X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcinemassacre.py;h=806e378b1b6da0eebe01bdd3992d53814090bf59;hb=d9116714f253b2c0d75528062ee568cd844204e7;hp=16eaff3a159c6187395a4b72fb1c3eabe262eb11;hpb=400afddaf49353c9b4c31d17d5efe4045e500fec;p=youtube-dl diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index 16eaff3a1..806e378b1 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -1,100 +1,102 @@ # encoding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor from ..utils import ( ExtractorError, + int_or_none, ) + class CinemassacreIE(InfoExtractor): - """Information Extractor for Cinemassacre""" - _VALID_URL = r'(?:http://)?(?:www\.)?(?Pcinemassacre\.com/(?P[0-9]{4})/(?P[0-9]{2})/(?P[0-9]{2})/.+?)(?:[/?].*)?' - _TESTS = [{ - u'url': u'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', - u'file': u'19911.mp4', - u'info_dict': { - u'upload_date': u'20121110', - u'title': u'“Angry Video Game Nerd: The Movie” – Trailer', - #u'description': u'“Angry Video Game Nerd: The Movie” is...', # Description is too long - }, - u'params': { - u'skip_download': True, + _VALID_URL = r'http://(?: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', + 'ext': 'mp4', + 'upload_date': '20121110', + 'title': '“Angry Video Game Nerd: The Movie” – Trailer', + 'description': 'md5:fb87405fcb42a331742a0dce2708560b', + }, }, - }] + { + 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', + 'md5': 'd72f10cd39eac4215048f62ab477a511', + 'info_dict': { + 'id': '521be8ef82b16', + 'ext': 'mp4', + 'upload_date': '20131002', + 'title': 'The Mummy’s Hand (1940)', + }, + } + ] - def _real_extract(self,url): + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') - webpage_url = u'http://' + mobj.group('url') - webpage = self._download_webpage(webpage_url, None) # Don't know video id yet + webpage = self._download_webpage(url, display_id) video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d') - video_id = self._html_search_regex(r'src="http://player\.screenwavemedia\.com/play/embed\.php\?id=(?P.+?)"', - webpage, u'video_id') - video_title = self._html_search_regex(r'

(?P.+?)</h1>[^<]*</div>', - webpage, u'title') - video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>', - webpage, u'description', flags=re.DOTALL, fatal=False) - - playerdata_url = u'http://player.screenwavemedia.com/play/player.php?id=' + video_id - playerdata = self._download_webpage(playerdata_url, video_id) - base_url = self._html_search_regex(r'\'streamer\': \'(?P<base_url>rtmp://[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3})/vod\'', - playerdata, u'base_url') - base_url += '/Cinemassacre/' - # The file names in playerdata are wrong for some videos??? - sd_file = 'Cinemassacre-%s_high.mp4' % video_id - hd_file = 'Cinemassacre-%s.mp4' % video_id - video_thumbnail = 'http://image.screenwavemedia.com/Cinemassacre/Cinemassacre-%s_thumb_640x360.jpg' % video_id - - formats = [{ - 'id': video_id, - 'url': base_url + hd_file, - 'format': 'hd', - 'ext': 'mp4', - 'title': video_title, - 'description': video_description, - 'upload_date': video_date, - 'thumbnail': video_thumbnail, - }, - { - 'id': video_id, - 'url': base_url + sd_file, - 'ext': 'mp4', - 'format': 'sd', - 'title': video_title, - 'description': video_description, - 'upload_date': video_date, - 'thumbnail': video_thumbnail, - }] - - if self._downloader.params.get('listformats', None): - self._print_formats(formats) - return + mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?:Cinemassacre-)?(?P<video_id>.+?))"', 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') + + video_title = self._html_search_regex( + r'<title>(?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) + video_thumbnail = self._og_search_thumbnail(webpage) - req_format = self._downloader.params.get('format', 'best') - self.to_screen(u'Format: %s' % req_format) + playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage') - if req_format is None or req_format == 'best': - return [formats[0]] - elif req_format == 'worst': - return [formats[-1]] - elif req_format in ('-1', 'all'): - return formats - else: - format = self._specific( req_format, formats ) - if format is None: - raise ExtractorError(u'Requested format not available') - return [format] + vidurl = self._search_regex( + r'\'vidurl\'\s*:\s*"([^\']+)"', playerdata, 'vidurl').replace('\\/', '/') - def _print_formats(self, formats): - """Print all available formats""" - print(u'Available formats:') - print(u'ext\t\tformat') - print(u'---------------------------------') - for format in formats: - print(u'%s\t\t%s' % (format['ext'], format['format'])) + videolist_url = self._search_regex( + r"file\s*:\s*'(http.+?/jwplayer\.smil)'", playerdata, 'jwplayer.smil') + videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML') - def _specific(self, req_format, formats): - for x in formats: - if x["format"] == req_format: - return x - return None + formats = [] + baseurl = vidurl[:vidurl.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) + + return { + 'id': video_id, + 'title': video_title, + 'formats': formats, + 'description': video_description, + 'upload_date': video_date, + 'thumbnail': video_thumbnail, + }