public function rssProxyAction()
{
$overrideFeedUrl = $this->getEvent()->getRequest()->getQuery()->get('urlOverride');
$limit = $this->getEvent()->getRequest()->getQuery()->get('limit');
$instanceId = $this->getEvent()->getRequest()->getQuery()->get('instanceId');
/** @var \Rcm\Service\PluginManager $pluginManager */
$pluginManager = $this->serviceLocator->get('\\Rcm\\Service\\PluginManager');
if ($instanceId > 0) {
$instanceConfig = $pluginManager->getInstanceConfig($instanceId);
} else {
$instanceConfig = $pluginManager->getDefaultInstanceConfig('RcmRssFeed');
}
$feedUrl = $instanceConfig['rssFeedUrl'];
$cacheKey = 'rcmrssfeed-' . md5($feedUrl);
if ($this->cacheMgr->hasItem($cacheKey)) {
$viewRssData = json_decode($this->cacheMgr->getItem($cacheKey));
$this->sendJson($viewRssData);
}
if (!empty($overrideFeedUrl) && $overrideFeedUrl != 'null') {
//$permissions = $this->userMgr->getLoggedInAdminPermissions();
$permissions = null;
/**
* Only admins can override the url. This prevents people from using
* our proxy to DDOS other sites.
*/
$allowed = $this->rcmIsAllowed('sites.' . $this->siteId, 'admin');
if ($allowed) {
$feedUrl = $overrideFeedUrl;
}
}
if (empty($limit)) {
$limit = $instanceConfig['rssFeedLimit'];
}
$rssReader = new Reader();
//Tried to add a timeout like this but it didnt work
$httpClient = new Client($feedUrl, ['timeout' => 5]);
$rssReader->setHttpClient($httpClient);
try {
$feedData = $rssReader->import($feedUrl);
} catch (\Exception $e) {
$feedData = [];
}
$feedCount = 0;
$viewRssData = [];
foreach ($feedData as $entry) {
if ($feedCount == $limit) {
break;
}
$viewRssData[] = ['feedtitle' => $entry->getTitle(), 'description' => $entry->getDescription(), 'dateModified' => $entry->getDateModified(), 'authors' => $entry->getAuthors(), 'feedlink' => $entry->getLink()];
$feedCount++;
}
$this->cacheMgr->addItem($cacheKey, json_encode($viewRssData));
$this->sendJson($viewRssData);
}
/**
* Get an array with feed authors
*
* @return array
*/
public function getAuthors()
{
if (array_key_exists('authors', $this->data)) {
return $this->data['authors'];
}
$authors = array();
$list = $this->getXpath()->query('//dc11:creator');
if (!$list->length) {
$list = $this->getXpath()->query('//dc10:creator');
}
if (!$list->length) {
$list = $this->getXpath()->query('//dc11:publisher');
if (!$list->length) {
$list = $this->getXpath()->query('//dc10:publisher');
}
}
if ($list->length) {
foreach ($list as $author) {
$authors[] = array('name' => $author->nodeValue);
}
$authors = new Collection\Author(Reader\Reader::arrayUnique($authors));
} else {
$authors = null;
}
$this->data['authors'] = $authors;
return $this->data['authors'];
}
public function testCanDetectHubs()
{
$feed = \Zend\Feed\Reader\Reader::importFile(__DIR__ . '/_files/rss20.xml');
$this->assertEquals(array(
'http://www.example.com/hub', 'http://www.example.com/hub2'
), PubSubHubbub\PubSubHubbub::detectHubs($feed));
}
/**
* Get an array with feed authors
*
* @return array
*/
public function getAuthors()
{
if (array_key_exists('authors', $this->_data)) {
return $this->_data['authors'];
}
$authors = array();
$list = $this->getXpath()->query($this->getXpathPrefix() . '//atom:author');
if (!$list->length) {
/**
* TODO: Limit query to feed level els only!
*/
$list = $this->getXpath()->query('//atom:author');
}
if ($list->length) {
foreach ($list as $author) {
$author = $this->_getAuthor($author);
if (!empty($author)) {
$authors[] = $author;
}
}
}
if (count($authors) == 0) {
$authors = null;
} else {
$authors = new Collection\Author(Reader\Reader::arrayUnique($authors));
}
$this->_data['authors'] = $authors;
return $this->_data['authors'];
}
/**
* Get an array with feed authors
*
* @return array
*/
public function getAuthors()
{
if (array_key_exists('authors', $this->_data)) {
return $this->_data['authors'];
}
$list = $this->_xpath->query('//atom:author');
$authors = array();
if ($list->length) {
foreach ($list as $author) {
$author = $this->_getAuthor($author);
if (!empty($author)) {
$authors[] = $author;
}
}
}
if (count($authors) == 0) {
$authors = null;
} else {
$authors = new Collection\Author(
Reader\Reader::arrayUnique($authors)
);
}
$this->_data['authors'] = $authors;
return $this->_data['authors'];
}
/**
* Process RSS feed and return results.
