Php Scrapper anuntul.ro

[UnixDevel]

<?
$url="http://m.anuntul.ro/anunturi/19";
include_once'simple_html_dom.php';
function extrage_info($url){
  $ch = curl_init();
  $timeout = 30;
  curl_setopt($ch,CURLOPT_URL,$url);
  curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
  curl_setopt($ch,CURLOPT_CONNECTTIMEOUT,$timeout);
  curl_setopt($ch,CURLOPT_USERAGENT, 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1');
  curl_setopt($ch,CURLOPT_FOLLOWLOCATION, 1);
  $data = curl_exec($ch);
  curl_close($ch);
  $html = str_get_html($data);
  foreach($html->find('div.txt') as $article) {
	    $item2['title']     = $article->find('a', 0)->plaintext;
/* 		$alabama= $article->find('p');
		$item2['continut']     = $alabama[0]; */
		$text[]=$item2;
 }
return $text[0]['title'];
$html->clear(); 
unset($html);
}
function get_data($url){
  $ch = curl_init();
  $timeout = 30;
  curl_setopt($ch,CURLOPT_URL,$url);
  curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
  curl_setopt($ch,CURLOPT_CONNECTTIMEOUT,$timeout);
  curl_setopt($ch,CURLOPT_USERAGENT, 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1');
  curl_setopt($ch,CURLOPT_FOLLOWLOCATION, 1);
  $data = curl_exec($ch);
  curl_close($ch);
$html = str_get_html($data);
foreach($html->find('div.of') as $article) {
    $item['title']     = $article->find('div.of_tit', 0)->plaintext;
    $item['intro']    = $article->find('div.flr', 0)->plaintext;
	$lk=$article->find('div.of_end', 0)->innertext;
	$ex=explode('<a href="/anunt/',$lk);
	$ex2=explode('/',$ex[1]);
	$item['lk']=$ex2[0];
	$item['continut']=extrage_info('http://m.anuntul.ro/anunt/'.$ex2[0].'');
    $articles[] = $item;
}

foreach($articles as $articole){
	print_r($articole);
}
$html->clear(); 
unset($html);
}









$urls=array('http://m.anuntul.ro/anunturi/19&ord=date&sor=asc&p=1',
			'http://m.anuntul.ro/anunturi/19&ord=date&sor=asc&p=2',
			'http://m.anuntul.ro/anunturi/19&ord=date&sor=asc&p=3',
			'http://m.anuntul.ro/anunturi/19&ord=date&sor=asc&p=4',
			'http://m.anuntul.ro/anunturi/19&ord=date&sor=asc&p=5',

			);

foreach($urls as $url){
	$continut=get_data($url);
	echo $continut;
}

?>

un mic php scrrapper facut de mine , sper sa va fie de folos ,foloseste simple_html_doom ce poate fi luat de pe sourceforge ...

aplicatia merge combinata cu scrappy php class