/**
* Fetches the data for a given OfDB id
*
* @author Chinamann <*****@*****.**>
* @param int OfDB id
* @return array Result data
*/
function ofdbscraperData($id)
{
global $CLIENTERROR;
global $ofdbscraperServer;
global $ofdbscraperIdPrefix;
global $cache;
global $config;
$id = preg_replace('/^' . $ofdbscraperIdPrefix . '/', '', $id);
list($id, $vid) = explode("-", $id, 2);
$data = array();
//result
$ary = array();
//temp
$ary2 = array();
//temp2
// Fetch Mainpage
$resp = httpClient(ofdbscraperContentUrl($id), $cache);
if (!$resp['success']) {
$CLIENTERROR .= $resp['error'] . "\n";
}
// add encoding
$data['encoding'] = get_response_encoding($resp);
// add engine ID -> important for non edit.php refetch
$data['imdbID'] = $ofdbscraperIdPrefix . $id;
$resp['data'] = preg_replace('/[\\r\\n\\t]/', ' ', $resp['data']);
// Titles / Year
preg_match('/<title>(.*?)<\\/title>/i', $resp['data'], $ary);
$ary[1] = preg_replace('/^OFDb[\\s-]*/', '', $ary[1]);
$ary[1] = preg_replace('/\\[.*\\]/', ' ', $ary[1]);
if (preg_match('/\\(([0-9]*)\\)/i', $ary[1], $ary2)) {
$data['year'] = trim($ary2[1]);
}
$ary[1] = preg_replace('/\\([0-9]*\\)/', ' ', $ary[1]);
$ary[1] = preg_replace('/\\s{2,}/s', ' ', $ary[1]);
// check if there is a comma sperated article at the end
if (preg_match('#(.*),\\s*(A|The|Der|Die|Das|Ein|Eine|Einer)\\s*$#i', $ary[1], $subRes)) {
$ary[1] = $subRes[2] . ' ' . $subRes[1];
}
list($t, $s) = explode(" - ", trim($ary[1]), 2);
$data['title'] = trim($t);
$data['subtitle'] = trim($s);
// Original Title
if (preg_match('/Originaltitel.*?<b>(.*?)</i', $resp['data'], $ary)) {
$data['orgtitle'] .= trim($ary[1]);
}
// Country
if (preg_match('/>Herstellungsland:.*?<b><a.*?>(.*?)<\\/a>/i', $resp['data'], $ary)) {
$data['country'] .= trim($ary[1]);
}
// Rating
if (preg_match('/Note: <span itemprop="ratingValue">([0-9\\.]+)/', $resp['data'], $ary)) {
// if (preg_match('/<br>Note:\s*([0-9\.]+)/', $resp['data'], $ary)) {
$data['rating'] = $ary[1];
}
// Cover URL
if (preg_match('#<img src="(http://img.ofdb.de/film/na.gif)"#i', $resp['data'], $ary)) {
$data['coverurl'] = "";
} else {
if (preg_match('#<img src="(http://img.ofdb.de/film/.*?\\.jpg)"#i', $resp['data'], $ary)) {
$data['coverurl'] = trim($ary[1]);
}
}
// Fetch first VID if none already selected
if (!$vid) {
if (preg_match_all('/view\\.php\\?page=fassung&fid=' . $id . '&vid=([0-9]+)".*?class="Klein">(.*?)</i', $resp['data'], $ary, PREG_SET_ORDER)) {
foreach ($ary as $row) {
if (trim($row[2]) == "K" || trim($row[2]) == "KV") {
$vid = $row[1];
break;
}
}
if (!$vid) {
$vid = $ary[1][1];
}
}
}
// IMDB ID
$data['imdbID'] = $ofdbscraperIdPrefix . "{$id}-{$vid}";
// Fetch Plot
if (preg_match('#href="(plot/[^"]+)"#i', $resp['data'], $ary)) {
$subresp = httpClient($ofdbscraperServer . '/' . $ary[1], $cache);
if (!$resp['success']) {
$CLIENTERROR .= $subresp['error'] . "\n";
}
$subresp['data'] = preg_replace('/[\\r\\n\\t]/', ' ', $subresp['data']);
//ofdbDbg($subresp['data'],false);
