forked from blallo/rss-bridge
Merge pull request #308 from LogMANOriginal/ElsevierBridge
Elsevier bridge
This commit is contained in:
commit
84847bf85f
1 changed files with 79 additions and 43 deletions
|
@ -1,10 +1,4 @@
|
|||
<?php
|
||||
/**
|
||||
* ElsevierBridge
|
||||
*
|
||||
* @name Elsevier Bridge
|
||||
* @description Returns the recent articles published in Elsevier journals
|
||||
*/
|
||||
class ElsevierBridge extends BridgeAbstract{
|
||||
public function loadMetadatas() {
|
||||
|
||||
|
@ -12,32 +6,73 @@ class ElsevierBridge extends BridgeAbstract{
|
|||
$this->name = 'Elsevier journals recent articles';
|
||||
$this->uri = 'http://www.journals.elsevier.com';
|
||||
$this->description = 'Returns the recent articles published in Elsevier journals';
|
||||
$this->update = '2016-06-26';
|
||||
$this->update = '2016-08-02';
|
||||
|
||||
$this->parameters=
|
||||
$this->parameters[] =
|
||||
'[
|
||||
{
|
||||
"name" : "Journal name",
|
||||
"identifier" : "j"
|
||||
"identifier" : "j",
|
||||
"required" : "true",
|
||||
"exampleValue" : "academic-pediatrics",
|
||||
"title" : "Insert html-part of your journal"
|
||||
}
|
||||
]';
|
||||
}
|
||||
|
||||
// Extracts the list of names from an article as string
|
||||
function ExtractArticleName ($article){
|
||||
$names = $article->find('small', 0);
|
||||
if($names)
|
||||
return trim($names->plaintext);
|
||||
return '';
|
||||
}
|
||||
|
||||
// Extracts the timestamp from an article
|
||||
function ExtractArticleTimestamp ($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]+\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]);
|
||||
} else {
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
// Extracts the content from an article
|
||||
function ExtractArticleContent ($article){
|
||||
$content = $article->find('.article-content', 0);
|
||||
if($content){
|
||||
return trim($content->plaintext);
|
||||
}
|
||||
return '';
|
||||
}
|
||||
|
||||
public function collectData(array $param){
|
||||
$uri = 'http://www.journals.elsevier.com/'.$param['j'].'/recent-articles/';
|
||||
$html = file_get_html($uri)
|
||||
or $this->returnError('No results for Elsevier journal '.$param['j'], 404);
|
||||
$uri = 'http://www.journals.elsevier.com/' . $param['j'] . '/recent-articles/';
|
||||
$html = file_get_html($uri) or $this->returnError('No results for Elsevier journal '.$param['j'], 404);
|
||||
|
||||
foreach($html->find('.pod-listing') as $article){
|
||||
|
||||
$item = new \Item();
|
||||
$item->uri=$article->find('.pod-listing-header>a',0)->getAttribute('href').'?np=y';
|
||||
$item->title=$article->find('.pod-listing-header>a',0)->plaintext;
|
||||
$item->name=trim($article->find('small',0)->plaintext);
|
||||
$item->timestamp=strtotime($article->find('.article-info',0)->plaintext);
|
||||
$item->content=trim($article->find('.article-content',0)->plaintext);
|
||||
|
||||
$this->items[]=$item;
|
||||
$item->uri = $article->find('.pod-listing-header>a',0)->getAttribute('href').'?np=y';
|
||||
$item->title = $article->find('.pod-listing-header>a',0)->plaintext;
|
||||
$item->name = $this->ExtractArticleName($article);
|
||||
$item->timestamp = $this->ExtractArticleTimestamp($article);
|
||||
$item->content = $this->ExtractArticleContent($article);
|
||||
$this->items[] = $item;
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -53,3 +88,4 @@ class ElsevierBridge extends BridgeAbstract{
|
|||
return 43200; // 12h
|
||||
}
|
||||
}
|
||||
?>
|
Loading…
Reference in a new issue