Last active
January 25, 2016 19:41
-
-
Save juanpablocs/19b29d5ad53656bce067 to your computer and use it in GitHub Desktop.
scraping for program guide. get info in json and save result data to xml
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
// programador: [email protected] | |
// | |
class directv | |
{ | |
var $url = "http://www.directv.com.ve/movil/ProgramGuide/ProgramGuide"; | |
public function getProgramation($ids) | |
{ | |
$html = $this->html($this->url); | |
preg_match('#<table id="program-guide"(?:[^>]+)>(.*?)</table>#si', $html, $data); | |
preg_match_all('#<tr>(.*?)</tr>#si', $data[1], $tbody); | |
$results = empty($tbody[1]) ? [] : $tbody[1]; | |
$tmp = []; | |
foreach ($results as $result) { | |
$data = $this->matchInfoData($result); | |
if($data){ | |
$tmp[] = $data; | |
} | |
} | |
if(count($tmp)<1) return ['error'=>true, 'message'=>'error get scraping']; | |
if(is_array($ids) && count($ids)>0) | |
{ | |
$tmp2 = []; | |
foreach ($ids as $id) { | |
$key = array_search($id, array_column($tmp, 'channel_number')); | |
if($key !== false){ | |
$tmp2[] = $tmp[$key]; | |
} | |
} | |
$tmp = $tmp2; | |
} | |
return $tmp; | |
} | |
private function matchInfoData($html){ | |
$html = preg_replace('/\s+/', ' ', $html); | |
preg_match('#href="/movil/ProgramGuide/ProgrammingDetails\?strEventID=([^"]+)"#si', $html, $r); | |
preg_match('#<strong>([^<]+)</strong>#si', $html, $t); | |
preg_match('#<dd><strong>Duraci&\#243\;n:</strong> (.*?) </dd>#si', $html, $d); | |
if(!empty($r[1])){ | |
preg_match('#<p>([^<]+)<br />([^<]+)</p>#si', $html, $channel); | |
return [ | |
'id' => $r[1], | |
'title' => $t[1], | |
'duration' => $d[1], | |
'channel_number' => $channel[1], | |
'channel_name' => $channel[2], | |
]; | |
} | |
return false; | |
} | |
private function html($url) | |
{ | |
$ch = curl_init(); | |
curl_setopt($ch, CURLOPT_REFERER, "http://www.google.com/"); | |
curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; es-ES; rv:1.9.0.3) Gecko/2008092417 Firefox/3.0.3"); | |
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); | |
curl_setopt($ch, CURLOPT_COOKIEJAR, __dir__."/cookie.txt"); | |
curl_setopt($ch, CURLOPT_COOKIEFILE, __dir__."/cookie.txt"); | |
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 4); // controla tiempo de espera al buscar. | |
curl_setopt($ch, CURLOPT_URL, $url); | |
$buffer = curl_exec($ch); | |
curl_close($ch); | |
return $buffer; | |
} | |
} | |
// run baby | |
$ids = @$_GET['ids']; | |
$ids = ( !empty($ids) ) ? explode(',', $ids) : false; | |
$d = new directv; | |
$json = $d->getProgramation($ids); | |
if(!empty($_GET['save'])){ | |
$file = 'xmls/channels.xml'; | |
if(!is_writable($file)) | |
die('error folder o archivo no existe o no tiene permiso 777'); | |
$dom = new DomDocument('1.0', 'UTF-8'); | |
$channels = $dom->appendChild($dom->createElement('canales')); | |
for ($i = 0; $i < count($json); $i++) { | |
$channel = $dom->createElement('canal'); | |
$channels->appendChild($channel); | |
$id = $dom->createAttribute('id'); | |
$id->appendChild($dom->createTextNode($json[$i]['id'])); | |
$channel->appendChild($id); | |
$channel_name = $dom->createAttribute('canal'); | |
$channel_name->appendChild($dom->createTextNode($json[$i]['channel_name'])); | |
$channel->appendChild($channel_name); | |
$title = $dom->createAttribute('programa'); | |
$title->appendChild($dom->createTextNode($json[$i]['title'])); | |
$channel->appendChild($title); | |
$duration = $dom->createAttribute('duracion'); | |
$duration->appendChild($dom->createTextNode($json[$i]['duration'])); | |
$channel->appendChild($duration); | |
} | |
$dom->formatOutput = true; | |
$dom->saveXML(); | |
$dom->save($file); | |
die('guardo correctamente'); | |
} | |
print json_encode($json); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment