X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/415fdb62500dca2e22067a05008dfbf87c75b662..d018d3313032e12968a6add6800e51d412e2f602:/youtube_dl/extractor/cinemassacre.py diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index 496271b..fd1770d 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -4,20 +4,19 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, - int_or_none, -) +from ..utils import ExtractorError +from .bliptv import BlipTVIE +from .screenwavemedia import ScreenwaveMediaIE class CinemassacreIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P[0-9]{4})/(?P[0-9]{2})/(?P[0-9]{2})/(?P[^?#/]+)' + _VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P[0-9]{4})/(?P[0-9]{2})/(?P[0-9]{2})/(?P[^?#/]+)' _TESTS = [ { 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', 'md5': 'fde81fbafaee331785f58cd6c0d46190', 'info_dict': { - 'id': '19911', + 'id': 'Cinemassacre-19911', 'ext': 'mp4', 'upload_date': '20121110', 'title': '“Angry Video Game Nerd: The Movie” – Trailer', @@ -28,73 +27,85 @@ class CinemassacreIE(InfoExtractor): 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', 'md5': 'd72f10cd39eac4215048f62ab477a511', 'info_dict': { - 'id': '521be8ef82b16', + 'id': 'Cinemassacre-521be8ef82b16', 'ext': 'mp4', 'upload_date': '20131002', 'title': 'The Mummy’s Hand (1940)', }, + }, + { + # blip.tv embedded video + 'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/', + 'md5': 'ca9b3c8dd5a66f9375daeb5135f5a3de', + 'info_dict': { + 'id': '4065369', + 'ext': 'flv', + 'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles', + 'upload_date': '20061207', + 'uploader': 'cinemassacre', + 'uploader_id': '250778', + 'timestamp': 1283233867, + 'description': 'md5:0a108c78d130676b207d0f6d029ecffd', + } + }, + { + # Youtube embedded video + 'url': 'http://cinemassacre.com/2006/09/01/mckids/', + 'md5': '6eb30961fa795fedc750eac4881ad2e1', + 'info_dict': { + 'id': 'FnxsNhuikpo', + 'ext': 'mp4', + 'upload_date': '20060901', + 'uploader': 'Cinemassacre Extras', + 'description': 'md5:de9b751efa9e45fbaafd9c8a1123ed53', + 'uploader_id': 'Cinemassacre', + 'title': 'AVGN: McKids', + } + }, + { + 'url': 'http://cinemassacre.com/2015/05/25/mario-kart-64-nintendo-64-james-mike-mondays/', + 'md5': '1376908e49572389e7b06251a53cdd08', + 'info_dict': { + 'id': 'Cinemassacre-555779690c440', + 'ext': 'mp4', + 'description': 'Let’s Play Mario Kart 64 !! Mario Kart 64 is a classic go-kart racing game released for the Nintendo 64 (N64). Today James & Mike do 4 player Battle Mode with Kyle and Bootsy!', + 'title': 'Mario Kart 64 (Nintendo 64) James & Mike Mondays', + 'upload_date': '20150525', + } } ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) display_id = mobj.group('display_id') + video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d') webpage = self._download_webpage(url, display_id) - video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d') - mobj = re.search(r'src="(?Phttp://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P.+?))"', webpage) - if not mobj: - raise ExtractorError('Can\'t extract embed url and video id') - playerdata_url = mobj.group('embed_url') - video_id = mobj.group('video_id') + + playerdata_url = self._search_regex( + [ + ScreenwaveMediaIE.EMBED_PATTERN, + r']+src="(?P(?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"', + ], + webpage, 'player data URL', default=None, group='url') + if not playerdata_url: + playerdata_url = BlipTVIE._extract_url(webpage) + if not playerdata_url: + raise ExtractorError('Unable to find player data') video_title = self._html_search_regex( r'(?P<title>.+?)\|', webpage, 'title') video_description = self._html_search_regex( r'<div class="entry-content">(?P<description>.+?)</div>', webpage, 'description', flags=re.DOTALL, fatal=False) - - playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage') - video_thumbnail = self._search_regex( - r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False) - sd_url = self._search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file') - videolist_url = self._search_regex(r'file: \'([^\']+\.smil)\'}', playerdata, 'videolist_url') - - videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML') - - formats = [] - baseurl = sd_url[:sd_url.rfind('/')+1] - for video in videolist.findall('.//video'): - src = video.get('src') - if not src: - continue - file_ = src.partition(':')[-1] - width = int_or_none(video.get('width')) - height = int_or_none(video.get('height')) - bitrate = int_or_none(video.get('system-bitrate')) - format = { - 'url': baseurl + file_, - 'format_id': src.rpartition('.')[0].rpartition('_')[-1], - } - if width or height: - format.update({ - 'tbr': bitrate // 1000 if bitrate else None, - 'width': width, - 'height': height, - }) - else: - format.update({ - 'abr': bitrate // 1000 if bitrate else None, - 'vcodec': 'none', - }) - formats.append(format) - self._sort_formats(formats) + video_thumbnail = self._og_search_thumbnail(webpage) return { - 'id': video_id, + '_type': 'url_transparent', + 'display_id': display_id, 'title': video_title, - 'formats': formats, 'description': video_description, 'upload_date': video_date, 'thumbnail': video_thumbnail, + 'url': playerdata_url, }