Set how much feed autodiscovery to do
public set_autodiscovery_level ( integer $level = SIMPLEPIE_LOCATOR_ALL ) | ||
$level | integer | Feed Autodiscovery Level (level can be a combination of the above constants, see bitwise OR operator) |
function add($render) { $url = $_REQUEST['url']; require_once 'lib/simplepie/simplepie.inc'; $pie = new SimplePie(); $pie->enable_cache(false); $pie->set_autodiscovery_level(SIMPLEPIE_LOCATOR_ALL); $pie->set_feed_url($url); $pie->init(); $feed_url = $pie->feed_url; $feed_title = $pie->get_title(); // Save feed to insert into session variables for later insertion into db // only do this if we found items at the given url. This way we won't // insert broken urls in doadd(). Also prevents inserting a new feed // that never gets subscribed to in the following page. if (count($pie->get_items()) > 0) { $_SESSION['new_feed_url'] = $feed_url; $_SESSION['new_feed_name'] = $feed_title; } else { $_SESSION['new_feed_url'] = NULL; $_SESSION['new_feed_name'] = NULL; } $render->assign('url', $url); $render->assign('feed_url', $feed_url); $render->assign('items', array_slice($pie->get_items(), 0, 5)); $render->assign('feed', $pie); $render->assign('title', 'Adding Feed'); $render->display('feed_search.tpl'); }
// Get RSS/Atom feed //////////////////////////////// if (!$html_only) { debug('--------'); debug("Attempting to process URL as feed"); // Send user agent header showing PHP (prevents a HTML response from feedburner) $http->userAgentDefault = HumbleHttpAgent::UA_PHP; // configure SimplePie HTTP extension class to use our HumbleHttpAgent instance SimplePie_HumbleHttpAgent::set_agent($http); $feed = new SimplePie(); // some feeds use the text/html content type - force_feed tells SimplePie to process anyway $feed->force_feed(true); $feed->set_file_class('SimplePie_HumbleHttpAgent'); //$feed->set_feed_url($url); // colons appearing in the URL's path get encoded $feed->feed_url = $url; $feed->set_autodiscovery_level(SIMPLEPIE_LOCATOR_NONE); $feed->set_timeout(20); $feed->enable_cache(false); $feed->set_stupidly_fast(true); $feed->enable_order_by_date(false); // we don't want to do anything to the feed $feed->set_url_replacements(array()); // initialise the feed // the @ suppresses notices which on some servers causes a 500 internal server error $result = @$feed->init(); //$feed->handle_content_type(); //$feed->get_title(); if ($result && (!is_array($feed->data) || count($feed->data) == 0)) { die('Sorry, no feed items found'); } // from now on, we'll identify ourselves as a browser
/** * A clone of the function 'fetch_feed' in wp-includes/feed.php [line #529] * * Called from 'wprss_get_feed_items' * * @since 3.5 */ function wprss_fetch_feed($url, $source = NULL) { // Import SimplePie require_once ABSPATH . WPINC . '/class-feed.php'; // Trim the URL $url = trim($url); // Initialize the Feed $feed = new SimplePie(); // Obselete method calls ? //$feed->set_cache_class( 'WP_Feed_Cache' ); //$feed->set_file_class( 'WP_SimplePie_File' ); $feed->set_feed_url($url); $feed->set_autodiscovery_level(SIMPLEPIE_LOCATOR_ALL); // If a feed source was passed if ($source !