*
* @param $feed_url
* @param null $cache_name
* @param int $cache_expires
* @return array|mixed
*/
public static function getNewsFeed($feed_url, $cache_name = NULL, $cache_expires = 900)
{
if (!is_null($cache_name)) {
$feed_cache = Cache::get('feed_' . $cache_name);
} else {
$feed_cache = null;
}
if ($feed_cache) {
return $feed_cache;
}
// Catch the occasional error when the RSS feed is malformed or the HTTP request times out.
try {
$news_feed = Reader::import($feed_url);
} catch (\Exception $e) {
$news_feed = NULL;
}
if (!is_null($news_feed)) {
$latest_news = array();
$article_num = 0;
foreach ($news_feed as $item) {
$article_num++;
$news_item = array('num' => $article_num, 'title' => $item->getTitle(), 'timestamp' => $item->getDateModified()->getTimestamp(), 'description' => trim($item->getDescription()), 'link' => $item->getLink(), 'categories' => $item->getCategories()->getValues());
$latest_news[] = $news_item;
}
$latest_news = array_slice($latest_news, 0, 10);
if (!is_null($cache_name)) {
Cache::set($latest_news, 'feed_' . $cache_name, array('feeds', $cache_name), $cache_expires);
}
return $latest_news;
}
}
/**
* Loads a newsfeed object.
*
* @param string $feedurl
* @param bool $cache
* @return Reader
*/
public function load($url, $cache = true)
{
if ($cache) {
Reader::setCache(new ZendCacheDriver('cache/expensive'));
}
$feed = Reader::import($url);
return $feed;
}
public function read() : array
{
$url = sprintf(self::ATOM_FORMAT, $this->user);
$feed = FeedReader::import($url);
$entries = Collection::create($feed)->filterChain($this->filters)->slice($this->limit)->map(function ($entry) {
return ['title' => $entry->getTitle(), 'link' => $entry->getLink()];
});
return ['last_modified' => $feed->getDateModified(), 'link' => $feed->getLink(), 'links' => $entries->toArray()];
}
/**
* Loads feed from an url or file path
*
* @param string $file
*
* @return Reader
*/
public function load($file)
{
if (file_exists($file)) {
$this->feed = ZendReader::importFile($file);
} else {
$this->feed = ZendReader::import($file);
}
return $this;
}
/**
* Returns if the provided $content_type is a feed.
*
* @param string $document
* The actual HTML or XML document from the HTTP request.
*
* @return bool
* Returns true if this is a parsable feed, false if not.
*/
public static function isFeed($data)
{
Reader::setExtensionManager(\Drupal::service('feed.bridge.reader'));
try {
$feed_type = Reader::detectType($data);
} catch (\Exception $e) {
return FALSE;
}
return $feed_type != Reader::TYPE_ANY;
}
/**
* Loads a newsfeed object.
*
* @param string $feedurl
* @param int $cache - number of seconds to cache the RSS feed data for
* @return Reader
*/
public function load($url, $cache = 3600)
{
if ($cache !== false) {
Reader::setCache(new ZendCacheDriver('cache/expensive', $cache));
}
// Load the RSS feed, either from remote URL or from cache
// (if specified above and still fresh)
$feed = Reader::import($url);
return $feed;
}
/**
* Simple utility function which imports any feed URL and
* determines the existence of Hub Server endpoints. This works
* best if directly given an instance of Zend_Feed_Reader_Atom|Rss
* to leverage off.
