2013-08-09 20:57:25 +04:00
|
|
|
<?php
|
2018-11-10 21:01:57 +03:00
|
|
|
require_once __DIR__ . '/lib/rssbridge.php';
|
2018-05-29 12:52:17 +03:00
|
|
|
|
2018-06-27 20:09:41 +03:00
|
|
|
Configuration::verifyInstallation();
|
|
|
|
Configuration::loadConfiguration();
|
|
|
|
|
|
|
|
Authentication::showPromptIfNeeded();
|
|
|
|
|
|
|
|
date_default_timezone_set('UTC');
|
2017-09-25 20:14:02 +03:00
|
|
|
|
|
|
|
/*
|
|
|
|
Move the CLI arguments to the $_GET array, in order to be able to use
|
|
|
|
rss-bridge from the command line
|
|
|
|
*/
|
Catching up | [Main] Debug mode, parse utils, MIME | [Bridges] Add/Improve 20 bridges (#802)
* Debug mode improvements
- Improve debug warning message
- Restore error reporting in debug mode
- Fix 'notice' messages for unset fields
* Add parsing utility functions
html.php
- extractFromDelimiters
- stripWithDelimiters
- stripRecursiveHTMLSection
- markdownToHtml (partial)
bridges
- remove now-duplicate functions
- call functions from html.php instead
* [Anidex] New bridge
Anime torrent tracker
* [Anime-Ultime] Restore thumbnail
* [CNET] Recreate bridge
Full rewrite as the previous one was broken
* [Dilbert] Minor URI fix
Use new self::URI property
* [EstCeQuonMetEnProd] Fix content extraction
Bridge was broken
* [Facebook] Fix "SpSonsSoriSsés" label
... which was taking space in item title
* [Futura-Sciences] Use HTTPS, More cleanup
Use HTTPS as FS now offer HTTPS
Clean additional useless HTML elements
* [GBATemp] Multiple fixes
- Fix categories: missing "break" statements
- Restore thumbnail as enclosure
- Fix date extraction
- Fix user blog post extraction
- Use getSimpleHTMLDOMCached
* [JapanExpo] Fix bridge, HTTPS, thumbnails
- Fix getSimpleHTMLDOMCached call
- Upgrade to HTTPS as JE now offers HTTPS
- Restore thumbnails as enclosures
* [LeMondeInformatique] Fix bridge, HTTPS
- Upgrade to HTTPS as LMI now offers HTTPS
- Restore thumbnails using small images
- Fix content extraction
- Fix text encoding issue
* [Nextgov] Fix content extraction
- Restore thumbnail and use small image
- Field extraction fixes
* [NextInpact] Add categories and filtering by type
- Offer all RSS feeds
- Allow filtering by article type
- Implement extraction for brief articles
- Remove article limit, many brief articles are publied all at once
* [NyaaTorrents] New bridge
Anime torrent tracker
* [Releases3DS] Cache content, restore thumbnail
- Use getSimpleHTMLDOMCached
- Restore thumbnail as enclosure
* [TheHackerNews] Fix bridge
- Fix content extraction including article body
- Restore thumbnail as enclosure
* [WeLiveSecurity] HTTPS, Fix content extraction
- Upgrade to HTTPS as WLS now offers HTTPS
- Fix content extraction including article body
* [WordPress] Reduce timeout, more content selectors
- Reduce timeout to use default one (1h)
- Add new content selector (articleBody)
- Find thumbnail and set as enclosure
- Fix <script> cleanup
* [YGGTorrent] Increase limit, use cache
- Increase item limit as uploads are very frequent
- Use getSimpleHTMLDOMCached
* [ZDNet] Rewrite with FeedExpander
- Upgrade to HTTPS as ZD now offers HTTPS
- Use FeedExpander for secondary fields
- Fix content extraction for article body
* [Main] Handle MIME type for enclosures
Many feed readers will ignore enclosures (e.g. thumbnails) with no MIME type. This commit adds automatic MIME type detection based on file extension (which may be inaccurate but is the only way without fetching the content).
