PHP完美的提取链接正则

小学生表示不爽

于 2014-08-27 11:56:30 发布

阅读量882

点赞数

本文链接：https://blog.youkuaiyun.com/u013327409/article/details/38867999

版权

 
      function 
       match_links( 
      $document 
      ) {      
     
 
      preg_match_all( 
      "'<\s*a\s.*?href\s*=\s*([\"\'])?(?(1)(.*?)\\1|([^\s\>]+))[^>]*>?(.*?)</a>'isx" 
      , 
      $document 
      , 
      $links 
      );                          
      while 
      (list( 
      $key 
      , 
      $val 
      ) = each( 
      $links 
      [2])) {  
      if 
      (! 
      empty 
      ( 
      $val 
      ))  
      $match 
      [ 
      'link' 
      ][] =  
      $val 
      ;  
     
 
      }  
      while 
      (list( 
      $key 
      , 
      $val 
      ) = each( 
      $links 
      [3])) {  
      if 
      (! 
      empty 
      ( 
      $val 
      ))  
      $match 
      [ 
      'link' 
      ][] =  
      $val 
      ;  
     
 
      }          
      while 
      (list( 
      $key 
      , 
      $val 
      ) = each( 
      $links 
      [4])) {  
      if 
      (! 
      empty 
      ( 
      $val 
      ))  
      $match 
      [ 
      'content' 
      ][] =  
      $val 
      ;  
     
 
      }  
      while 
      (list( 
      $key 
      , 
      $val 
      ) = each( 
      $links 
      [0])) {  
      if 
      (! 
      empty 
      ( 
      $val 
      ))  
      $match 
      [ 
      'all' 
      ][] =  
      $val 
      ;  
     
 
      }                  
      return 
      $match 
      ;  
     
 
      } 
     