {if ($k!=0) {foreach ($v as $k 1=> $v 1) {if ($k 1<=15) {$jifen [$k][]= $v 1;} else{$sheshou [$k][]= $v 1;}}} echo "
";p Rint_r ($jifen);p rint_r ($sheshou); echo"
/*array ([1] = = Array ([0] = [1] = [2] = 03 [3] = [4] = [5] = [6] = [7] = 08 [8 ] = [9] = [ten] = [one] = [one] = [13] [ + [+] [+] [2] = = Array ([0] = wide State Evergrande [1] = Beijing Guoan [2] = Guangzhou freego [3] = Shanghai East Asia [4] = Guizhou Maotai [5] Shandong Luneng [6] = Tianjin Teda [7] = Jiangsu Sainty Day [8] = Shanghai Greenland [9] = Changchun Yatai [Ten] = Hangzhou Greentown [one] = Dalian Aerbin [[+] = Shanghai Shen Xin [] = Henan Jianye [] =&G T Liaoning Hong Yun [[+] = Harbin Yi Teng) [3] = = Array ([0] = [1] = 19 [2] = 19 [3] = [4] = [5] = [6] = [7] = 18 [8] = [9] = [ten] = [one] = [+] = 19 [4] = [+] ([+] = [] = +) [+] = = Array ([ 0] [1] = [2] [3] = [4] = 30 [5] [6] [7] = [8] = [9] = 21 [10] = [one] = [16] = [+] = [+] + [1] 5] (= +)) array ([1] = = Array ([0] = [1] = [2] =&G T [3] = [4] = [5] = [6] = [7] = 08 [8] = = [9] = [+] = [+] ~ [ALL] [] = [+] [] [] [] [] [] []] [=&G] T [+] [+] = [2] = = Array ([0] = = Elksen [1] = = Hammed [2] = Haisen [3] = Damrey [4] [+] = [5] = Lowe [6] = [7] = Dejan [8] = Bathala [9] = = Bruno [Ten] = Ricardo [One] = Zhao Dongquan [[]] = Eno [All] = Yuri [+] [MO] Renault [] = Rene ) [3] = = Array ([0] = [1] = [2] = 13 [3 ] = 9 [4] = 9 [5] = 9 [6] = 9 [7] = 8 [8] = = 7 [9] = 7 [Ten] = 7 [One] = 7 [All] = 7 [] = 7 [+] = 6 [+] = 6) [4] = = Array ([0] = Guangzhou Evergrande [1] = Guangzhou freego [2] = Shanghai East Asia [3] = Guangzhou freego [4] = Harbin Yi Teng [5] = Shandong Luneng [6] = Hangzhou Greentown [7] = Beijing Guoan [8] = Beijing Guoan [9] = Dalian Aerbin [ten] = Harbin Yi Teng [ Shanghai East Asia [Three] = Changchun Yatai [All] = Guizhou Maotai [+] = Shanghai Greenland [All] = Guangzhou Evergrande ))*/ 
I'll handle it in the back.
 
 
 
$url = ' http://sports.sohu.com/zhongchao.shtml '; $s = file_get_contents ($url);p Reg_match_all ('/(? <=) \s
 
       
        
  /isu ', $s, $m);p Rint_r (Preg_grep ('/rank/', $m [0]));
 
       
 
Array ([2] = =

Sohu page is gb2312, after the acquisition need to turn UTF8, otherwise it will garbled
  

      
Echo '
  
           ; $url = ' http://sports.sohu.com/zhongchao.shtml '; $s = file_get_contents ($url); $s = iconv (' GBK ', ' UTF8 ', $s); gb2312 Turn Utf8preg_match_all ('/(? <=) \s
  
          
           
   /isu ', $s, $m);//Get the standings preg_match_all ('
  /
          
      ...... And then I'm going to do it myself. How is an empty array  
        
          \s* 
         
          \s* 
         

       
       
 
        
 
         
Rank
 
         
Team
 
         
matches
 
         
points
 
        
 
        
 
         
01
 
         
Guangzhou Heng da
 
         
20
 
         
45
 
        
 
        
 
