/**
* Fetches the data for a given IMDB-ID
*
* @author Tiago Fonseca <*****@*****.**>
* @author Victor La <*****@*****.**>
* @author Roland Obermayer <*****@*****.**>
* @param int IMDB-ID
* @return array Result data
*/
function imdbData($imdbID)
{
global $imdbServer;
global $imdbIdPrefix;
global $CLIENTERROR;
global $cache;
$imdbID = preg_replace('/^' . $imdbIdPrefix . '/', '', $imdbID);
$data = array();
// result
$ary = array();
// temp
// fetch mainpage
$resp = httpClient($imdbServer . '/title/tt' . $imdbID . '/', $cache);
// added trailing / to avoid redirect
if (!$resp['success']) {
$CLIENTERROR .= $resp['error'] . "\n";
}
// add encoding
$data['encoding'] = get_response_encoding($resp);
// Check if it is a TV series episode
if (preg_match('/<div id="titleTVEpisodes"/i', $resp['data'])) {
#if (preg_match('/<div id="titleTVSeries"/i', $resp['data'])) {
$data['istv'] = 1;
# find id of Series
preg_match('/<a href="\\/title\\/tt(\\d+)\\/episodes.*?" title="Full Episode List.*"/i', $resp['data'], $ary);
$data['tvseries_id'] = trim($ary[1]);
}
// Titles and Year
if ($data['istv']) {
preg_match('/<meta name="title" content=""(.*?)"\\s+(.*?)(.TV episode .*?)?( - IMDB)?"/si', $resp['data'], $ary);
$data['title'] = trim($ary[1]);
$data['subtitle'] = trim($ary[2]);
#dlog($ary);
if (preg_match('/<h1 class="header".*?>.*?<span class="nobr">\\(.*?(\\d\\d\\d\\d)\\)</si', $resp['data'], $ary)) {
$data['year'] = $ary[1];
}
} else {
preg_match('/<meta name="title" content="(IMDb - )?(.*?) \\(.*?(\\d\\d\\d\\d).*?\\)( - IMDb)?" \\/>/si', $resp['data'], $ary);
#dlog($ary);
$data['year'] = trim($ary[3]);
# split title - subtitle
list($t, $s) = explode(' - ', trim($ary[2]), 2);
$data['title'] = trim($t);
$data['subtitle'] = trim($s);
}
# orig. title
preg_match('/<span class="title-extra".+?>\\s*"?(.*?)"?\\s*<i>\\(original title\\)<\\/i>\\s*</si', $resp['data'], $ary);
$data['origtitle'] = trim($ary[1]);
// Cover URL
$data['coverurl'] = imdbGetCoverURL($resp['data']);
// MPAA Rating
preg_match('/<span\\s?itemprop="contentRating">(.*?)</is', $resp['data'], $ary);
$data['mpaa'] = trim($ary[1]);
// UK BBFC Rating
# no longer appears on main page
#preg_match('/>\s*UK:(.*?)<\/a>\s+/s', $resp['data'], $ary);
#$data['bbfc'] = trim($ary[1]);
// Runtime
// many but not all yet have new <time itemprop="duration"> tag
preg_match('/itemprop="duration".*?>(\\d+)\\s+min<\\//si', $sresp['data'], $ary);
if (!$ary) {
preg_match('/Runtime:?<\\/h4>.*?>(\\d+)\\s+min/si', $resp['data'], $ary);
}
$data['runtime'] = preg_replace('/,/', '', trim($ary[1]));
// Director
preg_match('/Directors?:\\s*<\\/h4>(.+?)<\\/div>/si', $resp['data'], $ary);
preg_match_all('/<a.*?href="\\/name\\/nm.+?".*?>(.+?)<\\/a>/si', $ary[1], $ary, PREG_PATTERN_ORDER);
// TODO: Update templates to use multiple directors
$data['director'] = trim(join(', ', $ary[1]));
// Rating
preg_match('/<span .*? itemprop="ratingValue">([\\d\\.]+)<\\/span>/si', $resp['data'], $ary);
$data['rating'] = trim($ary[1]);
// Countries
preg_match('/Country:\\s*<\\/h4>(.+?)<\\/div>/si', $resp['data'], $ary);
preg_match_all('/<a.*?href="\\/country\\/.+?".*?>(.+?)<\\/a>/si', $ary[1], $ary, PREG_PATTERN_ORDER);
$data['country'] = trim(join(', ', $ary[1]));
// Languages
preg_match('/Languages?:\\s*<\\/h4>(.+?)<\\/div>/si', $resp['data'], $ary);
preg_match_all('/<a.*?href="\\/language\\/.+?".*?>(.+?)<\\/a>/si', $ary[1], $ary, PREG_PATTERN_ORDER);
$data['language'] = trim(strtolower(join(', ', $ary[1])));
// Genres (as Array)
preg_match('/Genres:\\s*<\\/h4>(.+?)<\\/div>/si', $resp['data'], $ary);
preg_match_all('/<a.*?href="\\/genres?\\/.+?".*?>(.+?)<\\/a>/si', $ary[1], $ary, PREG_PATTERN_ORDER);
foreach ($ary[1] as $genre) {
$data['genres'][] = trim($genre);
}
// for Episodes - try to get some missing stuff from the main series page
if ($data['istv'] and (!$data['runtime'] or !$data['country'] or !$data['language'] or !$data['coverurl'])) {
$sresp = httpClient($imdbServer . '/title/tt' . $data['tvseries_id'] . '/', $cache);
if (!$sresp['success']) {
$CLIENTERROR .= $resp['error'] . "\n";
}
# runtime
if (!$data['runtime']) {
preg_match('/itemprop="duration".*?>(\\d+)\\s+min<\\//si', $sresp['data'], $ary);
if (!$ary) {