*
* @param \Zend\Feed\Reader\Feed\AbstractFeed|string $source
* @return array
* @throws Exception\InvalidArgumentException
*/
public static function detectHubs($source)
{
if (is_string($source)) {
$feed = Reader\Reader::import($source);
} elseif ($source instanceof Reader\Feed\AbstractFeed) {
$feed = $source;
} else {
throw new Exception\InvalidArgumentException('The source parameter was' . ' invalid, i.e. not a URL string or an instance of type' . ' Zend\\Feed\\Reader\\Feed\\AbstractFeed');
}
return $feed->getHubs();
}
public function run()
{
$feed = Reader::import($this->feedUrl);
$data = array('title' => $feed->getTitle(), 'link' => $feed->getLink(), 'dateModified' => $feed->getDateModified(), 'description' => $feed->getDescription(), 'language' => $feed->getLanguage(), 'entries' => array());
foreach ($feed as $entry) {
$edata = array('title' => $entry->getTitle(), 'description' => $entry->getDescription(), 'dateModified' => $entry->getDateModified(), 'authors' => $entry->getAuthors(), 'link' => $entry->getLink(), 'content' => $entry->getContent());
$data['entries'][] = $edata;
}
echo $this->render('default', ['data' => $data]);
// $this->registerClientScript();
}
/**
* Constructor
*
* @param DOMDocument $dom
* @param string $type
*/
public function __construct(DOMDocument $dom, $type = null)
{
parent::__construct($dom, $type);
$atomClass = Reader\Reader::getPluginLoader()->getClassName('Atom\\Feed');
$this->_extensions['Atom\\Feed'] = new $atomClass($dom, $this->_data['type'], $this->_xpath);
$atomClass = Reader\Reader::getPluginLoader()->getClassName('DublinCore\\Feed');
$this->_extensions['DublinCore\\Feed'] = new $atomClass($dom, $this->_data['type'], $this->_xpath);
foreach ($this->_extensions as $extension) {
$extension->setXpathPrefix('/atom:feed');
}
}
public function __invoke($services)
{
$http = $services->get('http');
FeedReader::setHttpClient($http);
FeedReader::setExtensionManager($this->createExtensionManager());
$config = $services->get('Config');
$config = $config['github'];
$reader = new AtomReader($config['user']);
$reader->setLimit($config['limit']);
return $reader;
}
/**
* Constructor
*
* @param DOMElement $entry
* @param int $entryKey
* @param string $type
* @return void
*/
public function __construct(\DOMElement $entry, $entryKey, $type = null)
{
parent::__construct($entry, $entryKey, $type);
// Everyone by now should know XPath indices start from 1 not 0
$this->_xpathQuery = '//atom:entry[' . ($this->_entryKey + 1) . ']';
$atomClass = Reader\Reader::getPluginLoader()->getClassName('Atom\\Entry');
$this->_extensions['Atom\\Entry'] = new $atomClass($entry, $entryKey, $type);
$threadClass = Reader\Reader::getPluginLoader()->getClassName('Thread\\Entry');
$this->_extensions['Thread\\Entry'] = new $threadClass($entry, $entryKey, $type);
$threadClass = Reader\Reader::getPluginLoader()->getClassName('DublinCore\\Entry');
$this->_extensions['DublinCore\\Entry'] = new $threadClass($entry, $entryKey, $type);
}
function setUp()
{
parent::setUp();
// Do not delete old aggregator items during these tests, since our sample
// feeds have hardcoded dates in them (which may be expired when this test
// is run).
$this->container->get('config.factory')->get('aggregator.settings')->set('items.expire', AGGREGATOR_CLEAR_NEVER)->save();
// Reset any reader cache between tests.
Reader::reset();
// Set our bridge extension manager to Zend Feed.
$bridge = $this->container->get('feed.bridge.reader');
Reader::setExtensionManager($bridge);
}
public function import()
{
$this->logger('Import ' . $this->uri, 'info', $this->logger_level);
try {
$this->feed = Reader::import($this->uri);
if (!isset($this->feed)) {
throw new \Exception('Unreadble');
}
} catch (\Exception $e) {
$this->logger('Feed empty ', 'err', $this->logger_level);
return false;
}
}
/**
* @return array
*/
public function getEntries()
{
if (empty($this->entries)) {
$feeds = $this->getOutlet()->getFeeds();
foreach ($feeds as $feed) {
$reader = Reader::import($feed->getUrl());
foreach ($reader as $entry) {
$this->entries[] = $entry;
}
}
}
return $this->entries;
}
/**
* Simple utility function which imports any feed URL and
* determines the existence of Hub Server endpoints. This works
* best if directly given an instance of Zend_Feed_Reader_Atom|Rss
* to leverage off.
*
* @param Zend_Feed_Reader_FeedAbstract|\Zend\Feed\AbstractFeed|string $source
* @return array
*/
public static function detectHubs($source)
{
if (is_string($source)) {
$feed = Reader\Reader::import($source);
} elseif (is_object($source) && $source instanceof Reader\FeedAbstract) {
$feed = $source;
} elseif (is_object($source) && $source instanceof \Zend\Feed\AbstractFeed) {
$feed = Reader\Reader::importFeed($source);
} else {
require_once 'Zend/Feed/Pubsubhubbub/Exception.php';
throw new Exception('The source parameter was' . ' invalid, i.e. not a URL string or an instance of type' . ' Zend_Feed_Reader_FeedAbstract or Zend_Feed_Abstract');
}
return $feed->getHubs();
}
/**
* Constructor: Create a Source object which is largely just a normal
* Zend\Feed\Reader\AbstractFeed object only designed to retrieve feed level
* metadata from an Atom entry's source element.
