<?
include '../connect.php';

$area_sql = mysql_query("SELECT * FROM `boz2` WHERE junk = '' AND `level`='1' LIMIT 1");
if(!mysql_num_rows($area_sql)){echo 'Done'; die;}
while($area_row = mysql_fetch_array($area_sql)){
$listing_website=$area_row['listing_website'];
$listing_lon=$area_row['listing_lon'];
$listing_lat=$area_row['listing_lat'];
$listing_name=addslashes($area_row['listing_name']);
$listing_address=addslashes($area_row['listing_address']);
$listing_town=addslashes($area_row['listing_town']);
$listing_postcode=$area_row['listing_postcode'];
$listing_telephone=$area_row['listing_telephone'];
$listing_openinghours=$area_row['listing_openinghours'];
$adid=$area_row['listing_id']; 

}

$listing_website = str_ireplace("http://", "", $listing_website);
echo "$adid - $listing_website";

		$url = "http://www.{$listing_website}";
		//$url = "http://www.labrasserielondon.com";
			$curl = curl_init();
            curl_setopt($curl, CURLOPT_URL, $url);
            curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
            curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true);
            curl_setopt($curl, CURLOPT_TIMEOUT, 60);
            curl_setopt($curl, CURLOPT_PROXY, $proxy);
            curl_setopt($curl, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.2) Gecko/20090729 Firefox/7 GTB5');
            $html = curl_exec($curl);
            $code = curl_getinfo($curl, CURLINFO_HTTP_CODE);
            curl_close($curl);
  

 
$url = rtrim($url, "/");
$checkurl = explode('.',$url); $checkurl = $checkurl[1]; $checkurl = "$checkurl.";

//$html = file_get_contents($url);
//Create a new DOM document
$dom = new DOMDocument;

//Parse the HTML. The @ is used to suppress any parsing errors
//that will be thrown if the $html string isn't valid XHTML.
@$dom->loadHTML($html);



//Get all links. You could also use any other tag name here,
//like 'img' or 'table', to extract other tags.
$links = $dom->getElementsByTagName('a');
$html3[] = $dom->getElementsByTagName('title')->item(0)->textContent;

preg_match('/<meta name="description" content="(.*)" \/>/i', $html, $matches);

$html3[] = $matches[1];

//Iterate over the extracted links and display their URLs
foreach ($links as $link){
    //Extract and show the "href" attribute.
    $linksadd = $link->nodeValue; 
    $linktext = $link->getAttribute('href'); 

	if ((strpos($linktext, "http://") === 0) || (strpos($linktext, "www.") === 0) ){ 
	$makethelink =  "$linktext"; 
	  } else { $linktext = ltrim($linktext, "/"); $makethelink ="{$url}/{$linktext}"; }
	  
	if ((strpos($makethelink, $checkurl) && strpos($makethelink, "#") == false)) {
	$makethelink = rtrim($makethelink, "/"); $makethelink = str_replace(array('http://','www.'), '' ,$makethelink); 
	@mysql_query("INSERT INTO `boz2` SET `listing_lon`='{$listing_lon}',`listing_lat`='{$listing_lat}', `listing_name`='{$listing_name}',`listing_address`='{$listing_address}', `listing_town`='{$listing_town}', `listing_postcode`='{$listing_postcode}', `listing_telephone`='{$listing_telephone}', `listing_website`='{$makethelink}', `level`='2'");
	
	//echo "$makethelink<br>";
	$html3[] .= "$linksadd ";
	}   
	
}

$htmlheaders =  implode($html3);
$htmlheaders = "$htmlheaders";
$html2 = strip_html_tags($html);

$html4 = "$html2 $htmlheaders";

$html4 = preg_replace( '/[^A-Z]/i', ' ', $html4); 
$html4 = preg_replace('/\s\s+/', ' ', trim($html4));

$html4 = explode(' ',$html4);

foreach ($html4 as $htmlss){
$html6[] = trim($htmlss);

}
$html6 = array_unique($html6);


foreach ($html6 as $html7){
$html8 .= trim($html7).' ';

}
$html8 = removeCommonWords($html8);
echo "<hr>$html8"; 
$html8= addslashes($html8);
mysql_query("UPDATE `boz2` SET `content`='{$html8}',`junk`='1' WHERE `listing_id`='{$adid}' LIMIT 1"); 
//echo $html4;



