diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 027fb06f9..6b7660ab1 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -51,7 +51,6 @@ from .cbsnews import CBSNewsIE from .ceskatelevize import CeskaTelevizeIE from .channel9 import Channel9IE from .chilloutzone import ChilloutzoneIE -from .cinemassacre import CinemassacreIE from .clipfish import ClipfishIE from .cliphunter import CliphunterIE from .clipsyndicate import ClipsyndicateIE @@ -336,6 +335,7 @@ from .savefrom import SaveFromIE from .sbs import SBSIE from .scivee import SciVeeIE from .screencast import ScreencastIE +from .screenwavemedia import ScreenwaveMediaIE from .servingsys import ServingSysIE from .sexu import SexuIE from .sexykarma import SexyKarmaIE diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/screenwavemedia.py similarity index 50% rename from youtube_dl/extractor/cinemassacre.py rename to youtube_dl/extractor/screenwavemedia.py index b7fa73c3b..cf9b8e0de 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/screenwavemedia.py @@ -6,18 +6,23 @@ import re from .common import InfoExtractor from ..utils import ( ExtractorError, + month_by_name, int_or_none, ) +class ScreenwaveMediaIE(InfoExtractor): + _VALID_URL = r'(?:http://)?(?' \ + r':(?Pplayer\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P.+))' \ + r'|(?P(?:www\.)?cinemassacre\.com/(?P[0-9]{4})/(?P[0-9]{2})/(?P[0-9]{2})/(?P[^?#/]+))' \ + r'|(?P(?:www\.)?teamfourstar\.com/video/(?P[a-z0-9\-]+)/?)' \ + r')' -class CinemassacreIE(InfoExtractor): - _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', + 'id': 'Cinemasssacre-19911', 'ext': 'mp4', 'upload_date': '20121110', 'title': '“Angry Video Game Nerd: The Movie” – Trailer', @@ -28,7 +33,7 @@ class CinemassacreIE(InfoExtractor): 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', 'md5': 'd72f10cd39eac4215048f62ab477a511', 'info_dict': { - 'id': '521be8ef82b16', + 'id': 'Cinemasssacre-521be8ef82b16', 'ext': 'mp4', 'upload_date': '20131002', 'title': 'The Mummy’s Hand (1940)', @@ -36,18 +41,16 @@ class CinemassacreIE(InfoExtractor): } ] - def _real_extract(self, url): + def _cinemassacre_get_info(self, url): mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('display_id') + display_id = mobj.group('cm_display_id') 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\?[^"]*\bid=(?P(?:Cinemassacre-)?(?P.+?)))"', webpage) + video_date = mobj.group('cm_date_Y') + mobj.group('cm_date_m') + mobj.group('cm_date_d') + mobj = re.search(r'src="(?Phttp://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', 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') - full_video_id = mobj.group('full_video_id') video_title = self._html_search_regex( r'(?P<title>.+?)\|', webpage, 'title') @@ -56,10 +59,56 @@ class CinemassacreIE(InfoExtractor): webpage, 'description', flags=re.DOTALL, fatal=False) video_thumbnail = self._og_search_thumbnail(webpage) - playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage') + return { + 'title': video_title, + 'description': video_description, + 'upload_date': video_date, + 'thumbnail': video_thumbnail, + '_embed_url': playerdata_url, + } + + def _teamfourstar_get_info(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('tfs_display_id') + webpage = self._download_webpage(url, display_id) + + mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', webpage) + if not mobj: + raise ExtractorError('Can\'t extract embed url and video id') + playerdata_url = mobj.group('embed_url') + + video_title = self._html_search_regex( + r'<div class="heroheadingtitle">(?P<title>.+?)</div>', webpage, 'title') + video_date = self._html_search_regex( + r'<div class="heroheadingdate">(?P<date>.+?)</div>', webpage, 'date') + mobj = re.match('(?P<month>[A-Z][a-z]+) (?P<day>\d+), (?P<year>\d+)', video_date) + video_date = '%04u%02u%02u' % (int(mobj.group('year')), month_by_name(mobj.group('month')), int(mobj.group('day'))) + video_description = self._html_search_regex( + r'<div class="postcontent">(?P<description>.+?)</div>', webpage, 'description', flags=re.DOTALL) + video_thumbnail = self._og_search_thumbnail(webpage) + return { + 'title': video_title, + 'description': video_description, + 'upload_date': video_date, + 'thumbnail': video_thumbnail, + '_embed_url': playerdata_url, + } + + def _screenwavemedia_get_info(self, url): + mobj = re.match(self._VALID_URL, url) + if not mobj: + raise ExtractorError('Can\'t extract embed url and video id') + video_id = mobj.group('video_id') + + playerdata = self._download_webpage(url, video_id, 'Downloading player webpage') + + vidtitle = self._search_regex( + r'\'vidtitle\'\s*:\s*"([^\']+)"', playerdata, 'vidtitle').replace('\\/', '/') vidurl = self._search_regex( r'\'vidurl\'\s*:\s*"([^\']+)"', playerdata, 'vidurl').replace('\\/', '/') + pageurl = self._search_regex( + r'\'pageurl\'\s*:\s*"([^\']+)"', playerdata, 'pageurl', fatal=False).replace('\\/', '/') videolist_url = None @@ -67,7 +116,7 @@ class CinemassacreIE(InfoExtractor): if mobj: videoserver = mobj.group('videoserver') mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata) - vidid = mobj.group('vidid') if mobj else full_video_id + vidid = mobj.group('vidid') if mobj else video_id videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid) else: mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata) @@ -110,9 +159,36 @@ class CinemassacreIE(InfoExtractor): return { 'id': video_id, - 'title': video_title, + 'title': vidtitle, 'formats': formats, - 'description': video_description, - 'upload_date': video_date, - 'thumbnail': video_thumbnail, + '_episode_page': pageurl, } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + + swm_info = None + site_info = None + + if mobj.group('generic'): + swm_info = self._screenwavemedia_get_info(url) + url = swm_info['_episode_page'] + mobj = re.match(self._VALID_URL, url) + + if mobj: + if mobj.group('cinemassacre'): + site_info = self._cinemassacre_get_info(url) + elif mobj.group('teamfourstar'): + site_info = self._teamfourstar_get_info(url) + + if not swm_info: + if site_info: + swm_info = self._screenwavemedia_get_info(site_info['_embed_url']) + + if not swm_info: + raise ExtractorError("Failed to extract metadata for this URL") + + if site_info: + swm_info.update(site_info) + + return swm_info