One can force enclosure type using #.ext anchor (hacky, needs improving)
* [FeedExpander] Improve field extraction
- Add support for passing enclosures
- Improve author and uri extraction
- Fix 'notice' PHP error messages
* [Pull] Coding style fixes for #802
* [Pull] Implementing changes for #802
- Fix coding style issues with str append
- Remove useless CACHE_TIMEOUT
- Use count() instead of $limit
- Use defaultLinkTo() + handle strings
- Use http_build_query()
- Fix missing </em>
- Remove error_reporting(0)
- warning CSS (@LogMANOriginal)
- Fix typo in FeedExpander comment
* [Main] More documentation for markdownToHtml
See #802 for more details
2018-09-09 22:20:13 +03:00
|
|
|
if (isset($argv)) {
|
|
|
|
parse_str(implode('&', array_slice($argv, 1)), $cliArgs);
|
|
|
|
$params = array_merge($_GET, $cliArgs);
|
|
|
|
} else {
|
|
|
|
$params = $_GET;
|
|
|
|
}
|
2017-09-25 20:14:02 +03:00
|
|
|
|
2018-11-05 20:51:57 +03:00
|
|
|
define('USER_AGENT',
|
|
|
|
'Mozilla/5.0 (X11; Linux x86_64; rv:30.0) Gecko/20121202 Firefox/30.0(rss-bridge/'
|
|
|
|
. Configuration::$VERSION
|
|
|
|
. ';+'
|
|
|
|
. REPOSITORY
|
|
|
|
. ')'
|
|
|
|
);
|
|
|
|
|
|
|
|
ini_set('user_agent', USER_AGENT);
|
2015-11-30 12:47:16 +03:00
|
|
|
|
2014-05-25 21:56:59 +04:00
|
|
|
// default whitelist
|
|
|
|
$whitelist_default = array(
|
2017-08-05 16:46:16 +03:00
|
|
|
'BandcampBridge',
|
|
|
|
'CryptomeBridge',
|
|
|
|
'DansTonChatBridge',
|
|
|
|
'DuckDuckGoBridge',
|
|
|
|
'FacebookBridge',
|
2018-11-11 00:33:19 +03:00
|
|
|
'FlickrBridge',
|
2017-08-05 16:46:16 +03:00
|
|
|
'GooglePlusPostBridge',
|
|
|
|
'GoogleSearchBridge',
|
|
|
|
'IdenticaBridge',
|
|
|
|
'InstagramBridge',
|
|
|
|
'OpenClassroomsBridge',
|
|
|
|
'PinterestBridge',
|
|
|
|
'ScmbBridge',
|
|
|
|
'TwitterBridge',
|
|
|
|
'WikipediaBridge',
|
|
|
|
'YoutubeBridge');
|
2014-05-25 21:56:59 +04:00
|
|
|
|
2016-09-10 22:01:02 +03:00
|
|
|
try {
|
|
|
|
|
2018-11-11 00:26:56 +03:00
|
|
|
Bridge::setWhitelist($whitelist_default);
|
2017-03-08 13:56:39 +03:00
|
|
|
|
2018-07-21 19:15:07 +03:00
|
|
|
$showInactive = filter_input(INPUT_GET, 'show_inactive', FILTER_VALIDATE_BOOLEAN);
|
2017-10-12 19:14:34 +03:00
|
|
|
$action = array_key_exists('action', $params) ? $params['action'] : null;
|
|
|
|
$bridge = array_key_exists('bridge', $params) ? $params['bridge'] : null;
|
2016-09-10 22:01:02 +03:00
|
|
|
|
2018-08-09 20:14:10 +03:00
|
|
|
// Return list of bridges as JSON formatted text
|
|
|
|
if($action === 'list') {
|
|
|
|
|
|
|
|
$list = new StdClass();
|
|
|
|
$list->bridges = array();
|
|
|
|
$list->total = 0;
|
|
|
|
|
|
|
|
foreach(Bridge::listBridges() as $bridgeName) {
|
|
|
|
|
|
|
|
$bridge = Bridge::create($bridgeName);
|
|
|
|
|
|
|
|
if($bridge === false) { // Broken bridge, show as inactive
|
|
|
|
|
|
|
|
$list->bridges[$bridgeName] = array(
|
|
|
|
'status' => 'inactive'
