rss-bridge/bridges/ElsevierBridge.php
Joseph 4c0e234479 [Bridges] Use HTTPS (#1337)
* [Rule34pahealBridge] Use HTTPS
* [KonachanBridge] Use HTTPS
* [Rule34Bridge] Use HTTPS
* [SafebooruBridge] Use HTTPS
* [TbibBridge] Use HTTPS
* [XbooruBridge] Use HTTPS
* [ScmbBridge] Use HTTPS
* [ReporterreBridge] Use HTTPS
* [BastaBridge] Use HTTPS
* [NiceMatinBridge] Use HTTPS
* [ScoopItBridge] Use HTTPS
* [TheCodingLoveBridge] Use HTTPS
* [Shimmie2Bridge] Use HTTPS
* [HDWallpapersBridge] Use HTTPS
* [GiphyBridge] Use HTTPS
* [PickyWallpapersBridge] Use HTTPS
* [ParuVenduImmoBridge] Use HTTPS
* [ElsevierBridge] Use HTTPS
* [CastorusBridge] Use HTTPS
* [CollegeDeFranceBridge] Use HTTPS
* [MangareaderBridge] Use HTTPS
2019-10-16 21:34:28 +02:00

79 lines
2.4 KiB
PHP
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<?php
class ElsevierBridge extends BridgeAbstract {
const MAINTAINER = 'Pierre Mazière';
const NAME = 'Elsevier journals recent articles';
const URI = 'https://www.journals.elsevier.com/';
const CACHE_TIMEOUT = 43200; //12h
const DESCRIPTION = 'Returns the recent articles published in Elsevier journals';
const PARAMETERS = array( array(
'j' => array(
'name' => 'Journal name',
'required' => true,
'exampleValue' => 'academic-pediactrics',
'title' => 'Insert html-part of your journal'
)
));
// Extracts the list of names from an article as string
private function extractArticleName($article){
$names = $article->find('small', 0);
if($names)
return trim($names->plaintext);
return '';
}
// Extracts the timestamp from an article
private function extractArticleTimestamp($article){
$time = $article->find('.article-info', 0);
if($time) {
$timestring = trim($time->plaintext);
/*
The format depends on the age of an article:
- Available online 29 July 2016
- July 2016
- MayJune 2016
*/
if(preg_match('/\S*(\d+\s\S+\s\d{4})/ims', $timestring, $matches)) {
return strtotime($matches[0]);
} elseif (preg_match('/[A-Za-z]+\-([A-Za-z]+\s\d{4})/ims', $timestring, $matches)) {
return strtotime($matches[0]);
} elseif (preg_match('/([A-Za-z]+\s\d{4})/ims', $timestring, $matches)) {
return strtotime($matches[0]);
} else {
return 0;
}
}
return 0;
}
// Extracts the content from an article
private function extractArticleContent($article){
$content = $article->find('.article-content', 0);
if($content) {
return trim($content->plaintext);
}
return '';
}
public function getIcon() {
return 'https://cdn.elsevier.io/verona/includes/favicons/favicon-32x32.png';
}
public function collectData(){
$uri = self::URI . $this->getInput('j') . '/recent-articles/';
$html = getSimpleHTMLDOM($uri)
or returnServerError('No results for Elsevier journal ' . $this->getInput('j'));
foreach($html->find('.pod-listing') as $article) {
$item = array();
$item['uri'] = $article->find('.pod-listing-header>a', 0)->getAttribute('href') . '?np=y';
$item['title'] = $article->find('.pod-listing-header>a', 0)->plaintext;
$item['author'] = $this->extractArticleName($article);
$item['timestamp'] = $this->extractArticleTimestamp($article);
$item['content'] = $this->extractArticleContent($article);
$this->items[] = $item;
}
}
}