if (preg_match('#</b><br><br>(.*?)</font></p>#i', $subresp['data'], $ary)) {
$ary[1] = preg_replace('/\\s{2,}/s', ' ', $ary[1]);
$ary[1] = preg_replace('#<(br|p)[ /]*>#i', "\n", $ary[1]);
$data['plot'] = trim($ary[1]);
//$data['plot'] = "aeääääaaaä";
}
}
// Fetch Details
$resp = httpClient(ofdbscraperDetailUrl($id), $cache);
if (!$resp['success']) {
$CLIENTERROR .= $resp['error'] . "\n";
}
$resp['data'] = preg_replace('/[\\r\\n\\t]/', ' ', $resp['data']);
// Director
if (preg_match('/<b><i>Regie<\\/i><\\/b>.*?<table.*?>(.*?)<\\/table>/i', $resp['data'], $ary)) {
if (preg_match_all('/class="Daten"><a.*?>(.*?)<\\/a>/i', $ary[1], $ary2, PREG_SET_ORDER)) {
foreach ($ary2 as $row) {
$data['director'] .= trim($row[1]) . ', ';
}
$data['director'] = preg_replace('/, $/', '', $data['director']);
}
}
// Cast
if (preg_match('/<b><i>Darsteller<\\/i><\\/b>.*?<table.*?>(.*)<\\/table>/', $resp['data'], $ary)) {
// dirty workaround for (.*?) failed on very long match groups issue (tested at PHP 5.2.5.5)
// e.g.: ofdb:7749-111320 (Angel - Jäger der Finsternis)
$ary[1] = preg_replace('#</table.*#', '', $ary[1]);
if (preg_match_all('/class="Daten"><a(.*?)">(.*?)<\\/a>.*?<\\/td> <td.*?<\\/td> <td[^>]*>(.*?)<\\/td>/i', $ary[1], $ary2, PREG_SET_ORDER)) {
foreach ($ary2 as $row) {
$actor = trim(strip_tags($row[2]));
$actorid = "";
if (!empty($row[1])) {
if (preg_match('#href="view.php\\?page=person&id=([0-9]*)#i', $row[1], $idAry)) {
$actorid = $ofdbscraperIdPrefix . $idAry[1];
}
}
$character = "";
if (!empty($row[3])) {
if (preg_match('#class="Normal">... ([^<]*)<#i', $row[3], $charAry)) {
$character = trim(strip_tags($charAry[1]));
}
}
$data['cast'] .= "{$actor}::{$character}::{$actorid}\n";
}
}
}
// Genres
$genres = array('Amateur' => '', 'Eastern' => '', 'Experimentalfilm' => '', 'Mondo' => '', 'Kampfsport' => 'Sport', 'Biographie' => 'Biography', 'Katastrophen' => 'Thriller', 'Krimi' => 'Crime', 'Science-Fiction' => 'Sci-Fi', 'Kinder-/Familienfilm' => 'Family', 'Dokumentation' => 'Documentary', 'Action' => 'Action', 'Drama' => 'Drama', 'Abenteuer' => 'Adventure', 'Historienfilm' => 'History', 'Kurzfilm' => 'Short', 'Liebe/Romantik' => 'Romance', 'Heimatfilm' => 'Romance', 'Grusel' => 'Horror', 'Horror' => 'Horror', 'Erotik' => 'Adult', 'Hardcore' => 'Adult', 'Sex' => 'Adult', 'Musikfilm' => 'Musical', 'Animation' => 'Animation', 'Fantasy' => 'Fantasy', 'Trash' => 'Horror', 'Komödie' => 'Comedy', 'Krieg' => 'War', 'Mystery' => 'Mystery', 'Thriller' => 'Thriller', 'Tierfilm' => 'Documentary', 'Western' => 'Western', 'TV-Serie' => '', 'TV-Mini-Serie' => '', 'Sportfilm' => 'Sport', 'Splatter' => 'Horror', 'Manga/Anime' => 'Animation');
if (preg_match('/>Genre\\(s\\)\\:.*?<b>(.*?)<\\/b>/i', $resp['data'], $ary)) {
if (preg_match_all('/<a.*?>(.*?)<\\/a>/i', $ary[1], $ary2, PREG_SET_ORDER)) {
foreach ($ary2 as $row) {
$genre = trim(html_entity_decode($row[1]));
$genre = strip_tags($genre);
if (!$genre) {
continue;
}
if (isset($genres[$genre])) {
