+ 'thumbnail': self._get_thumbnail_url(uri, itemdoc),
+ 'description': description,
+ 'duration': float_or_none(content_el.attrib.get('duration')),
+ 'timestamp': timestamp,
+ }
+
+ def _get_feed_query(self, uri):
+ data = {'uri': uri}
+ if self._LANG:
+ data['lang'] = self._LANG
+ return data
+
+ def _get_videos_info(self, uri, use_hls=True):
+ video_id = self._id_from_uri(uri)
+ feed_url = self._get_feed_url(uri)
+ info_url = update_url_query(feed_url, self._get_feed_query(uri))
+ return self._get_videos_info_from_url(info_url, video_id, use_hls)
+
+ def _get_videos_info_from_url(self, url, video_id, use_hls=True):
+ idoc = self._download_xml(
+ url, video_id,
+ 'Downloading info', transform_source=fix_xml_ampersands)
+
+ title = xpath_text(idoc, './channel/title')
+ description = xpath_text(idoc, './channel/description')
+
+ entries = []
+ for item in idoc.findall('.//item'):
+ info = self._get_video_info(item, use_hls)
+ if info:
+ entries.append(info)
+
+ return self.playlist_result(
+ entries, playlist_title=title, playlist_description=description)
+
+ def _extract_triforce_mgid(self, webpage, data_zone=None, video_id=None):
+ triforce_feed = self._parse_json(self._search_regex(
+ r'triforceManifestFeed\s*=\s*({.+?})\s*;\s*\n', webpage,
+ 'triforce feed', default='{}'), video_id, fatal=False)
+
+ data_zone = self._search_regex(
+ r'data-zone=(["\'])(?P<zone>.+?_lc_promo.*?)\1', webpage,
+ 'data zone', default=data_zone, group='zone')
+
+ feed_url = try_get(
+ triforce_feed, lambda x: x['manifest']['zones'][data_zone]['feed'],
+ compat_str)
+ if not feed_url:
+ return
+
+ feed = self._download_json(feed_url, video_id, fatal=False)
+ if not feed:
+ return
+
+ return try_get(feed, lambda x: x['result']['data']['id'], compat_str)
+
+ def _extract_mgid(self, webpage):
+ try:
+ # the url can be http://media.mtvnservices.com/fb/{mgid}.swf
+ # or http://media.mtvnservices.com/{mgid}
+ og_url = self._og_search_video_url(webpage)
+ mgid = url_basename(og_url)
+ if mgid.endswith('.swf'):
+ mgid = mgid[:-4]
+ except RegexNotFoundError:
+ mgid = None
+
+ if mgid is None or ':' not in mgid:
+ mgid = self._search_regex(
+ [r'data-mgid="(.*?)"', r'swfobject\.embedSWF\(".*?(mgid:.*?)"'],
+ webpage, 'mgid', default=None)
+
+ if not mgid:
+ sm4_embed = self._html_search_meta(
+ 'sm4:video:embed', webpage, 'sm4 embed', default='')
+ mgid = self._search_regex(
+ r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=None)
+
+ if not mgid:
+ mgid = self._extract_triforce_mgid(webpage)
+
+ return mgid
+
+ def _real_extract(self, url):
+ title = url_basename(url)
+ webpage = self._download_webpage(url, title)
+ mgid = self._extract_mgid(webpage)
+ videos_info = self._get_videos_info(mgid)
+ return videos_info
+
+
+class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
+ IE_NAME = 'mtvservices:embedded'
+ _VALID_URL = r'https?://media\.mtvnservices\.com/embed/(?P<mgid>.+?)(\?|/|$)'
+
+ _TEST = {
+ # From http://www.thewrap.com/peter-dinklage-sums-up-game-of-thrones-in-45-seconds-video/
+ 'url': 'http://media.mtvnservices.com/embed/mgid:uma:video:mtv.com:1043906/cp~vid%3D1043906%26uri%3Dmgid%3Auma%3Avideo%3Amtv.com%3A1043906',
+ 'md5': 'cb349b21a7897164cede95bd7bf3fbb9',
+ 'info_dict': {
+ 'id': '1043906',
+ 'ext': 'mp4',
+ 'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds',
+ 'description': '"Sexy sexy sexy, stabby stabby stabby, beautiful language," says Peter Dinklage as he tries summarizing "Game of Thrones" in under a minute.',
+ 'timestamp': 1400126400,
+ 'upload_date': '20140515',
+ },
+ }
+
+ @staticmethod
+ def _extract_url(webpage):
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media.mtvnservices.com/embed/.+?)\1', webpage)
+ if mobj:
+ return mobj.group('url')
+
+ def _get_feed_url(self, uri):
+ video_id = self._id_from_uri(uri)
+ config = self._download_json(
+ 'http://media.mtvnservices.com/pmt/e1/access/index.html?uri=%s&configtype=edge' % uri, video_id)
+ return self._remove_template_parameter(config['feedWithQueryParams'])
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ mgid = mobj.group('mgid')
+ return self._get_videos_info(mgid)
+
+
+class MTVIE(MTVServicesInfoExtractor):
+ IE_NAME = 'mtv'
+ _VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|(?:full-)?episodes)/(?P<id>[^/?#.]+)'
+ _FEED_URL = 'http://www.mtv.com/feeds/mrss/'
+
+ _TESTS = [{
+ 'url': 'http://www.mtv.com/video-clips/vl8qof/unlocking-the-truth-trailer',
+ 'md5': '1edbcdf1e7628e414a8c5dcebca3d32b',
+ 'info_dict': {
+ 'id': '5e14040d-18a4-47c4-a582-43ff602de88e',
+ 'ext': 'mp4',
+ 'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer',
+ 'description': '"Unlocking the Truth" premieres August 17th at 11/10c.',
+ 'timestamp': 1468846800,
+ 'upload_date': '20160718',
+ },
+ }, {
+ 'url': 'http://www.mtv.com/full-episodes/94tujl/unlocking-the-truth-gates-of-hell-season-1-ep-101',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.mtv.com/episodes/g8xu7q/teen-mom-2-breaking-the-wall-season-7-ep-713',
+ 'only_matching': True,
+ }]
+
+
+class MTVJapanIE(MTVServicesInfoExtractor):
+ IE_NAME = 'mtvjapan'
+ _VALID_URL = r'https?://(?:www\.)?mtvjapan\.com/videos/(?P<id>[0-9a-z]+)'
+
+ _TEST = {
+ 'url': 'http://www.mtvjapan.com/videos/prayht/fresh-info-cadillac-escalade',
+ 'info_dict': {
+ 'id': 'bc01da03-6fe5-4284-8880-f291f4e368f5',
+ 'ext': 'mp4',
+ 'title': '【Fresh Info】Cadillac ESCALADE Sport Edition',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }
+ _GEO_COUNTRIES = ['JP']
+ _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
+
+ def _get_feed_query(self, uri):
+ return {
+ 'arcEp': 'mtvjapan.com',
+ 'mgid': uri,
Rapsys Git / youtubedl / blobdiff