== NULL) { // Get the force feed option for the feed source $force_feed = get_post_meta($source, 'wprss_force_feed', TRUE); // If turned on, force the feed if ($force_feed == 'true') { $feed->force_feed(TRUE); } } // Set timeout to 30s. Default: 15s $feed->set_timeout(30); //$feed->set_cache_duration( apply_filters( 'wp_feed_cache_transient_lifetime', 12 * HOUR_IN_SECONDS, $url ) ); $feed->enable_cache(FALSE); // Reference array action hook, for the feed object and the URL do_action_ref_array('wp_feed_options', array(&$feed, $url)); // Prepare the tags to strip from the feed $tags_to_strip = apply_filters('wprss_feed_tags_to_strip', $feed->strip_htmltags, $source); // Strip them $feed->strip_htmltags($tags_to_strip); // Fetch the feed $feed->init(); $feed->handle_content_type(); // Convert the feed error into a WP_Error, if applicable if ($feed->error()) { return new WP_Error('simplepie-error', $feed->error()); } // If no error, return the feed return $feed; }
function RssFeed($link) { //process rss $feed_url = $link; $items_per_feed = 10; $items_max_age = '-60 days'; $max_age = $items_max_age ? date('Y-m-d H:i:s', strtotime($items_max_age)) : null; $items = array(); App::import('vendor', 'simplepie/simplepie'); $feed = new SimplePie(); $feed->set_cache_location(CACHE . 'simplepie'); $feed->set_feed_url($feed_url); $feed->set_autodiscovery_level(SIMPLEPIE_LOCATOR_NONE); $feed->init(); if ($feed->error() || $feed->feed_url != $feed_url) { return false; } for ($i = 0; $i < $feed->get_item_quantity($items_per_feed); $i++) { $feeditem = $feed->get_item($i); # create a NoseRub item out of the feed item $item = array(); $item['datetime'] = $feeditem->get_date('Y-m-d H:i:s'); if ($max_age && $item['datetime'] < $max_age) { # we can stop here, as we do not expect any newer items break; } $item['title'] = $feeditem->get_title(); $item['url'] = $feeditem->get_link(); //$item['intro'] = @$intro; //$item['type'] = @$token; //$item['username'] = $username; $items[] = $item; } unset($feed); $items; foreach ($items as $_item) { echo '<a href="' . $_item['url'] . '">' . $_item['title'] . '</a><br/>'; } //end process rss }
/** * get title, url and preview for rss-feed * * @param string $feed_url * @param int $max_items maximum number of items to fetch * @return array * @access */ function getInfoFromFeed($username, $service_type_id, $feed_url, $max_items = 5) { # needed for autodiscovery of feed //require 'simplepie/simplepie.php'; $feed = new SimplePie(); $feed->set_cache_location(CACHE . 'simplepie'); $feed->set_feed_url($feed_url); $feed->set_autodiscovery_level(SIMPLEPIE_LOCATOR_ALL); @$feed->init(); if ($feed->error()) { return false; } $data = array(); $data['title'] = $feed->get_title(); $data['account_url'] = $feed->get_link(); $data['feed_url'] = $feed->feed_url; unset($feed); if (!$data['account_url']) { $data['account_url'] = $data['feed_url']; } $data['service_id'] = 8; # any RSS-Feed $data['username'] = '******'; $data['service_type_id'] = $service_type_id; $items = $this->feed2array($username, 8, $data['service_type_id'], $data['feed_url'], 5, null); if (!$items) { return false; } $data['items'] = $items; return $data; }
/** * A clone of the function 'fetch_feed' in wp-includes/feed.php [line #529] * * Called from 'wprss_get_feed_items' * * @since 3.5 */ function wprss_fetch_feed($url, $source = NULL, $param_force_feed = FALSE) { // Trim the URL $url = trim($url); // Initialize the Feed $feed = new SimplePie(); // Obselete method calls ? //$feed->set_cache_class( 'WP_Feed_Cache' ); //$feed->set_file_class( 'WP_SimplePie_File' ); $feed->set_feed_url($url); $feed->set_autodiscovery_level(SIMPLEPIE_LOCATOR_ALL); // If a feed source was passed if ($source !