$data['genres'][] = $genres[$genre];
}
}
}
}
// Fetch Version
$resp = httpClient(ofdbscraperVersionUrl($id, $vid), $cache);
if (!$resp['success']) {
$CLIENTERROR .= $resp['error'] . "\n";
}
$resp['data'] = preg_replace('/[\\r\\n\\t]/', ' ', $resp['data']);
// FSK
$fsks = array('FSK o.A.' => '0', 'FSK 6' => '6', 'FSK 12' => '12', 'FSK 16' => '16', 'FSK 18' => '18', 'Keine Jugendfreigabe' => '18', 'SPIO/JK' => '18', 'juristisch geprüft' => '', 'ungeprüft' => '');
if (preg_match('/>Freigabe:<.*?<b>(.*?)<\\/tr>/i', $resp['data'], $ary)) {
$fsk = trim(html_entity_decode($ary[1]));
$fsk = strip_tags($fsk);
if (isset($fsks[$fsk])) {
$data['fsk'] = $fsks[$fsk];
}
}
// Languages
// Languages (as Array)
$laguages = array('arabisch' => 'arabic', 'bulgarisch' => 'bulgarian', 'chinesisch' => 'chinese', 'tschechisch' => 'czech', 'dänisch' => 'danish', 'holändisch' => 'dutch', 'englisch' => 'english', 'französisch' => 'french', 'deutsch' => 'german', 'griechisch' => 'greek', 'ungarisch' => 'hungarian', 'isländisch' => 'icelandic', 'indisch' => 'indian', 'israelisch' => 'israeli', 'italienisch' => 'italian', 'japanisch' => 'japanese', 'koreanisch' => 'korean', 'norwegisch' => 'norwegian', 'polnisch' => 'polish', 'portugisisch' => 'portuguese', 'rumänisch' => 'romanian', 'russisch' => 'russian', 'serbisch' => 'serbian', 'spanisch' => 'spanish', 'schwedisch' => 'swedish', 'thailändisch' => 'thai', 'türkisch' => 'turkish', 'vietnamesisch' => 'vietnamese', 'kantonesisch' => 'cantonese', 'katalanisch' => 'catalan', 'zypriotisch' => 'cypriot', 'zyprisch' => 'cypriot', 'esperanto' => 'esperanto', 'gälisch' => 'gaelic', 'hebräisch' => 'hebrew', 'hindi' => 'hindi', 'jüdisch' => 'jewish', 'lateinisch' => 'latin', 'mandarin' => 'mandarin', 'serbokroatisch' => 'serbo-croatian', 'somalisch' => 'somali');
$lang_list = array();
// Runtime
if (preg_match('/>Laufzeit:<.*?<b>(.*?)\\s*Min/i', $resp['data'], $ary)) {
$ary[1] = preg_replace('/:.*/', '', $ary[1]);
$data['runtime'] = trim($ary[1]);
}
return $data;
}
/**
* At the moment - oct 2010 - most imdb-pages were changed to utf8,
* but e.g. fullcredits are still iso-8859-1
* so data is recoded here
*/
function imdbFixEncoding($data, $resp)
{
$result = $resp;
$pageEncoding = get_response_encoding($resp);
if ($pageEncoding != $data['encoding']) {
$result['data'] = iconv($pageEncoding, $data['encoding'], html_entity_decode_all($resp['data']));
}
return $result;
}
/**
* Fetches the data for a given Allocine-ID
*
* @author Douglas Mayle <*****@*****.**>
* @author Tiago Fonseca <*****@*****.**>
* @param int imdb-ID
* @return array Result data
*/
function allocineData($imdbID)
{
global $allocineServer;
global $allocineIdPrefix;
global $CLIENTERROR;
$allocineID = preg_replace('/^' . $allocineIdPrefix . '/', '', $imdbID);
// fetch mainpage
$resp = httpClient($allocineServer . '/film/fichefilm_gen_cfilm=' . $allocineID . '.html', 1);
// added trailing / to avoid redirect
if (!$resp['success']) {