/*
$arrayWords = explode(' ', $html4);
// Max size of each line
$maxLineLength = 18;
// Auxiliar counters, foreach will use them
$currentLength = 0;
$index = 0;
foreach($arrayWords as $word) {
    // +1 because the word will receive back the space in the end that it loses in explode()
    $wordLength = strlen($word) + 1;
    if( ( $currentLength + $wordLength ) <= $maxLineLength )
    {
        $arrayOutput[$index] .= $word . ' ';
        $currentLength += $wordLength;
    } else {
        $index += 1;
        $currentLength = $wordLength;
        $arrayOutput[$index] = $word;
    }
}
*/

//print_r($arrayOutput);




function strip_html_tags( $text )
{
    $text = preg_replace(
        array(
            '@<head[^>]*?>.*?</head>@siu',
            '@<style[^>]*?>.*?</style>@siu',
            '@<script[^>]*?.*?</script>@siu',
            '@<object[^>]*?.*?</object>@siu',
            '@<embed[^>]*?.*?</embed>@siu',
            '@<applet[^>]*?.*?</applet>@siu',
            '@<noframes[^>]*?.*?</noframes>@siu',
            '@<noscript[^>]*?.*?</noscript>@siu',
            '@<noembed[^>]*?.*?</noembed>@siu',
			'@<a .*>.*</a>@siU',
            '@</?((address)|(blockquote)|(center)|(del))@iu',
            '@</?((div)|(h[1-9])|(ins)|(isindex)|(p)|(pre))@iu',
            '@</?((dir)|(dl)|(dt)|(dd)|(li)|(menu)|(ol)|(ul))@iu',
            '@</?((table)|(th)|(td)|(caption))@iu',
            '@</?((form)|(button)|(fieldset)|(legend)|(input))@iu',
            '@</?((label)|(select)|(optgroup)|(option)|(textarea))@iu',
            '@</?((frameset)|(frame)|(iframe))@iu',
        ),
        array(
            ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ',
            "", "~\$0", "~\$0", "~\$0", "~\$0", "~\$0",
            "~\$0", "~\$0",
        ),
        $text );
    return strip_tags( $text );
}
	
