1
0
Fork 0
forked from blallo/rss-bridge

Merge pull request #151 from ORelio/master

NextImpactBridge Improvements
This commit is contained in:
Mitsu 2015-09-04 18:50:40 +02:00
commit 762ad0291e
2 changed files with 22 additions and 15 deletions

View file

@ -9,21 +9,24 @@
* @description Returns the newest articles. * @description Returns the newest articles.
* @maintainer qwertygc * @maintainer qwertygc
*/ */
class NextInpactBridge extends BridgeAbstract{ class NextInpactBridge extends BridgeAbstract {
public function collectData(array $param){ public function collectData(array $param) {
function StripCDATA($string) { function StripCDATA($string) {
$string = str_replace('<![CDATA[', '', $string); $string = str_replace('<![CDATA[', '', $string);
$string = str_replace(']]>', '', $string); $string = str_replace(']]>', '', $string);
return $string; return $string;
} }
function ExtractContent($url) { function ExtractContent($url) {
$html2 = file_get_html($url); $html2 = file_get_html($url);
$text = '<h2>'.$html2->find('div#actu_entete > h2', 0)->innertext.'</h2><br><br>'; $text = '<p><em>'.$html2->find('span.sub_title', 0)->innertext.'</em></p>'
$text = $text.$html2->find('div[itemprop=articleBody]', 0)->innertext; .'<p><img src="'.$html2->find('div.container_main_image_article', 0)->find('img.dedicated',0)->src.'" /></p>'
.'<div>'.$html2->find('div[itemprop=articleBody]', 0)->innertext.'</div>';
return $text; return $text;
} }
$html = file_get_html('http://www.nextinpact.com/rss/news.xml') or $this->returnError('Could not request Nextinpact.', 404); $html = file_get_html('http://www.nextinpact.com/rss/news.xml') or $this->returnError('Could not request Nextinpact.', 404);
$limit = 0; $limit = 0;
@ -32,6 +35,8 @@ class NextInpactBridge extends BridgeAbstract{
$item = new \Item(); $item = new \Item();
$item->title = StripCDATA($element->find('title', 0)->innertext); $item->title = StripCDATA($element->find('title', 0)->innertext);
$item->uri = StripCDATA($element->find('guid', 0)->plaintext); $item->uri = StripCDATA($element->find('guid', 0)->plaintext);
$item->thumbnailUri = StripCDATA($element->find('enclosure', 0)->url);
$item->author = StripCDATA($element->find('author', 0)->innertext);
$item->timestamp = strtotime($element->find('pubDate', 0)->plaintext); $item->timestamp = strtotime($element->find('pubDate', 0)->plaintext);
$item->content = ExtractContent($item->uri); $item->content = ExtractContent($item->uri);
$this->items[] = $item; $this->items[] = $item;

View file

@ -24,6 +24,7 @@ class MrssFormat extends FormatAbstract{
foreach($this->getDatas() as $data){ foreach($this->getDatas() as $data){
$itemTitle = strip_tags(is_null($data->title) ? '' : $data->title); $itemTitle = strip_tags(is_null($data->title) ? '' : $data->title);
$itemUri = is_null($data->uri) ? '' : $data->uri; $itemUri = is_null($data->uri) ? '' : $data->uri;
$itemAuthor = is_null($data->author) ? '' : $data->author;
$itemThumbnailUri = is_null($data->thumbnailUri) ? '' : $data->thumbnailUri; $itemThumbnailUri = is_null($data->thumbnailUri) ? '' : $data->thumbnailUri;
$itemTimestamp = is_null($data->timestamp) ? '' : date(DATE_RFC2822, $data->timestamp); $itemTimestamp = is_null($data->timestamp) ? '' : date(DATE_RFC2822, $data->timestamp);
// We prevent content from closing the CDATA too early. // We prevent content from closing the CDATA too early.
@ -37,6 +38,7 @@ class MrssFormat extends FormatAbstract{
<guid isPermaLink="true">{$itemUri}</guid> <guid isPermaLink="true">{$itemUri}</guid>
<pubDate>{$itemTimestamp}</pubDate> <pubDate>{$itemTimestamp}</pubDate>
<description>{$itemContent}</description> <description>{$itemContent}</description>
<author>{$itemAuthor}</author>
<media:title>{$itemTitle}</media:title> <media:title>{$itemTitle}</media:title>
<media:thumbnail url="{$itemThumbnailUri}" /> <media:thumbnail url="{$itemThumbnailUri}" />
</item> </item>