preg_match('/Runtime:?<\\/h4>.*?>(\\d+)\\s+min/si', $resp['data'], $ary);
}
$data['runtime'] = preg_replace('/,/', '', trim($ary[1]));
}
# country
if (!$data['country']) {
preg_match('/Country:\\s*<\\/h4>(.+?)<\\/div>/si', $sresp['data'], $ary);
preg_match_all('/<a.*?href="\\/country\\/.+?".*?>(.+?)<\\/a>/si', $ary[1], $ary, PREG_PATTERN_ORDER);
$data['country'] = trim(join(', ', $ary[1]));
}
# language
if (!$data['language']) {
preg_match('/Languages?:\\s*<\\/h4>(.+?)<\\/div>/si', $sresp['data'], $ary);
preg_match_all('/<a.*?href="\\/language\\/.+?".*?>(.+?)<\\/a>/si', $ary[1], $ary, PREG_PATTERN_ORDER);
$data['language'] = trim(strtolower(join(', ', $ary[1])));
}
# cover
if (!$data['coverurl']) {
$data['coverurl'] = imdbGetCoverURL($sresp['data']);
}
}
// Plot
preg_match('/<h2>Storyline<\\/h2>.*?<p>(.*?)</si', $resp['data'], $ary);
$data['plot'] = $ary[1];
// Fetch credits
$resp = imdbFixEncoding($data, httpClient($imdbServer . '/title/tt' . $imdbID . '/fullcredits', $cache));
if (!$resp['success']) {
$CLIENTERROR .= $resp['error'] . "\n";
}
// Cast
if (preg_match('#<table class="cast_list">(.*)#si', $resp['data'], $match)) {
// no idea why it does not always work with (.*?)</table
// could be some maximum length of .*?
// anyways, I'm cutting it here
$casthtml = substr($match[1], 0, strpos($match[1], '</table'));
if (preg_match_all('#<td .*? itemprop="actor".*?>\\s+<a href="/name/(nm\\d+)/?.*?".*?>(.*?)</a>.*?<td class="character">(.*?)</td>#si', $casthtml, $ary, PREG_PATTERN_ORDER)) {
for ($i = 0; $i < sizeof($ary[0]); $i++) {
$actorid = trim(strip_tags($ary[1][$i]));
$actor = trim(strip_tags($ary[2][$i]));
$character = trim(preg_replace('/\\s+/', ' ', strip_tags(preg_replace('/ /', ' ', $ary[3][$i]))));
$cast .= "{$actor}::{$character}::{$imdbIdPrefix}{$actorid}\n";
}
}
// remove html entities and replace with simple space
$data['cast'] = html_clean_utf8($cast);
// sometimes appearing in series (e.g. Scrubs)
$data['cast'] = preg_replace('#/ ... #', '', $data['cast']);
}
// Fetch plot
$resp = $resp = imdbFixEncoding($data, httpClient($imdbServer . '/title/tt' . $imdbID . '/plotsummary', $cache));
if (!$resp['success']) {
$CLIENTERROR .= $resp['error'] . "\n";
}
// Plot
preg_match('/<P CLASS="plotSummary">(.+?)<\\/P>/is', $resp['data'], $ary);
if ($ary[1]) {
$data['plot'] = trim($ary[1]);
$data['plot'] = preg_replace('/"/', '"', $data['plot']);
//Replace HTML " with "
//Begin removal of 'Written by' section
$data['plot'] = preg_replace('/<a href="\\/SearchPlotWriters.*?<\\/a>/', '', $data['plot']);
$data['plot'] = preg_replace('/Written by/', '', $data['plot']);
$data['plot'] = preg_replace('/<i>\\s+<\\/i>/', ' ', $data['plot']);
//End of removal of 'Written by' section
$data['plot'] = preg_replace('/\\s+/s', ' ', $data['plot']);
}
$data['plot'] = html_clean($data['plot']);
#dump($data['plot']);
return $data;
}
/**
* Clean HTML tags from hierarchical associative array
*
* @param array $data string or hierarchical array to convert
*/
function engine_clean_input(&$data)
{
if (is_array($data)) {
foreach ($data as $key => $val) {
if (is_array($val)) {
engine_clean_input($data[$key]);
} else {
$val = html_to_text($val);
$data[$key] = html_clean_utf8($val);
}
}
}
}
/**
* Fetches the data for a given Allocine-ID
*
* @author Douglas Mayle <*****@*****.**>
* @author Tiago Fonseca <*****@*****.**>
* @param int imdb-ID
* @return array Result data
*/
function allocineData($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 $data;
}
<?php
error_reporting(E_ALL ^ E_NOTICE);
if (!$submit) {
echo "<h2>Warning- be sure to backup your data before submitting the cleanup request!</h2>";
}
$SQL = 'SELECT * FROM ' . TBL_DATA;
$result = runSQL($SQL);
$count = 0;
foreach ($result as $video) {
$SQL = '';
$keys = array();
foreach ($video as $key => $value) {
if ($key == 'id') {
continue;
}
$new = html_clean_utf8($value);
if ($new != $value) {
$keys[] = $key;
if ($SQL) {
$SQL .= ', ';
}
$SQL .= "{$key} = '" . mysql_escape_string($new) . "'";
}
}
if ($SQL) {
$count++;
echo ($submit ? 'Converting: ' : '<b>Conversion needed:</b> ') . $video['title'] . "<br/>\n";
// actually perform the conversion?
if ($submit) {
$SQL = "UPDATE " . TBL_DATA . " SET {$SQL} WHERE id = " . $video['id'];
runSQL($SQL);
