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

microsoft quotes and UTF8 encoding fixed for

Browse source 
Developpez.com
This commit is contained in:
Paul Vayssiere 2014-07-15 19:31:54 -05:00
parent 94a6b42a2b
commit 2dd8f789fc
1 changed files with 23 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

28
bridges/DeveloppezDotComBridge.php
View file

@ -19,23 +19,41 @@ class DeveloppezDotComBridge extends BridgeAbstract{
return $string; return $string;
} }
function convert_smart_quotes($string)//F***ing quotes from Microsoft Word badly encoded, here was the trick: http://stackoverflow.com/questions/1262038/how-to-replace-microsoft-encoded-quotes-in-php
{
$search = array(chr(145),
chr(146),
chr(147),
chr(148),
chr(151));
$replace = array("'",
"'",
'"',
'"',
'-');
return str_replace($search, $replace, $string);
}
function DeveloppezDotComExtractContent($url) { function DeveloppezDotComExtractContent($url) {
$articleHTMLContent = file_get_html($url); $articleHTMLContent = file_get_html($url);
$text = $text.$articleHTMLContent->find('div.content', 0)->innertext; $text = convert_smart_quotes($articleHTMLContent->find('div.content', 0)->innertext);
$text = strip_tags($text, '<p><b><a><blockquote><img><em><br/><br><ul><li>'); $text = utf8_encode($text);
return $text; return trim($text);
} }
$rssFeed = file_get_html('http://www.developpez.com/index/rss') or $this->returnError('Could not request http://www.developpez.com/index/rss', 404); $rssFeed = file_get_html('http://www.developpez.com/index/rss') or $this->returnError('Could not request http://www.developpez.com/index/rss', 404);
$limit = 0; $limit = 0;
foreach($rssFeed->find('item') as $element) { foreach($rssFeed->find('item') as $element) {
if($limit < 15) { if($limit < 2) {
$item = new \Item(); $item = new \Item();
$item->title = DeveloppezDotComStripCDATA($element->find('title', 0)->innertext); $item->title = DeveloppezDotComStripCDATA($element->find('title', 0)->innertext);
$item->uri = DeveloppezDotComStripCDATA($element->find('guid', 0)->plaintext); $item->uri = DeveloppezDotComStripCDATA($element->find('guid', 0)->plaintext);
$item->timestamp = strtotime($element->find('pubDate', 0)->plaintext); $item->timestamp = strtotime($element->find('pubDate', 0)->plaintext);
$item->content = DeveloppezDotComExtractContent($item->uri); $content = DeveloppezDotComExtractContent($item->uri);
$item->content = strlen($content) ? $content : $element->description;//In case of it is a tutorial, we just keep the original description
$this->items[] = $item; $this->items[] = $item;
$limit++; $limit++;
} }