blallo/rss-bridge
1
0
Fork 1
Code Issues Pull requests Releases Wiki Activity

Merge pull request #70 from Polopollo/master

Browse source 
Add of GizmodoFR+Developpez.com+a small feature for NextImpact
This commit is contained in:
Mitsu 2014-07-16 17:04:48 +02:00
commit 9844fee8c5
6 changed files with 208 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

75
bridges/DeveloppezDotComBridge.php Normal file
View file

@ -0,0 +1,75 @@
<?php
/**
* RssBridgeDeveloppezDotCom
* Returns the 15 newest posts from http://www.developpez.com (full text)
* 2014-07-14
*
* @name Developpez.com Actus (FR)
* @homepage http://www.developpez.com/
* @description Returns the 15 newest posts from DeveloppezDotCom (full text).
* @maintainer polopollo
*/
class DeveloppezDotComBridge extends BridgeAbstract{
public function collectData(array $param){
function DeveloppezDotComStripCDATA($string) {
$string = str_replace('<![CDATA[', '', $string);
$string = str_replace(']]>', '', $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) {
$articleHTMLContent = file_get_html($url);
$text = convert_smart_quotes($articleHTMLContent->find('div.content', 0)->innertext);
$text = utf8_encode($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);
$limit = 0;
foreach($rssFeed->find('item') as $element) {
if($limit < 2) {
$item = new \Item();
$item->title = DeveloppezDotComStripCDATA($element->find('title', 0)->innertext);
$item->uri = DeveloppezDotComStripCDATA($element->find('guid', 0)->plaintext);
$item->timestamp = strtotime($element->find('pubDate', 0)->plaintext);
$content = DeveloppezDotComExtractContent($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;
$limit++;
}
}
}
public function getName(){
return 'DeveloppezDotCom';
}
public function getURI(){
return 'http://www.developpez.com/';
}
public function getCacheDuration(){
return 1800; // 30min
}
}

57
bridges/GizmodoFRBridge.php Normal file
View file

@ -0,0 +1,57 @@
<?php
/**
* RssBridgeGizmodoFR
* Returns the 15 newest posts from http://www.gizmodo.fr (full text)
* 2014-07-14
*
* @name GizmodoFR
* @homepage http://www.gizmodo.fr/
* @description Returns the 15 newest posts from GizmodoFR (full text).
* @maintainer polopollo
*/
class GizmodoFRBridge extends BridgeAbstract{
public function collectData(array $param){
function GizmodoFRExtractContent($url) {
$articleHTMLContent = file_get_html($url);
$text = $articleHTMLContent->find('div.entry-thumbnail', 0)->innertext;
$text = $text.$articleHTMLContent->find('div.entry-excerpt', 0)->innertext;
$text = $text.$articleHTMLContent->find('div.entry-content', 0)->innertext;
foreach($articleHTMLContent->find('pagespeed_iframe') as $element) {
$text = $text.'<p>link to a iframe (could be a video): <a href="'.$element->src.'">'.$element->src.'</a></p><br>';
}
$text = strip_tags($text, '<p><b><a><blockquote><img><em>');
return $text;
}
$rssFeed = file_get_html('http://www.gizmodo.fr/feed') or $this->returnError('Could not request http://www.gizmodo.fr/feed', 404);
$limit = 0;
foreach($rssFeed->find('item') as $element) {
if($limit < 15) {
$item = new \Item();
$item->title = $element->find('title', 0)->innertext;
$item->uri = $element->find('guid', 0)->plaintext;
$item->timestamp = strtotime($element->find('pubDate', 0)->plaintext);
$item->content = GizmodoFRExtractContent($item->uri);
$this->items[] = $item;
$limit++;
}
}
}
public function getName(){
return 'GizmodoFR';
}
public function getURI(){
return 'http://www.gizmodo.fr/';
}
public function getCacheDuration(){
return 1800; // 30min
}
}

