mirror of
https://github.com/RSS-Bridge/rss-bridge.git
synced 2024-11-26 19:36:52 +03:00
a4b9611e66
- Do not add spaces after opening or before closing parenthesis
// Wrong
if( !is_null($var) ) {
...
}
// Right
if(!is_null($var)) {
...
}
- Add space after closing parenthesis
// Wrong
if(true){
...
}
// Right
if(true) {
...
}
- Add body into new line
- Close body in new line
// Wrong
if(true) { ... }
// Right
if(true) {
...
}
Notice: Spaces after keywords are not detected:
// Wrong (not detected)
// -> space after 'if' and missing space after 'else'
if (true) {
...
} else{
...
}
// Right
if(true) {
...
} else {
...
}
75 lines
2.3 KiB
PHP
75 lines
2.3 KiB
PHP
<?php
|
||
class ElsevierBridge extends BridgeAbstract {
|
||
|
||
const MAINTAINER = 'Pierre Mazière';
|
||
const NAME = 'Elsevier journals recent articles';
|
||
const URI = 'http://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
|
||
- May–June 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 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;
|
||
}
|
||
}
|
||
}
|