function removeCommonWords($input){
 
 	// EEEEEEK Stop words
	$commonWords = array('find','a',' able',' about',' above',' abroad',' according',' accordingly',' across',' actually',' adj',' after',' afterwards',' again',' against',' ago',' ahead',' aint',' all',' allow',' allows',' almost',' alone',' along',' alongside',' already',' also',' although',' always',' am',' amid',' amidst',' among',' amongst',' an',' and',' another',' any',' anybody',' anyhow',' anyone',' anything',' anyway',' anyways',' anywhere',' apart',' appear',' appreciate',' appropriate',' are',' arent',' around',' as',' aside',' ask',' asking',' associated',' at',' available',' away',' awfully',' b',' back',' backward',' backwards',' be',' became',' because',' become',' becomes',' becoming',' been',' before',' beforehand',' begin',' behind',' being',' believe',' below',' beside',' besides',' best',' better',' between',' beyond',' both',' brief',' but',' by',' c',' came',' can',' cannot',' cant',' caption',' cause',' causes',' certain',' certainly',' changes',' clearly',' closed',' cmon',' co',' com',' come',' comes',' concerning',' consequently',' consider',' considering',' contact',' contain',' containing',' contains',' copyright',' corresponding',' could',' couldnt',' course',' cs',' currently',' d',' dare',' darent',' definitely',' described',' designed',' despite',' did',' didnt',' different',' directly',' do',' does',' doesnt',' doing',' done',' dont',' down',' downwards',' during',' e',' each',' edu',' eg',' eight',' eighty',' either',' else',' elsewhere',' end',' ending',' enough',' entirely',' especially',' et',' etc',' even',' ever',' evermore',' every',' everybody',' everyone',' everything',' everywhere',' ex',' exactly',' example',' except',' f',' fairly',' far',' farther',' few',' fewer',' fifth',' first',' five',' followed',' following',' follows',' for',' forever',' former',' formerly',' forth',' forward',' found',' four',' fri',' from',' further',' furthermore',' g',' get',' gets',' getting',' given',' gives',' go',' goes',' going',' gone',' got',' gotten',' greater manchester',' greetings',' h',' had',' hadnt',' half',' happens',' hardly',' has',' hasnt',' have',' havent',' having',' he',' hed',' hell',' hello',' help',' hence',' her',' here',' hereafter',' hereby',' herein',' heres',' hereupon',' hers',' herself',' hes',' hi',' him',' himself',' his',' hither',' hopefully',' how',' howbeit',' however',' hundred',' i',' id',' ie',' if',' ignored',' ill',' im',' immediate',' in',' inasmuch',' inc',' indeed',' indicate',' indicated',' indicates',' inner',' inside',' insofar',' instead',' into',' inward',' is',' isnt',' it',' itd',' itll',' its',' itself',' ive',' j',' just',' k',' keep',' keeps',' kept',' know',' known',' knows',' l',' last',' lately',' later',' latter',' latterly',' least',' less',' lest',' let',' lets',' like',' liked',' likely',' likewise',' little',' look',' looking',' looks',' low',' lower',' ltd',' m',' made',' mainly',' make',' makes',' many',' may',' maybe',' maynt',' me',' mean',' meantime',' meanwhile',' merely',' might',' mightnt',' mine',' minus',' miss',' mon',' more',' moreover',' most',' mostly',' mr',' mrs',' much',' must',' mustnt',' my',' myself',' n',' name',' namely',' nd',' near',' nearly',' necessary',' need',' neednt',' needs',' neither',' never',' neverf',' neverless',' nevertheless',' new',' next',' nine',' ninety',' no',' nobody',' non',' none',' nonetheless',' noone',' no-one',' nor',' normally',' not',' nothing',' notwithstanding',' novel',' now',' nowhere',' o',' obviously',' of',' off',' often',' oh',' ok',' okay',' old',' on',' once',' one',' ones',' only',' onto',' opening hours',' opposite',' or',' other',' others',' otherwise',' ought',' oughtnt',' our',' ours',' ourselves',' out',' outside',' over',' overall',' own',' p',' particular',' particularly',' past',' per',' perhaps',' placed',' please',' plus',' possible',' presumably',' probably',' provided',' provides',' q',' que',' quite',' qv',' r',' rather',' rd',' re',' really',' reasonably',' recent',' recently',' regarding',' regardless',' regards',' relatively',' respectively',' right',' round',' s',' said',' same',' sat',' saw',' say',' saying',' says',' second',' secondly',' see',' seeing',' seem',' seemed',' seeming',' seems',' seen',' self',' selves',' sensible',' sent',' serious',' seriously',' seven',' several',' shall',' shant',' she',' shed',' shell',' shes',' should',' shouldnt',' since',' six',' so',' some',' somebody',' someday',' somehow',' someone',' something',' sometime',' sometimes',' somewhat',' somewhere',' soon',' sorry',' specified',' specify',' specifying',' still',' sub',' such',' sun',' sup',' sure',' t',' take',' taken',' taking',' tell',' tends',' th',' than',' thank',' thanks',' thanx',' that',' thatll',' thats',' thatve',' the',' their',' theirs',' them',' themselves',' then',' thence',' there',' thereafter',' thereby',' thered',' therefore',' therein',' therell',' therere',' theres',' thereupon',' thereve',' these',' they',' theyd',' theyll',' theyre',' theyve',' thing',' things',' think',' third',' thirty',' this',' thorough',' thoroughly',' those',' though',' three',' through',' throughout',' thru',' thurs',' thus',' till',' to',' together',' too',' took',' toward',' towards',' tried',' tries',' truly',' try',' trying',' ts',' tues',' twice',' two',' u',' un',' under',' underneath',' undoing',' unfortunately',' unless',' unlike',' unlikely',' until',' unto',' up',' upon',' upwards',' us',' use',' used',' useful',' uses',' using',' usually',' v',' value',' various',' versus',' very',' via',' viz',' vs',' w',' want',' wants',' was',' wasnt',' way',' we',' wed',' welcome',' well',' went',' were',' werent',' west yorkshire',' weve',' what',' whatever',' whatll',' whats',' whatve',' when',' whence',' whenever',' where',' whereafter',' whereas',' whereby',' wherein',' wheres',' whereupon',' wherever',' whether',' which',' whichever',' while',' whilst',' whither',' who',' whod',' whoever',' whole',' wholl',' whom',' whomever',' whos',' whose',' why',' will',' willing',' wish',' with',' within',' without',' wonder',' wont',' would',' wouldnt',' x',' y',' yes',' yet',' you',' youd',' youll',' your',' youre',' yours',' yourself',' yourselves',' youve',' z',' zero');
 
	return preg_replace('/\b('.implode('|',$commonWords).')\b/i','',$input);
}

echo "<meta http-equiv=\"refresh\" content=\"1\" />"; 
?>