11
<?php
class Thief{
var $URL;
function getSourceList ()
{
var $sList = @file_get_contents( $this->URL );
preg_match_all( "/<a(.*?)<\/a>/i", $sList, $list );
$list = $list[0];
if(!$list || !is_array($list)){
return $this->getSourceListExtend($sList);
}else{
return $this->getList ( $list );
}
}
function getSourceListExtend($sList)
{
$content=explode("</a>",$sList);
for($i=0;$i<count($content)-1;$i++)
{
$lists=explode("<a",$content[$i]);
$list[]=$lists[1];
}
return $this->GetListExtend( $list );
}
function getList ( $list )
{
for ( $i = 0; $i < count( $list ); $i++ )
{
preg_match_all( "/href=(\"|'|)(.*?)(\"|'|)/i", $list[$i], $tempc );
//获取的数据正确
if( !empty( $templ[1][0] ) && !empty( $tempc[2][0] ) )
{
if( 0 == strpos( $tempc[2][0], "/" ) )
{
preg_match( "@http://(.*?)/@i", $this->URL, $url );
$tempc[2][0] = substr( $url[0], 0, strlen( $url[0] ) - 1 ) . $tempc[2][0];
}
$listContent[$i][1] = $tempc[2][0];
}
}
if(!$listContent || !is_array($listContent)){
return $this->GetListExtend ( $list );
}else{
return $listContent;
}
}
function GetListExtend ( $list )
{
$list=str_replace("\"","",$list);
$list=str_replace("'","",$list);
$list=str_replace("=","",$list);
for ( $i = 0; $i <count( $list ); $i++ )
{
$temp_link=$this->cut($list[$i],"href"," ");
//获取的数据正确
if( !empty( $temp_link ))
{
if( 0 == strpos( $tempc[2][0], "/" ) )
{
}
$listContent[$i][1] = $temp_link;
}
}
return $listContent;
}
}
?>