|
|
|
|
);
|
|
|
|
|
|
|
|
continue;
|
|
|
|
|
|
|
|
}
|
|
|
|
|
2018-11-11 00:26:56 +03:00
|
|
|
$status = Bridge::isWhitelisted($bridgeName) ? 'active' : 'inactive';
|
2018-08-09 20:14:10 +03:00
|
|
|
|
|
|
|
$list->bridges[$bridgeName] = array(
|
|
|
|
'status' => $status,
|
|
|
|
'uri' => $bridge->getURI(),
|
|
|
|
'name' => $bridge->getName(),
|
2018-08-21 18:46:47 +03:00
|
|
|
'icon' => $bridge->getIcon(),
|
2018-08-09 20:14:10 +03:00
|
|
|
'parameters' => $bridge->getParameters(),
|
|
|
|
'maintainer' => $bridge->getMaintainer(),
|
|
|
|
'description' => $bridge->getDescription()
|
|
|
|
);
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
$list->total = count($list->bridges);
|
|
|
|
|
|
|
|
header('Content-Type: application/json');
|
|
|
|
echo json_encode($list, JSON_PRETTY_PRINT);
|
|
|
|
|
|
|
|
} elseif($action === 'display' && !empty($bridge)) {
|
2016-09-10 22:01:02 +03:00
|
|
|
|
2017-09-25 20:14:02 +03:00
|
|
|
$format = $params['format']
|
2017-08-28 21:45:04 +03:00
|
|
|
or returnClientError('You must specify a format!');
|
2013-08-09 20:57:25 +04:00
|
|
|
|
2016-09-10 22:01:02 +03:00
|
|
|
// DEPRECATED: 'nameFormat' scheme is replaced by 'name' in format parameter values
|
|
|
|
// this is to keep compatibility until futher complete removal
|
2017-07-29 20:28:00 +03:00
|
|
|
if(($pos = strpos($format, 'Format')) === (strlen($format) - strlen('Format'))) {
|
2016-09-10 22:01:02 +03:00
|
|
|
$format = substr($format, 0, $pos);
|
|
|
|
}
|
|
|
|
|
|
|
|
// whitelist control
|
2018-11-11 00:26:56 +03:00
|
|
|
if(!Bridge::isWhitelisted($bridge)) {
|
2016-09-10 22:01:02 +03:00
|
|
|
throw new \HttpException('This bridge is not whitelisted', 401);
|
|
|
|
die;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Data retrieval
|
|
|
|
$bridge = Bridge::create($bridge);
|
2016-10-02 17:43:08 +03:00
|
|
|
|
2017-10-12 19:14:34 +03:00
|
|
|
$noproxy = array_key_exists('_noproxy', $params) && filter_var($params['_noproxy'], FILTER_VALIDATE_BOOLEAN);
|
2017-07-29 20:28:00 +03:00
|
|
|
if(defined('PROXY_URL') && PROXY_BYBRIDGE && $noproxy) {
|
2017-02-14 19:28:07 +03:00
|
|
|
define('NOPROXY', true);
|
2016-09-26 00:22:33 +03:00
|
|
|
}
|
2016-09-10 22:01:02 +03:00
|
|
|
|
2018-10-15 18:21:43 +03:00
|
|
|
// Cache timeout
|
2018-03-14 20:06:36 +03:00
|
|
|
$cache_timeout = -1;
|
|
|
|
if(array_key_exists('_cache_timeout', $params)) {
|
2018-10-15 18:21:43 +03:00
|
|
|
|
2018-03-14 20:06:36 +03:00
|
|
|
if(!CUSTOM_CACHE_TIMEOUT) {
|
|
|
|
throw new \HttpException('This server doesn\'t support "_cache_timeout"!');
|
|
|
|
}
|
|
|
|
|
|
|
|
$cache_timeout = filter_var($params['_cache_timeout'], FILTER_VALIDATE_INT);
|
2018-10-15 18:21:43 +03:00
|
|
|
|
|
|
|
} else {
|
|
|
|
$cache_timeout = $bridge->getCacheTimeout();
|
2018-03-14 20:06:36 +03:00
|
|
|
}
|
|
|
|
|
2018-09-22 16:35:08 +03:00
|
|
|