$CLIENTERROR .= $resp['error'] . "\n";
}
$data = array();
// result
$ary = array();
// temp
// add encoding
$data['encoding'] = get_response_encoding($resp);
// Allocine ID
$data['id'] = "allocine:" . $allocineID;
// We remove all the multiples spaces and line breakers
$resp['data'] = preg_replace('/[\\s]{2,}/', '', $resp['data']);
/*
Title and subtitle
*/
preg_match('#<h1.*?>(.*?)</h1>#si', $resp['data'], $ary);
list($t, $s) = explode(" - ", trim($ary[1]), 2);
// Some bugs when using html_clean function --> using html_clean_utf8
$data['title'] = html_clean_utf8($t);
$data['subtitle'] = html_clean_utf8($s);
/*
Year
*/
preg_match('/<a.*? href="\\/film\\/tous\\/decennie.*?year=(\\d+)">(\\d+)<\\/a>/i', $resp['data'], $ary);
if (!empty($ary[1])) {
$data['year'] = trim($ary[1]);
}
/*
Release Date
added to the comments
*/
preg_match('#<a.*? href="/film/agenda\\.html\\?week=\\d+\\-\\d+\\-\\d+">(.*)</a>#i', $resp['data'], $ary);
$release_date = "";
if (!empty($ary[1])) {
$release_date = "\r\nDate de sortie cinéma : " . html_clean_utf8($ary[1]);
}
/*
Cover URL
*/
preg_match('#<div class="colleft">\\s*?<div class="vmargin20b">\\s*?<div class=\\"poster\\">\\s*?<em class=\\"imagecontainer\\">\\s*?<a .*?>\\s*?<img.*?src=\'(.*?)\'.*?>#si', $resp['data'], $ary);
$data['coverurl'] = trim($ary[1]);
/*
Runtime
*/
#Durée : 02h13min
preg_match('/Durée :\\s*?(\\d+)h(\\d+)\\s*?min/i', $resp['data'], $ary);
$hours = preg_replace('/,/', '', trim($ary[1]));
$minutes = preg_replace('/,/', '', trim($ary[2]));
$data['runtime'] = $hours * 60 + $minutes;
/*
Director
*/
preg_match('#Réalisé par\\s*<span.*?><a.*?rel="v:directedBy".*?href=\'/personne/fichepersonne_gen_cpersonne=\\d+\\.html\' title=\'.*\'>(.*)</a></span>#i', $resp['data'], $ary);
$data['director'] = trim($ary[1]);
/*
Rating
*/
preg_match('#<p class="withstars"><a.*?href="/film/critiquepublic_gen_cfilm=\\d+\\.html"><img.*?class="stareval.*?".*?<span class=\\"moreinfo\\">\\((.*)\\)</span></p>#i', $resp['data'], $ary);
$data['rating'] = trim($ary[1]);
$data['rating'] = str_replace(",", ".", $data['rating']);
// Allocine rating is based on 5, imdb is based on 10
$data['rating'] = $data['rating'] * 2;
/*
Countries
*/
// Countries in English
$map_countries = array('allemand' => 'Germany', 'américain' => 'USA', 'arménien' => 'Armenia', 'argentin' => 'Argentina', 'sud-africain' => 'South Africa', 'australien' => 'Australia', 'belge' => 'Belgium', 'britannique' => 'UK', 'bulgare' => 'Bulgaria', 'canadien' => 'Canada', 'chinois' => 'China', 'coréen' => 'South Korea', 'danois' => 'Denmark', 'espagnol' => 'Spain', 'français' => 'France', 'grec' => 'Greece', 'hollandais' => 'Netherlands', 'hong-kongais' => 'Hong-Kong', 'hongrois' => 'Hungary', 'indien' => 'India', 'irlandais' => 'Republic of Ireland', 'islandais' => 'Iceland', 'israëlien' => 'Israel', 'italien' => 'Italy', 'japonais' => 'Japan', 'luxembourgeois' => 'Luxembourg', 'mexicain' => 'Mexico', 'norvégien' => 'Norge', 'néo-zélandais' => 'New Zealand', 'polonais' => 'Poland', 'portugais' => 'Portugal', 'roumain' => 'Romania', 'russe' => 'Russia', 'serbe' => 'Serbia', 'suédois' => 'Sweden', 'taïwanais' => 'Taiwan', 'tchèque' => 'Czech Republic', 'thaïlandais' => 'Thailand', 'turc' => 'Turkey', 'ukrainien' => 'Ukraine', 'vietnamien' => 'Vietnam');