*
* @param DOMElement $source
* @param string $xpathPrefix Passed from parent Entry object
* @param string $type Nearly always Atom 1.0
*/
public function __construct(\DOMElement $source, $xpathPrefix, $type = Reader\Reader::TYPE_ATOM_10)
{
$this->_domDocument = $source->ownerDocument;
$this->_xpath = new \DOMXPath($this->_domDocument);
$this->_data['type'] = $type;
$this->_registerNamespaces();
$this->_loadExtensions();
$atomClass = Reader\Reader::getPluginLoader()->getClassName('Atom\\Feed');
$this->_extensions['Atom\\Feed'] = new $atomClass($this->_domDocument, $this->_data['type'], $this->_xpath);
$atomClass = Reader\Reader::getPluginLoader()->getClassName('DublinCore\\Feed');
$this->_extensions['DublinCore\\Feed'] = new $atomClass($this->_domDocument, $this->_data['type'], $this->_xpath);
foreach ($this->_extensions as $extension) {
$extension->setXpathPrefix(rtrim($xpathPrefix, '/') . '/atom:source');
}
}
/**
* Constructor
*
* @param DOMElement $entry
* @param int $entryKey
* @param string $type
*/
public function __construct(DOMElement $entry, $entryKey, $type = null)
{
parent::__construct($entry, $entryKey, $type);
// Everyone by now should know XPath indices start from 1 not 0
$this->xpathQuery = '//atom:entry[' . ($this->entryKey + 1) . ']';
$manager = Reader\Reader::getExtensionManager();
$extensions = array('Atom\\Entry', 'Thread\\Entry', 'DublinCore\\Entry');
foreach ($extensions as $name) {
$extension = $manager->get($name);
$extension->setEntryElement($entry);
$extension->setEntryKey($entryKey);
$extension->setType($type);
$this->extensions[$name] = $extension;
}
}
/**
* @inheritDoc
*
*/
public function import()
{
if (empty($this->feedUri) || !is_string($this->feedUri)) {
throw new Exception\UnexpectedValueException(sprintf('Feed uri not valid.'));
}
$feed = Reader::import($this->feedUri);
foreach ($feed as $entry) {
if ($this->entryIsNew($entry)) {
$postId = $this->createPostFromEntry($entry);
if (!empty($this->entryParams['taxonomy'])) {
$this->createTermsFromEntry($postId, $entry);
}
}
}
}
/**
* Constructor
*
* @param Zend_Feed_Abstract $feed The source Zend_Feed object
* @param string $type Feed type
* @return void
*/
public function __construct(\DomDocument $dom, $type = null, \DOMXPath $xpath = null)
{
$this->_domDocument = $dom;
if ($type !== null) {
$this->_data['type'] = $type;
} else {
$this->_data['type'] = Reader\Reader::detectType($dom);
}
if ($xpath !== null) {
$this->_xpath = $xpath;
} else {
$this->_xpath = new \DOMXPath($this->_domDocument);
}
$this->_registerNamespaces();
}
public function __invoke(ContainerInterface $container) : AtomReader
{
$http = $container->get(FeedReaderHttpClientInterface::class);
FeedReader::setHttpClient($http);
FeedReader::setExtensionManager(new StandaloneExtensionManager());
$config = $container->get('config');
$config = $config['github'];
$reader = new AtomReader($config['user']);
$reader->setLimit($config['limit']);
$reader->addFilter(function ($entry) {
if (false !== strpos($entry->getLink(), 'weierophinney/mwop.net')) {
return false;
}
return true;
});
return $reader;
}
/**
* Constructor
*
* @param DOMDocument $dom
* @param string $type
*/
public function __construct(DOMDocument $dom, $type = null)
{
parent::__construct($dom, $type);
$manager = Reader\Reader::getExtensionManager();
$atomFeed = $manager->get('Atom\\Feed');
$atomFeed->setDomDocument($dom);
$atomFeed->setType($this->data['type']);
$atomFeed->setXpath($this->xpath);
$this->extensions['Atom\\Feed'] = $atomFeed;
$atomFeed = $manager->get('DublinCore\\Feed');
$atomFeed->setDomDocument($dom);
$atomFeed->setType($this->data['type']);
$atomFeed->setXpath($this->xpath);
$this->extensions['DublinCore\\Feed'] = $atomFeed;
foreach ($this->extensions as $extension) {
$extension->setXpathPrefix('/atom:feed');
}
}
public function getData()
{
// Fetch the latest Slashdot headlines
try {