// Remove parameters that don't concern bridges
|
|
|
|
$bridge_params = array_diff_key(
|
|
|
|
$params,
|
|
|
|
array_fill_keys(
|
|
|
|
array(
|
|
|
|
'action',
|
|
|
|
'bridge',
|
|
|
|
'format',
|
|
|
|
'_noproxy',
|
|
|
|
'_cache_timeout',
|
2018-11-02 13:05:46 +03:00
|
|
|
'_error_time'
|
2018-09-22 16:35:08 +03:00
|
|
|
), '')
|
|
|
|
);
|
|
|
|
|
|
|
|
// Remove parameters that don't concern caches
|
|
|
|
$cache_params = array_diff_key(
|
|
|
|
$params,
|
|
|
|
array_fill_keys(
|
|
|
|
array(
|
|
|
|
'action',
|
|
|
|
'format',
|
|
|
|
'_noproxy',
|
|
|
|
'_cache_timeout',
|
2018-11-02 13:05:46 +03:00
|
|
|
'_error_time'
|
2018-09-22 16:35:08 +03:00
|
|
|
), '')
|
|
|
|
);
|
|
|
|
|
2016-10-08 16:28:36 +03:00
|
|
|
// Initialize cache
|
|
|
|
$cache = Cache::create('FileCache');
|
2018-11-06 20:35:40 +03:00
|
|
|
$cache->setPath(PATH_CACHE);
|
2016-10-08 17:18:10 +03:00
|
|
|
$cache->purgeCache(86400); // 24 hours
|
2018-09-22 16:35:08 +03:00
|
|
|
$cache->setParameters($cache_params);
|
2016-10-20 23:03:23 +03:00
|
|
|
|
2018-10-15 18:21:43 +03:00
|
|
|
$items = array();
|
|
|
|
$infos = array();
|
|
|
|
$mtime = $cache->getTime();
|
|
|
|
|
|
|
|
if($mtime !== false
|
|
|
|
&& (time() - $cache_timeout < $mtime)
|
2018-11-10 22:44:23 +03:00
|
|
|
&& !Debug::isEnabled()) { // Load cached data
|
2018-10-15 18:21:43 +03:00
|
|
|
|
|
|
|
// Send "Not Modified" response if client supports it
|
|
|
|
// Implementation based on https://stackoverflow.com/a/10847262
|
|
|
|
if(isset($_SERVER['HTTP_IF_MODIFIED_SINCE'])) {
|
|
|
|
$stime = strtotime($_SERVER['HTTP_IF_MODIFIED_SINCE']);
|
|
|
|
|
|
|
|
if($mtime <= $stime) { // Cached data is older or same
|
2018-11-05 21:28:47 +03:00
|
|
|
header('Last-Modified: ' . gmdate('D, d M Y H:i:s ', $mtime) . 'GMT', true, 304);
|
2018-10-15 18:21:43 +03:00
|
|
|
die();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
$cached = $cache->loadData();
|
|
|
|
|
|
|
|
if(isset($cached['items']) && isset($cached['extraInfos'])) {
|
|
|
|
$items = $cached['items'];
|
|
|
|
$infos = $cached['extraInfos'];
|
|
|
|
}
|
|
|
|
|
|
|
|
} else { // Collect new data
|
|
|
|
|
|
|
|
try {
|
|
|
|
$bridge->setDatas($bridge_params);
|
|
|
|
$bridge->collectData();
|
|
|
|
|
|
|
|
$items = $bridge->getItems();
|
|
|
|
$infos = array(
|
|
|
|
'name' => $bridge->getName(),
|
|
|
|
'uri' => $bridge->getURI(),
|
|
|
|
'icon' => $bridge->getIcon()
|
|
|
|
);
|
|
|
|
} catch(Error $e) {
|
2018-10-24 16:50:48 +03:00
|
|
|
error_log($e);
|
|
|
|
|
2018-10-15 18:21:43 +03:00
|
|
|
$item = array();
|
|
|
|
|
|
|
|
// Create "new" error message every 24 hours
|
|
|
|
$params['_error_time'] = urlencode((int)(time() / 86400));
|
|
|
|
|
|
|
|
// Error 0 is a special case (i.e. "trying to get property of non-object")
|
|
|
|
if($e->getCode() === 0) {
|
|
|
|
$item['title'] = 'Bridge encountered an unexpected situation! (' . $params['_error_time'] . ')';