         
02
 
         
Beijing Guoan
 
        
(.+?) <\/td>\s*
 
         
(.+?) <\/td>\s*
 
         
(\d+) <\/td>\s*
 
         
(.+?) <\/td>\s*<\/tr>/i ', $m [0][2], $scores), $scoreboard = Array (); for ($i =0, $len =count ($scores [1]); $i <$ Len $i + +) {$tmp = Array ($scores [1][$i],strip_tags ($scores [2][$i]), $scores [3][$i], $scores [4][$i]); Array_push ($ Scoreboard, $tmp);} Print_r ($scoreboard);//Archer list Preg_match_all ('/
 
        
 
        
(.+?) <\/td>\s*
 
         
(.+?) <\/td>\s*
 
         
(\d+) <\/td>\s*
 
         
(.+?) <\/td>\s*<\/tr>/i ', $m [0][3], $shooters), $shooterboard = Array (); for ($i =0, $len =count ($shooters [1]); $i < $len; $i + +) {$tmp = Array ($shooters [1][$i],strip_tags ($shooters [2][$i]), $shooters [3][$i], $shooters [4][$i]); Array_push ($ Shooterboard, $tmp);} Print_r ($shooterboard); 
 
Standings
 
Array ([0] = = Array ([0] = [1] = Guangzhou Evergrande [2] = 20 [3            ] [1] = = Array ([0] = [1] = = Beijing Guoan [2] = 19            [3] = [2] = = Array ([0] = [1] = + Guangzhou Freego [2] = [3] = 3] [+] = [0] = [1] = Shanghai East            Asia [2] = [3] = [4] = = Array ([0] = 05 [1] = Guizhou Maotai [2] = [3] = [5] = = Array ([0] = 0            6 [1] = Shandong Luneng [2] = [3] = [6] = = Array (        [0] = [1] = Tianjin Teda [2] = [3] = +) [7] = = Array ([0] = = [1] = = Jiangsu Sainty Day [2] = [3] = [8] = = Array (        [0] = [1] = Shanghai Greenland [2] = [3] = +) [9] = = Array ([0] = [1] = Changchun Yatai [2] = [3] = 21) [10] =        > Array ([0] = = [1] = Hangzhou Greentown [2] = [3] = 21 ) [One] = Array ([0] = [1] = Dalian Aerbin [2] = 19 [3             ] = [+] = Array ([0] = [1] = Shanghai Shen Xin [2] = 19            [3] = [+] = Array ([0] = [1] = Henan Jianye [2] = [3] = + [+] = = Array ([0] = [1] = = Liaoning Hongyun [2] =>            [3] [+] [+] [+] = Array ([0] = [1] = = Harbin Yi Teng [2] = [3] = 12))
 
 
Shooter List
 
Array ([0] = = Array ([0] = [1] = Elksen [2] = 17 [3             ] = Guangzhou Evergrande) [1] = = Array ([0] = [1] = = Hammed [2] = 16            [3] = Guangzhou freego) [2] = = Array ([0] = [1] = Haisen [2] = [3] = Shanghai East Asia) [3] = = Array ([0] = [1] = =            Damrey [2] = 9 [3] = Guangzhou freego) [4] = = Array ([0] = 04  [1] [+] = [2] = 9 [3] = + harbin Yi Teng) [5] = = Array ([0] = =            [1] = Lowe [2] = 9 [3] = Shandong Luneng) [6] = = Array (        [0] = [1] + [2] = 9 [3] = Hangzhou Greentown) [7] = = Array ([0] = = [1] = = Dejan [2] = 8 [3] = = Beijing Guoan) [8] = = Array (        [0] = [1] = Bathala [2] = 7 [3] = = Beijing Guoan) [9] = = Array ([0] = [1] = Bruno [2] = 7 [3] = = Dalian Aerbin) [10] =        > Array ([0] = [1] = Ricardo [2] = 7 [3] = Harbin Yi Teng ) [one] = = Array ([0] = [1] = Zhao Dongquan [2] = = 7 [3] =            > Shanghai East Asia) [+] = Array ([0] = [1] = = Eno [2] = 7 [3] = Changchun Yatai) [+] = Array ([0] = [1] = Yuri [ 2] + + 7 [3] = Guizhou Maotai) [+] = Array ([0] = [1] = +- Connaught [2] = 6            [2] = 6 [3] = Guangzhou Evergrande))
 