$slashdotRss = \Zend\Feed\Reader\Reader::import('http://rss.slashdot.org/Slashdot/slashdot');
} catch (\Zend\Feed\Exception\Reader\RuntimeException $e) {
// feed import failed
echo "Exception caught importing feed: {$e->getMessage()}\n";
exit;
}
// Initialize the channel/feed data array
$channel = array('title' => $slashdotRss->getTitle(), 'link' => $slashdotRss->getLink(), 'description' => $slashdotRss->getDescription(), 'items' => array());
// Loop over each channel item/entry and store relevant data for each
foreach ($slashdotRss as $item) {
$channel['items'][] = array('title' => $item->getTitle(), 'link' => $item->getLink(), 'description' => $item->getDescription());
}
return $channel;
}
/**
* Constructor
*
* @param Zend_Feed_Entry_Abstract $entry
* @param int $entryKey
* @param string $type
* @return void
*/
public function __construct(\DOMElement $entry, $entryKey, $type = null)
{
$this->_entry = $entry;
$this->_entryKey = $entryKey;
$this->_domDocument = $entry->ownerDocument;
if ($type !== null) {
$this->_data['type'] = $type;
} else {
$this->_data['type'] = Reader\Reader::detectType($entry->ownerDocument, true);
}
// set the XPath query prefix for the entry being queried
if ($this->getType() == Reader\Reader::TYPE_RSS_10 || $this->getType() == Reader\Reader::TYPE_RSS_090) {
$this->setXpathPrefix('//rss:item[' . ($this->_entryKey + 1) . ']');
} elseif ($this->getType() == Reader\Reader::TYPE_ATOM_10 || $this->getType() == Reader\Reader::TYPE_ATOM_03) {
$this->setXpathPrefix('//atom:entry[' . ($this->_entryKey + 1) . ']');
} else {
$this->setXpathPrefix('//item[' . ($this->_entryKey + 1) . ']');
}
}
/**
* Constructor: Create a Source object which is largely just a normal
* Zend\Feed\Reader\AbstractFeed object only designed to retrieve feed level
* metadata from an Atom entry's source element.
*
* @param DOMElement $source
* @param string $xpathPrefix Passed from parent Entry object
* @param string $type Nearly always Atom 1.0
*/
public function __construct(DOMElement $source, $xpathPrefix, $type = Reader\Reader::TYPE_ATOM_10)
{
$this->domDocument = $source->ownerDocument;
$this->xpath = new DOMXPath($this->domDocument);
$this->data['type'] = $type;
$this->registerNamespaces();
$this->loadExtensions();
$manager = Reader\Reader::getExtensionManager();
$extensions = array('Atom\\Feed', 'DublinCore\\Feed');
foreach ($extensions as $name) {
$extension = $manager->get($name);
$extension->setDomDocument($this->domDocument);
$extension->setType($this->data['type']);
$extension->setXpath($this->xpath);
$this->extensions[$name] = $extension;
}
foreach ($this->extensions as $extension) {
$extension->setXpathPrefix(rtrim($xpathPrefix, '/') . '/atom:source');
}
}
public static function fetch($feed_url, $params = array())
{
try {
$news_feed = Reader::import($feed_url);
} catch (\Exception $e) {
return array();
}
if (is_null($news_feed)) {
return array();
}
$latest_news = array();
$article_num = 0;
foreach ($news_feed as $item) {
$article_num++;
$guid = $item->getId();
$title = $item->getTitle();
// Process categories.
$categories_raw = $item->getCategories()->getValues();
// Process main description.
$description = trim($item->getDescription());
// Remove extraneous tags.
$description = str_replace(array("\r", "\n"), array('', ' '), $description);
// Strip new lines.
$description = preg_replace('/<a[^(>)]+>read more<\\/a>/iu', '', $description);
// Remove "read more" link.
$web_url = $item->getLink();
if (is_array($web_url)) {
$web_url = $web_url[0];
}
if (!$web_url && substr($guid, 0, 4) == 'http') {
$web_url = $guid;
}
$author = $item->getAuthor();
if (is_array($author)) {
$author = $author[0]->nodeValue;
}
$news_item = array('guid' => 'rss_' . md5($guid), 'timestamp' => $item->getDateModified()->getTimestamp(), 'media_format' => 'mixed', 'title' => $title, 'body' => $description, 'web_url' => $web_url, 'author' => $author);
$latest_news[] = $news_item;
}
return $latest_news;
}