|
|
|
|
} else {
|
|
|
|
$item['title'] = 'Bridge returned error ' . $e->getCode() . '! (' . $params['_error_time'] . ')';
|
|
|
|
}
|
|
|
|
|
|
|
|
$item['uri'] = parse_url($_SERVER['REQUEST_URI'], PHP_URL_PATH) . '?' . http_build_query($params);
|
|
|
|
$item['timestamp'] = time();
|
|
|
|
$item['content'] = buildBridgeException($e, $bridge);
|
|
|
|
|
|
|
|
$items[] = $item;
|
|
|
|
} catch(Exception $e) {
|
2018-10-24 16:50:48 +03:00
|
|
|
error_log($e);
|
|
|
|
|
2018-10-15 18:21:43 +03:00
|
|
|
$item = array();
|
|
|
|
|
|
|
|
// Create "new" error message every 24 hours
|
|
|
|
$params['_error_time'] = urlencode((int)(time() / 86400));
|
|
|
|
|
|
|
|
$item['uri'] = parse_url($_SERVER['REQUEST_URI'], PHP_URL_PATH) . '?' . http_build_query($params);
|
|
|
|
$item['title'] = 'Bridge returned error ' . $e->getCode() . '! (' . $params['_error_time'] . ')';
|
|
|
|
$item['timestamp'] = time();
|
|
|
|
$item['content'] = buildBridgeException($e, $bridge);
|
|
|
|
|
|
|
|
$items[] = $item;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Store data in cache
|
|
|
|
$cache->saveData(array(
|
|
|
|
'items' => $items,
|
|
|
|
'extraInfos' => $infos
|
|
|
|
));
|
|
|
|
|
2017-07-29 20:16:16 +03:00
|
|
|
}
|
2016-09-10 22:05:29 +03:00
|
|
|
|
2016-09-10 22:01:02 +03:00
|
|
|
// Data transformation
|
|
|
|
try {
|
|
|
|
$format = Format::create($format);
|
2018-10-15 18:21:43 +03:00
|
|
|
$format->setItems($items);
|
|
|
|
$format->setExtraInfos($infos);
|
2018-10-22 20:14:49 +03:00
|
|
|
$format->setLastModified($cache->getTime());
|
2016-11-29 03:48:59 +03:00
|
|
|
$format->display();
|
2018-04-04 21:02:40 +03:00
|
|
|
} catch(Error $e) {
|
2018-10-24 16:50:48 +03:00
|
|
|
error_log($e);
|
2018-11-05 21:28:47 +03:00
|
|
|
header('Content-Type: text/html', true, $e->getCode());
|
2017-07-29 20:16:16 +03:00
|
|
|
die(buildTransformException($e, $bridge));
|
2018-04-06 21:34:44 +03:00
|
|
|
} catch(Exception $e) {
|
2018-10-24 16:50:48 +03:00
|
|
|
error_log($e);
|
2018-11-05 21:28:47 +03:00
|
|
|
header('Content-Type: text/html', true, $e->getCode());
|
2018-10-15 18:21:43 +03:00
|
|
|
die(buildTransformException($e, $bridge));
|
2018-04-06 21:34:44 +03:00
|
|
|
}
|
2018-07-21 19:15:07 +03:00
|
|
|
} else {
|
2018-11-11 00:26:56 +03:00
|
|
|
echo BridgeList::create($showInactive);
|
2016-09-10 22:01:02 +03:00
|
|
|
}
|
2017-07-29 20:28:00 +03:00
|
|
|
} catch(HttpException $e) {
|
2018-10-24 16:50:48 +03:00
|
|
|
error_log($e);
|
2018-11-05 21:28:47 +03:00
|
|
|
header('Content-Type: text/plain', true, $e->getCode());
|
2016-09-10 22:01:02 +03:00
|
|
|
die($e->getMessage());
|
2017-07-29 20:28:00 +03:00
|
|
|
} catch(\Exception $e) {
|
2018-10-24 16:50:48 +03:00
|
|
|
error_log($e);
|
2016-09-10 22:01:02 +03:00
|
|
|
die($e->getMessage());
|
2013-08-09 20:57:25 +04:00
|
|
|
}
|