== NULL || $param_force_feed) { // Get the force feed option for the feed source $force_feed = get_post_meta($source, 'wprss_force_feed', TRUE); // If turned on, force the feed if ($force_feed == 'true' || $param_force_feed) { $feed->force_feed(TRUE); } } // Set timeout limit $fetch_time_limit = wprss_get_feed_fetch_time_limit(); $feed->set_timeout($fetch_time_limit); //$feed->set_cache_duration( apply_filters( 'wp_feed_cache_transient_lifetime', 12 * HOUR_IN_SECONDS, $url ) ); $feed->enable_cache(FALSE); // Reference array action hook, for the feed object and the URL do_action_ref_array('wp_feed_options', array(&$feed, $url)); // Prepare the tags to strip from the feed $tags_to_strip = apply_filters('wprss_feed_tags_to_strip', $feed->strip_htmltags, $source); // Strip them $feed->strip_htmltags($tags_to_strip); do_action('wprss_fetch_feed_before', $feed); // Fetch the feed $feed->init(); $feed->handle_content_type(); do_action('wprss_fetch_feed_after', $feed); // Convert the feed error into a WP_Error, if applicable if ($feed->error()) { if ($source !== NULL) { $msg = sprintf(__('Failed to fetch the RSS feed. Error: %s', WPRSS_TEXT_DOMAIN), $feed->error()); update_post_meta($source, 'wprss_error_last_import', $msg); } return new WP_Error('simplepie-error', $feed->error()); } // If no error, return the feed and remove any error meta delete_post_meta($source, "wprss_error_last_import"); return $feed; }
public static function get_default_item() { $id = filter_input(INPUT_POST, 'id'); $value_default = filter_input(INPUT_POST, 'val_default'); if ($value_default == '') { return 'Do nothing!'; } $feed = new SimplePie(); $path = OGRAB_EDATA . 'item-' . $id . DS . 'row-default.dat'; $feed->set_feed_url($value_default); $feed->set_autodiscovery_level(SIMPLEPIE_LOCATOR_NONE); $feed->set_timeout(20); $feed->enable_cache(false); $feed->set_stupidly_fast(true); $feed->enable_order_by_date(false); // we don't want to do anything to the feed $feed->set_url_replacements(array()); $result = $feed->init(); if (isset($_GET['x'])) { echo "\n\n<br /><i><b>File:</b>" . __FILE__ . ' <b>Line:</b>' . __LINE__ . "</i><br />\n\n"; echo "<p>URL: [{$value_default}]</p>"; echo "<p>Error: [{$feed->error}]</p>"; } $items = $feed->get_items(); $c_items = count($items); if ($c_items == 0) { echo "<p>Error: [{$feed->error}]</p>"; return array(); } $row = new stdclass(); $row->title = html_entity_decode($items[0]->get_title(), ENT_QUOTES, 'UTF-8'); # the title for the post $row->link = $items[0]->get_link(); # a single link for the post $row->description = $items[0]->get_description(); # the content of the post (prefers summaries) $row->author = $items[0]->get_author(); # a single author for the post $row->date = $items[0]->get_date('Y-m-d H:i:s'); $row->enclosures = $items[0]->get_enclosures(); if (!is_file($path)) { $source = new stdClass(); } else { $source = ogb_common::get_default_data('', $id); } $source->so = $row; $cache = serialize($source); if (isset($_GET['x2'])) { //echo "\n\n<br /><i><b>File:</b>".__FILE__.' <b>Line:</b>'.__LINE__."</i><br />\n\n"; echo '<br>Path: ' . $path; } ogbFile::write($path, $cache); exit; }
public static function get_items_feed($url, $params = null) { $feed = new SimplePie(); $mode = isset($params->mode) ? $params->mode : 0; if ($mode == 0) { $feed->set_feed_url($url); } else { $html = ogbFile::get_curl($url); $feed->set_raw_data($html); } $feed->set_autodiscovery_level(SIMPLEPIE_LOCATOR_NONE); $feed->set_timeout(20); $feed->enable_cache(false); $feed->set_stupidly_fast(true); $feed->enable_order_by_date(false); // we don't want to do anything to the feed $feed->set_url_replacements(array()); $feed->force_feed(true); $result = $feed->init(); if (isset($_GET['x'])) { echo "\n\n<br /><i><b>File:</b>" . __FILE__ . ' <b>Line:</b>' . __LINE__ . "</i><br />\n\n"; echo "<p>URL: [{$url}]</p>"; echo "<p>Error: [{$feed->error}]</p>"; } $items = $feed->get_items(); $c_items = count($items); if ($c_items == 0) { echo "<p>Error: [{$feed->error}]</p>"; return array(); } for ($i = 0; $i < count($items); $i++) { $row = new stdclass(); $row->title = $items[$i]->get_title(); # the title for the post $row->link = $items[$i]->get_link(); # a single link for the post $row->description = $items[$i]->get_description(); # the content of the post (prefers summaries) $row->author = $items[$i]->get_author(); # a single author for the post $row->date = $items[$i]->get_date('Y-m-d H:i:s'); $row->enclosures = $items[$i]->get_enclosures(); $rows[] = $row; } return $rows; }
$feeds = runSQL($sql); $feeds_parse = array(); $feed_count = 0; //$feeds_parse['url'] = array(); //$feeds_parse['curl'] = array(); //$feeds_parse['data'] = array(); //$feeds_parse['id'] = array(); //$feeds_parse['mirror_url'] = array(); $master_curl = curl_multi_init(); //$data = new SimplePie_Cache_Extras(); $data = new SimplePie(); $data->set_cache_duration(300); $data->set_cache_location(MAGPIE_CACHE_DIR); $data->enable_cache(true); $data->set_sanitize_class('SimplePie_Sanitize_Null'); $data->set_autodiscovery_level(SIMPLEPIE_LOCATOR_ALL); //$data->set_stupidly_fast(true); // Don't need this $data->enable_order_by_date(false); foreach ($feeds as $feed) { if ($conf['debug'] == 'true') { print 'Fetching ' . $feed['url'] . " "; } // if($conf['debug'] == 'true') flush(); $enc = ''; // $data = fetch_rss($feed['url']); /* if(file_exists("mirror/" . md5($feed['url']) . ".xml")) { // $data = new SimplePie_Cache_Extras("mirror/" . md5($feed['url']) . ".xml"); $data->set_feed_url("mirror/" . md5($feed['url']) . ".xml"); // $data->set_cache_duration(300); $cache_time = $data->get_cache_time_remaining();
function get() { $purifier_config = HTMLPurifier_Config::createDefault(); $purifier_config->set('Cache.SerializerPath', 'cache'); // TODO: This feature is very nice, but breaks titles now that we purify them. Titles only need their entities fixed, so we shouldn't really purify them allowing us to turn this back on # $purifier_config->set('AutoFormat.Linkify', true); // Allow flash embeds in newer versions of purifier $purifier_config->set('HTML.SafeObject', true); $purifier_config->set('Output.FlashCompat', true); $purifier_config->set('HTML.FlashAllowFullScreen', true); $purifier = new HTMLPurifier($purifier_config); $query = 'SELECT * FROM lylina_feeds'; $feeds = $this->db->GetAll($query); $pie = new SimplePie(); $pie->enable_cache(false); $pie->set_sanitize_class('SimplePie_Sanitize_Null'); $pie->set_autodiscovery_level(SIMPLEPIE_LOCATOR_ALL); $pie->enable_order_by_date(false); // Array storing feeds which need to be parsed $feeds_parse = array(); // Keep track of how many we need to parse $feeds_count = 0; // Build array of feeds to fetch and their metadata foreach ($feeds as $feed) { // Track our cache $mod_time = -1; $cache_path = 'cache/' . md5($feed['url']) . '.xml'; if (file_exists($cache_path)) { $mod_time = @filemtime($cache_path); $filemd5 = @md5_file($cache_path); } else { $mod_time = -1; $filemd5 = 0; } // If our cache is older than 5 minutes, or doesn't exist, fetch new feeds if (time() - $mod_time > 300 || $mod_time == -1) { #if(true) { $feeds_parse[$feeds_count] = array(); $feeds_parse[$feeds_count]['url'] = $feed['url']; $feeds_parse[$feeds_count]['id'] = $feed['id']; $feeds_parse[$feeds_count]['name'] = $feed['name']; $feeds_parse[$feeds_count]['icon'] = $feed['favicon_url']; $feeds_parse[$feeds_count]['cache_path'] = $cache_path; $feeds_parse[$feeds_count]['filemd5'] = $filemd5; $feeds_parse[$feeds_count]['mod'] = $mod_time; $feeds_count++; } } // Get the data for feeds we need to parse $curl = new Curl_Get(); $feeds_data = $curl->multi_get($feeds_parse); // Handle the data and parse the feeds for ($n = 0; $n < count($feeds_parse); $n++) { $data = $feeds_data[$n]; $info = $feeds_parse[$n]; // If we got an error back from Curl if (isset($data['error']) && $data['error'] > 0) { // Should be logged error_log("Curl error: " . $data['error']); // If the feed has been retrieved with content, we should save it } elseif ($data['data'] != NULL) { file_put_contents($info['cache_path'], $data['data']); // Otherwise we've gotten an error on the feed, or there is nothing new, let's freshen the cache } else { touch($info['cache_path']); } } // Clear the file stat cache so we get good data on feed mirror size changes clearstatcache(); for ($n = 0; $n < count($feeds_parse); $n++) { $data = $feeds_data[$n]; $info = $feeds_parse[$n]; if ($data['data'] != NULL && md5_file($info['cache_path']) !== $info['filemd5']) { $pie->set_feed_url($info['cache_path']); $pie->init(); // If SimplePie finds a new RSS URL, let's update our cache if ($pie->feed_url != $info['url']) { $this->db->Execute('UPDATE lylina_items SET url=?, fallback_url=? WHERE id=?', array($pie->feed_url, $info['url'], $info['id'])); } // Update the real feed title - users who already have the feed added won't see the change // This is to prevent garbage names from OPML imports, which eventually won't be a problem, // but it's probably a good idea to keep the global title current anyway if ($pie->get_title() != $info['name']) { $this->db->Execute('UPDATE lylina_feeds SET name=? WHERE id=?', array($pie->get_title(), $info['id'])); } // TODO: Favicon handling isn't real pretty // If we have a new favicon URL, no cache, or stale cache, update cache if (!file_exists('cache/' . md5($info['url']) . '.ico') || time() - filemtime('cache/' . md5($info['url']) . '.ico') > 7 * 24 * 60 * 60 || $pie->get_favicon() != $info['icon']) { $this->update_favicon($info, $pie); } // If we can successfully parse the file, format them if ($pie->get_items()) { $this->insert_items($info, $pie, $purifier); } } else { // TODO: Provide debugging } } }
function feed2array($feed_url, $items_per_feed = 5, $items_max_age = '-21 days') { if (!$feed_url) { return false; } # get info about service type $max_age = $items_max_age ? date('Y-m-d H:i:s', strtotime($items_max_age)) : null; $items = array(); $feed = new SimplePie(); $feed->set_cache_location(CACHE . 'simplepie'); $feed->set_feed_url($feed_url); $feed->set_autodiscovery_level(SIMPLEPIE_LOCATOR_NONE); $feed->init(); if ($feed->error() || $feed->feed_url != $feed_url) { return false; } for ($i = 0; $i < $feed->get_item_quantity($items_per_feed); $i++) { $feeditem = $feed->get_item($i); # create a NoseRub item out of the feed item $item = array(); $item['datetime'] = $feeditem->get_date('Y-m-d H:i:s'); if ($max_age && $item['datetime'] < $max_age) { # we can stop here, as we do not expect any newer items break; } $item['title'] = $feeditem->get_title(); $item['url'] = $feeditem->get_link(); $item['intro'] = @$intro; $item['type'] = @$token; $item['username'] = $username; $items[] = $item; } unset($feed); return $items; }