if (preg_match_all('#Long\\-métrage\\s*?<a.*?href=".*?">(.*?)</a>#si', $resp['data'], $ary, PREG_PATTERN_ORDER) > 0) {
$originlist = explode(",", trim(join(', ', $ary[1])));
foreach ($originlist as $origin) {
$mapped_country_found = '';
foreach ($map_countries as $pattern_c => $mapped_country) {
if (preg_match_all('/' . $pattern_c . '/i', $origin, $junk, PREG_PATTERN_ORDER) > 0) {
$mapped_country_found = $mapped_country;
break;
}
}
if ($data['country'] == '') {
$data['country'] = $mapped_country_found;
} elseif (stristr($data['country'], $mapped_country_found) == TRUE) {
$data['country'] = $data['country'];
} else {
$data['country'] = $data['country'] . ', ' . $mapped_country_found;
}
}
}
/*
Plot
*/
preg_match('#<div id="synopsis_full">\\s*?<p>\\s*?<span class=\\"bold\\">Synopsis \\: </span>\\s*?<span property="v:summary">(.*?)</span>#is', $resp['data'], $ary);
if (!empty($ary[1])) {
$data['plot'] = $ary[1];
$data['plot'] = html_clean_utf8($data['plot']);
// And cleanup
$data['plot'] = trim($data['plot']);
$data['plot'] = preg_replace('/[\\n\\r]/', ' ', $data['plot']);
$data['plot'] = preg_replace('/ /', ' ', $data['plot']);
}
/*
Genres (as Array)
*/
$map_genres = array('Action' => 'Action', 'Animation' => 'Animation', 'Arts Martiaux' => 'Action', 'Aventure' => 'Adventure', 'Biopic' => 'Biography', 'Bollywood' => 'Musical', 'Classique' => '-', 'Comédie Dramatique' => 'Drama', 'Comédie musicale' => 'Musical', 'Comédie' => 'Comedy', 'Dessin animé' => 'Animation', 'Divers' => '-', 'Documentaire' => 'Documentary', 'Drame' => 'Drama', 'Epouvante-horreur' => 'Horror', 'Erotique' => 'Adult', 'Espionnage' => '-', 'Famille' => 'Family', 'Fantastique' => 'Fantasy', 'Guerre' => 'War', 'Historique' => 'History', 'Horreur' => 'Horror', 'Musique' => 'Musical', 'Policier' => 'Crime', 'Péplum' => 'History', 'Romance' => 'Romance', 'Science fiction' => 'Sci-Fi', 'Thriller' => 'Thriller', 'Western' => 'Western');
if (preg_match_all('#Genre :(.*?)</a>\\s*?<br#si', $resp['data'], $ary, PREG_PATTERN_ORDER) > 0) {
$genrelist = explode(",", trim(join(', ', $ary[1])));
foreach ($genrelist as $genre) {
$mapped_genre_found = '';
foreach ($map_genres as $pattern => $mapped_genre) {
if (preg_match_all('/' . $pattern . '/i', $genre, $junk, PREG_PATTERN_ORDER) > 0) {
$mapped_genre_found = $mapped_genre;
break;
}
}
$data['genres'][] = $mapped_genre_found != '-' ? $mapped_genre_found : trim($genre);
}
}
/*
Original Title
*/
preg_match('#Titre original : <span class=\\"purehtml\\"><em>(.*)</em></span>#', $resp['data'], $ary);
$data['origtitle'] = trim($ary[1]);
/*
Title and Subtitle
If sub-title is blank, we'll try to fill in the original title for foreign films.