69
bridges/LeJournalDuGeekBridge.php Normal file
View file

@ -0,0 +1,69 @@
<?php
/**
* RssBridgeLeJournalDuGeek
* Returns the 15 newest posts from http://www.journaldugeek.com (full text)
* 2014-07-14
*
* @name journaldugeek.com (FR)
* @homepage http://www.journaldugeek.com/
* @description Returns the 15 newest posts from LeJournalDuGeek (full text).
* @maintainer polopollo
*/
class LeJournalDuGeekBridge extends BridgeAbstract{
public function collectData(array $param){
function LeJournalDuGeekStripCDATA($string) {
$string = str_replace('<![CDATA[', '', $string);
$string = str_replace(']]>', '', $string);
return $string;
}
function LeJournalDuGeekExtractContent($url) {
$articleHTMLContent = file_get_html($url);
$text = $text.$articleHTMLContent->find('div.post-content', 0)->innertext;
foreach($articleHTMLContent->find('a.more') as $element) {
if ($element->innertext == "Source") {
$text = $text.'<p><a href="'.$element->href.'">Source : '.$element->href.'</a></p>';
break;
}
}
foreach($articleHTMLContent->find('iframe') as $element) {
if (preg_match("/youtube/i", $element->src)) {
$text = $text.'// An IFRAME to Youtube was included in the article: <a href="'.$element->src.'">'.$element->src.'</a><br>';
}
}
$text = strip_tags($text, '<p><b><a><blockquote><img><em><br/><br><ul><li>');
return $text;
}
$rssFeed = file_get_html('http://www.journaldugeek.com/rss') or $this->returnError('Could not request http://www.journaldugeek.com/rss', 404);
$limit = 0;
foreach($rssFeed->find('item') as $element) {
if($limit < 15) {
$item = new \Item();
$item->title = LeJournalDuGeekStripCDATA($element->find('title', 0)->innertext);
$item->uri = LeJournalDuGeekStripCDATA($element->find('guid', 0)->plaintext);
$item->timestamp = strtotime($element->find('pubDate', 0)->plaintext);
$item->content = LeJournalDuGeekExtractContent($item->uri);
$this->items[] = $item;
$limit++;
}
}
}
public function getName(){
return 'LeJournalDuGeek';
}
public function getURI(){
return 'http://www.journaldugeek.com/';
}
public function getCacheDuration(){
return 1800; // 30min
}
}

7
bridges/NextInpactBridge.php
View file

@ -10,7 +10,7 @@
* @maintainer qwertygc
*/
class NextInpactBridge extends BridgeAbstract{
public function collectData(array $param){
function StripCDATA($string) {
@ -20,7 +20,8 @@ class NextInpactBridge extends BridgeAbstract{
}
function ExtractContent($url) {
$html2 = file_get_html($url);
$text = $html2->find('div[itemprop=articleBody]', 0)->innertext;
$text = '<h2>'.$html2->find('div#actu_entete > h2', 0)->innertext.'</h2><br><br>';
$text = $text.$html2->find('div[itemprop=articleBody]', 0)->innertext;
return $text;
}
$html = file_get_html('http://www.nextinpact.com/rss/news.xml') or $this->returnError('Could not request Nextinpact.', 404);
@ -37,7 +38,7 @@ class NextInpactBridge extends BridgeAbstract{
$limit++;
}
}
}
public function getName(){

4
bridges/NumeramaBridge.php
View file

@ -1,6 +1,6 @@
<?php
/**
* RssBridgeNumerama
* RssBridgeNumerama
* Returns the 5 newest posts from http://www.numerama.com (full text)
* 2014-05-25
*
@ -39,7 +39,7 @@ class NumeramaBridge extends BridgeAbstract{
$limit++;
}
}
}
public function getName(){

2
bridges/WordPressBridge.php
View file

@ -11,7 +11,7 @@
* @update 2014-05-26
* @use1(url="blog URL (required)", name="blog name")
*/
class WordpressBridge extends BridgeAbstract {
class WordPressBridge extends BridgeAbstract {
private $url;
private $name;