php小偷程序实例代码

$homepage = file_get_contents('http://www.111com.net/');
echo $homepage;
?>

function fetch_urlpage_contents($url){
$c=file_get_contents($url);
return $c;
}
//获取匹配内容
function fetch_match_contents($begin,$end,$c)
{
$begin=change_match_string($begin);
$end=change_match_string($end);
$p = "{$begin}(.*){$end}";
if(eregi($p,$c,$rs))
{
return $rs[1];}
else { return "";}
}//转义正则表达式字符串
function change_match_string($str){
//注意，以下只是简单转义
//$old=array("/","$");
//$new=array("/","$");
$str=str_replace($old,$new,$str);
return $str;
}

//采集网页
function pick($url,$ft,$th)
{
$c=fetch_urlpage_contents($url);
foreach($ft as $key => $value)
{
$rs[$key]=fetch_match_contents($value["begin"],$value["end"],$c);
if(is_array($th[$key]))
{ foreach($th[$key] as $old => $new)
{
$rs[$key]=str_replace($old,$new,$rs[$key]);
}
}
}
return $rs;
}

$url="http://www.111com.net"; //要采集的地址
$ft["title"]["begin"]=""; //截取的结束点
$th["title"]["中山"]="广东"; //截取部分的替换

$ft["body"]["begin"]=""; //截取的开始点
$ft["body"]["end"]=""; //截取的结束点
$th["body"]["中山"]="广东"; //截取部分的替换

$rs=pick($url,$ft,$th); //开始采集

echo $rs["title"];
echo $rs["body"]; //输出
?>

function fetch_urlpage_contents($url){
$c=file_get_contents($url);
return $c;
}
//获取匹配内容
function fetch_match_contents($begin,$end,$c)
{
$begin=change_match_string($begin);
$end=change_match_string($end);
$p = "#{$begin}(.*){$end}#iU";//i表示忽略大小写，U禁止贪婪匹配
if(preg_match_all($p,$c,$rs))
{
return $rs;}
else { return "";}
}//转义正则表达式字符串
function change_match_string($str){
//注意，以下只是简单转义
$old=array("/","$",'?');
$new=array("/","$",'?');
$str=str_replace($old,$new,$str);
return $str;
}

//采集网页
function pick($url,$ft,$th)
{
$c=fetch_urlpage_contents($url);
foreach($ft as $key => $value)
{
$rs[$key]=fetch_match_contents($value["begin"],$value["end"],$c);
if(is_array($th[$key]))
{ foreach($th[$key] as $old => $new)
{
$rs[$key]=str_replace($old,$new,$rs[$key]);
}
}
}
return $rs;
}

$url="http://www.111com.net"; //要采集的地址
$ft["a"]["begin"]='
$ft["a"]["end"]='>'; //截取的结束点

$rs=pick($url,$ft,$th); //开始采集

print_r($rs["a"]);

?>

function GetSources($Url,$User_Agent='',$Referer_Url='') //抓取某个指定的页面
{
//$Url 需要抓取的页面地址
//$User_Agent 需要返回的user_agent信息 如“baiduspider”或“googlebot”
$ch = curl_init();
curl_setopt ($ch, CURLOPT_URL, $Url);
curl_setopt ($ch, CURLOPT_USERAGENT, $User_Agent);
curl_setopt ($ch, CURLOPT_REFERER, $Referer_Url);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION,1);
curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);
$MySources = curl_exec ($ch);
curl_close($ch);
return $MySources;
}
$Url = "http://www.111com.net"; //要获取内容的也没
$User_Agent = "baiduspider+(+http://www.baidu.com/search/spider.htm)";
$Referer_Url = 'http://www.111com.net/';
echo GetSources($Url,$User_Agent,$Referer_Url);
?>