*/
if (empty($data['subtitle'])) {
if ($data['origtitle']) {
$data['subtitle'] = $data['title'];
$data['title'] = $data['origtitle'];
}
}
/*
CREDITS AND CAST
*/
// fetch credits
// Another HTML page
$resp = httpClient($allocineServer . '/film/casting_gen_cfilm=' . $allocineID . '.html', 1);
if (!$resp['success']) {
$CLIENTERROR .= $resp['error'] . "\n";
}
// We remove all the multiples spaces and line breakers
$resp['data'] = preg_replace('/[\\s]{2,}/', '', $resp['data']);
if (preg_match('#<h2>Acteurs, rôles, personnages</h2>(.*?)<div class="titlebar">\\s*?<a class="anchor" id=\'actors\'></a>\\s*?<h2>#is', $resp['data'], $Section)) {
# the big ones with image
/*
<div class="titlebar">
<h3>
<a href="/personne/fichepersonne_gen_cpersonne=5568.html">Liam Neeson</a>
</h3>
</div>
<p>
Rôle : Qui-Gon Jinn
</p>
<div class="spacer"></div>
*/
preg_match_all('#<div class="titlebar">\\s*?<h3>\\s*?<a href="/personne/fichepersonne_gen_cpersonne=(\\d+?).html">(.*?)</a>\\s*?</h3>\\s*?</div>\\s*?<p>\\s*Rôle : (.*?)\\s*</p>#is', $Section[1], $ary, PREG_PATTERN_ORDER);
$count = 0;
while (isset($ary[1][$count])) {
$cast .= $ary[2][$count] . "::" . $ary[3][$count] . "::allocine:" . $ary[1][$count] . "\n";
$count++;
}
# extended cast - without image
/*
<tr class="odd">
<td>
Shmi Skywalker
</td>
<td>
<a href="/personne/fichepersonne_gen_cpersonne=14279.html">Pernilla August</a>
</td>
</tr>
*/
preg_match_all('#<tr.*?>\\s*?<td>\\s*(.*?)\\s*</td>\\s*?<td>\\s*?<a href="/personne/fichepersonne_gen_cpersonne=(\\d+).html">(.*?)</a>\\s*?</td>#si', $Section[1], $ary, PREG_PATTERN_ORDER);
$count = 0;
while (isset($ary[1][$count])) {
$cast .= $ary[3][$count] . "::" . $ary[1][$count] . "::allocine:" . $ary[2][$count] . "\n";
$count++;
}
$data['cast'] = trim($cast);
}
/*
Comments
*/
// By default
$data['language'] = 'french';
// Another HTML page
$resp = httpClient($allocineServer . '/film/fichefilm-' . $allocineID . '/technique/', 1);
if (!$resp['success']) {
$CLIENTERROR .= $resp['error'] . "\n";
}
// We remove all the multiples spaces and line breakers
$resp['data'] = preg_replace('/[\\s]{2,}/', '', $resp['data']);
// Technical informations as comment
preg_match('#<div class=\\"rubric\\">\\s*?<div class=\\"vpadding20b\\">\\s*(.*?)\\s*</div>\\s*?</div>#si', $resp['data'], $ary);
if (!empty($ary[1])) {
$data['comment'] = $ary[1];
$data['comment'] = str_replace("Tourné en :", "Tourné en : ", $data['comment']);
// Adding the release date in theater
$data['comment'] = $data['comment'] . $release_date;
// Search the language
// Default language
$data['language'] = "french";
if (preg_match('#<p>\\s*?<span class=\\"bold\\">Tourné en :</span>\\s*(.*?)\\s*</p>#si', $resp['data'], $ary)) {
$data['language'] = $ary[1];
// Converting languages from french to english
$map_languages = array('Anglais' => 'english', 'Français' => 'french', 'Allemand' => 'german', 'Italien' => 'italian', 'Espagnol' => 'spanish', 'Coréen' => 'Korean', 'Roumain' => 'romanian', 'Autre' => 'french', 'Hindi' => 'hindi', 'Arabe' => 'arabic', 'Thaï' => 'thai', 'Danois' => 'danish', 'Suédois' => 'swedish', 'Tchèque' => 'czech', 'Japonais' => 'japanese', 'Portugais' => 'portuguese', 'Norvégien' => 'norwegian', 'Bulgare' => 'bulgarian', 'Grec' => 'greek', 'Hongrois' => 'hungarian', 'Turc' => 'turkish', 'Islandais' => 'icelandic', 'Polonais' => 'polish', 'Russe' => 'russian', 'Ukrainien' => 'ukrainian', 'Serbe' => 'serbian', 'Vietnamien' => 'vietnamese', 'Afrikaans' => 'afrikaans');
