boyska/rss-bridge
1
0
Fork 0
forked from blallo/rss-bridge
Code Releases Activity

[Wikipedia] Improve title search algorithm

Browse source
This commit is contained in:
logmanoriginal 2016-08-07 11:26:45 +02:00
parent d4435e0b13
commit 0b923ab76a
1 changed files with 11 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
bridges/WikipediaBridge.php
View file

@ -107,9 +107,18 @@ class WikipediaBridge extends BridgeAbstract{
// Clean the bottom of the featured article // Clean the bottom of the featured article
$element->find('div', -1)->outertext = ''; $element->find('div', -1)->outertext = '';
// The title and URI of the article is best defined in an anchor containint the string '...' ('full article ...')
$target = $element->find('p/a', 0); // We'll use the first anchor as fallback
foreach($element->find('//a') as $anchor){
if(strpos($anchor->innertext, '...') !== false){
$target = $anchor;
break;
}
}
$item = new \Item(); $item = new \Item();
$item->uri = $this->uri . $element->find('p', 0)->find('a', 0)->href; $item->uri = $this->uri . $target->href;
$item->title = $element->find('p', 0)->find('a', 0)->title; $item->title = $target->title;
if(!$fullArticle) if(!$fullArticle)
$item->content = strip_tags(str_replace('href="/', 'href="' . $this->uri . '/', $element->innertext), '<a><p><br><img>'); $item->content = strip_tags(str_replace('href="/', 'href="' . $this->uri . '/', $element->innertext), '<a><p><br><img>');