foreach ($map_languages as $pattern => $map_lang) {
$data['language'] = str_replace($pattern, $map_lang, $data['language']);
}
}
}
// Return the data collected
return $data;
}
/**
* Fetches the data for a given Dvdfr-ID
*
* @param int IMDB-ID
* @return array Result data
*/
function dvdfrData($imdbID)
{
global $dvdfrServer;
global $CLIENTERROR;
$data = array();
// result
$ary = array();
// temp
$para['useragent'] = 'VideoDB (http://www.videodb.net/)';
// fetch mainpage
$resp = httpClient(dvdfrContentUrl($imdbID), 1, $para);
// added trailing / to avoid redirect
if (!$resp['success']) {
$CLIENTERROR .= $resp['error'] . "\n";
}
// add encoding
$data['encoding'] = get_response_encoding($resp);
// See http://www.dvdfr.com/api/dvd.php?id=2869 for output
// Titles
preg_match('#<titres>\\s*<fr>(.+?)</fr>\\s*<vo>(.+?)</vo>#is', $resp['data'], $ary);
$data['title'] = mb_convert_case(dvdfrCleanStr($ary[1]), MB_CASE_TITLE, $data['encoding']);
$data['subtitle'] = mb_convert_case(dvdfrCleanStr($ary[2]), MB_CASE_TITLE, $data['encoding']);
// I found: <div class="dvd_titleinfo">USA, Royaume-Uni , 2004<br />R&D TV, Sky TV, USA Cable Entertainment</div>
preg_match('#<listePays>\\s*<pays.*?>(.+?)</pays>#is', $resp['data'], $ary);
$data['country'] = dvdfrCleanStr($ary[1]);
preg_match('#<annee>(\\d+)</annee>#is', $resp['data'], $ary);
$data['year'] = dvdfrCleanStr($ary[1]);
// Cover URL
preg_match('#<cover>(.*?)</cover>#i', $resp['data'], $ary);
$data['coverurl'] = trim($ary[1]);
// Runtime
preg_match('#<duree>(\\d+)</duree>#i', $resp['data'], $ary);
$data['runtime'] = $ary[1];
// Director (only the first one)
preg_match('#<star type="R.*?alisateur" id="\\d+">(.*?)</star>#i', $resp['data'], $ary);
$data['director'] = dvdfrCleanStr($ary[1]);
// Plot
preg_match('#<synopsis>(.*?)</synopsis>#is', $resp['data'], $ary);
if (!empty($ary[1])) {
$data['plot'] = $ary[1];
// And cleanup
$data['plot'] = preg_replace('/[\\n\\r]/', ' ', $data['plot']);
$data['plot'] = preg_replace('/\\s+/', ' ', $data['plot']);
$data['plot'] = dvdfrCleanStr($data['plot']);
}
// maps dvdfr category ids to videodb category names
$category_map = array("1" => "Action", "2" => "Animation", "61" => "", "3" => "Adventure", "72" => "", "81" => "Musical", "4" => "Comedy", "5" => "Drama", "6" => "Musical", "74" => "Romance", "7" => "Music", "8" => "", "9" => "Short", "10" => "Documentary", "78" => "Documentary", "11" => "Music", "12" => "", "13" => "Documentary", "14" => "Drama", "73" => "Drama", "15" => "Adult", "16" => "Action", "17" => "Sci-Fi", "30" => "Musical", "83" => "Sport", "18" => "War", "19" => "Musical", "20" => "History", "21" => "Horror", "22" => "Comedy", "23" => "Animation", "24" => "Adult", "25" => "Music", "79" => "", "26" => "Music", "27" => "Action", "28" => "", "57" => "", "29" => "Documentary", "32" => "Music", "71" => "Music", "31" => "Music", "33" => "War", "34" => "Crime", "54" => "", "76" => "Music", "55" => "Music", "56" => "Sci-Fi", "60" => "", "75" => "", "58" => "", "59" => "", "62" => "", "63" => "Sport", "82" => "Sport", "64" => "Music", "65" => "", "66" => "Thriller", "67" => "Music", "68" => "Music", "69" => "Documentary", "70" => "Western", "Science Fiction" => "Sci-Fi");
// Genres (as Array)
if (preg_match_all('#<categorie>(.*?)</categorie>#i', $resp['data'], $ary, PREG_PATTERN_ORDER) > 0) {
$count = 0;
while (isset($ary[1][$count])) {
$data['genres'][] = $category_map[dvdfrCleanStr($ary[1][$count])];
$count++;
}
}
// Cast
if (preg_match('#<stars>(.*)</stars>#is', $resp['data'], $Section)) {
preg_match_all('#<star type="Acteur" id="(\\d+)">(.*?)</star>#i', $Section[1], $ary, PREG_PATTERN_ORDER);
for ($i = 0; $i < sizeof($ary[0]); $i++) {
$cast .= dvdfrCleanStr($ary[2][$i]) . '::::dvdfr' . dvdfrCleanStr($ary[1][$i]) . "\n";
#$cast .= "$actor::$character::$imdbIdPrefix$actorid\n";
}
$data['cast'] = dvdfrCleanStr($cast);
}
#// Convert ISO to UTF8
#$encoding = $data['encoding'];
#foreach( $data as $k => $v ) {
# $data[$k] = mb_convert_encoding(trim($v),'UTF-8',$encoding);
#}
return $data;
}
/**
* Search an image on isohunt
*
* Searches for a given title on the isohunt and returns the found links in
* an array
*
* @param string The search string
* @return array Associative array with id and title
*/
function isohuntSearch($title)
{
global $CLIENTERROR;
global $isohuntServer;
$data = array();
$url = $isohuntServer . '/js/rss/' . urlencode($title);
$resp = httpClient($url, 1);
if (!$resp['success']) {
$CLIENTERROR .= $resp['error'] . "\n";
}
// add encoding
$data['encoding'] = get_response_encoding($resp);
$xml = @simplexml_load_string($resp['data']);
/*
SimpleXMLElement Object
(
[@attributes] => Array
(
[version] => 2.0
)
[channel] => SimpleXMLElement Object
(
[title] => isoHunt > All > scrubs
[link] => http://isohunt.com
[description] => BitTorrent search feeds > All > scrubs
[language] => en-us
[category] => All
[ttl] => 60
[image] => SimpleXMLElement Object
(
[title] => isoHunt > All > scrubs
[url] => http://isohunt.com/img/buttons/isohunt-02.gif
[link] => http://isohunt.com/
[width] => 157
[height] => 45
)
[lastBuildDate] => Sun, 22 Mar 2009 22:47:21 GMT
[pubDate] => Sun, 22 Mar 2009 22:47:21 GMT
[item] => Array
(
[0] => SimpleXMLElement Object
(
[title] => Scrubs. S08E12. HDTV. XviD [3/9]
[link] => http://isohunt.com/torrent_details/72045453/scrubs?tab=summary
[guid] => http://isohunt.com/torrent_details/72045453/scrubs?tab=summary
[enclosure] => SimpleXMLElement Object
(
[@attributes] => Array
(
[url] => http://isohunt.com/download/72045453/scrubs.torrent
[length] => 354292859
[type] => application/x-bittorrent
)
)
[description] => <h3>Bit Torrent details:</h3>Category: TV<br>Original site: http://thepiratebay.org/<br>Size: 337.88 MB, in 2 files<br><br>Seeds: 3 | Leechers: 9 | Downloads: 16<p>Description:<br>Torrent downloaded from http://thepiratebay.org
[pubDate] => Fri, 20 Mar 2009 22:55:22 GMT
)
*/
if (is_object($xml)) {
foreach ($xml->channel->item as $row) {
$res = array();
$res['title'] = (string) $row->title;
# $res['imgsmall'] = $img;
# $res['coverurl'] = $img;
$res['url'] = (string) $row->link;
$res['torrent'] = (string) $row->enclosure['url'];
$res['filesize'] = (string) $row->enclosure['length'];
$res['subtitle'] = sizetostring($res['filesize'], 1);
$res['plot'] = (string) $row->description;
if (preg_match('#(Seeds: .+?)<#', $res['plot'], $m)) {
$res['sl'] = $m[1];
}
# dump($res);
$data[] = $res;
}
}
# dump($data);
return $data;
}
