diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 2483670398..31531855e8 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -622,23 +622,17 @@ class YoutubeDL(object): ie_result['url'], ie_key=ie_result.get('ie_key'), extra_info=extra_info, download=False, process=False) - def make_result(embedded_info): - new_result = ie_result.copy() - for f in ('_type', 'url', 'ext', 'player_url', 'formats', - 'entries', 'ie_key', 'duration', - 'subtitles', 'annotations', 'format', - 'thumbnail', 'thumbnails'): - if f in new_result: - del new_result[f] - if f in embedded_info: - new_result[f] = embedded_info[f] - return new_result - new_result = make_result(info) + new_result = ie_result.copy() + for f in ('_type', 'id', 'url', 'ext', 'player_url', 'formats', + 'entries', 'ie_key', 'duration', + 'subtitles', 'annotations', 'format', + 'thumbnail', 'thumbnails'): + if f in new_result: + del new_result[f] + if f in info: + new_result[f] = info[f] assert new_result.get('_type') != 'url_transparent' - if new_result.get('_type') == 'compat_list': - new_result['entries'] = [ - make_result(e) for e in new_result['entries']] return self.process_ie_result( new_result, download=download, extra_info=extra_info) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 6b7660ab15..982a134bf5 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -335,7 +335,7 @@ from .savefrom import SaveFromIE from .sbs import SBSIE from .scivee import SciVeeIE from .screencast import ScreencastIE -from .screenwavemedia import ScreenwaveMediaIE +from .screenwavemedia import CinemassacreIE, ScreenwaveMediaIE, TeamFourIE from .servingsys import ServingSysIE from .sexu import SexuIE from .sexykarma import SexyKarmaIE diff --git a/youtube_dl/extractor/screenwavemedia.py b/youtube_dl/extractor/screenwavemedia.py index cf9b8e0de9..1081904712 100644 --- a/youtube_dl/extractor/screenwavemedia.py +++ b/youtube_dl/extractor/screenwavemedia.py @@ -6,109 +6,28 @@ import re from .common import InfoExtractor from ..utils import ( ExtractorError, - month_by_name, int_or_none, + month_by_name, + unified_strdate, ) + 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')' + _VALID_URL = r'http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P.+)' - _TESTS = [ - { - 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', - 'md5': 'fde81fbafaee331785f58cd6c0d46190', - 'info_dict': { - 'id': 'Cinemasssacre-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': 'Cinemasssacre-521be8ef82b16', - 'ext': 'mp4', - 'upload_date': '20131002', - 'title': 'The Mummy’s Hand (1940)', - }, - } - ] - - def _cinemassacre_get_info(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('cm_display_id') - - webpage = self._download_webpage(url, display_id) - 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_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) - 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 _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') + _TESTS = [{ + 'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911', + 'only_matching': True, + }] + def _real_extract(self, url): + video_id = self._match_id(url) playerdata = self._download_webpage(url, video_id, 'Downloading player webpage') vidtitle = self._search_regex( - r'\'vidtitle\'\s*:\s*"([^\']+)"', playerdata, 'vidtitle').replace('\\/', '/') + 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('\\/', '/') + r'\'vidurl\'\s*:\s*"([^"]+)"', playerdata, 'vidurl').replace('\\/', '/') videolist_url = None @@ -134,61 +53,128 @@ class ScreenwaveMediaIE(InfoExtractor): 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')) + bitrate = int_or_none(video.get('system-bitrate'), scale=1000) format = { 'url': baseurl + file_, 'format_id': src.rpartition('.')[0].rpartition('_')[-1], } if width or height: format.update({ - 'tbr': bitrate // 1000 if bitrate else None, + 'tbr': bitrate, 'width': width, 'height': height, }) else: format.update({ - 'abr': bitrate // 1000 if bitrate else None, + 'abr': bitrate, 'vcodec': 'none', }) formats.append(format) - self._sort_formats(formats) else: formats = [{ 'url': vidurl, }] + self._sort_formats(formats) return { 'id': video_id, 'title': vidtitle, 'formats': formats, - '_episode_page': pageurl, } + +class CinemassacreIE(InfoExtractor): + _VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P<date_y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)' + _TESTS = [ + { + 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', + 'md5': 'fde81fbafaee331785f58cd6c0d46190', + 'info_dict': { + 'id': 'Cinemassacre-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': 'Cinemassacre-521be8ef82b16', + 'ext': 'mp4', + 'upload_date': '20131002', + 'title': 'The Mummy’s Hand (1940)', + }, + } + ] + 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') - swm_info = None - site_info = None + webpage = self._download_webpage(url, display_id) - if mobj.group('generic'): - swm_info = self._screenwavemedia_get_info(url) - url = swm_info['_episode_page'] - mobj = re.match(self._VALID_URL, url) + playerdata_url = self._search_regex( + r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', + webpage, 'player data URL') + 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) - if mobj: - if mobj.group('cinemassacre'): - site_info = self._cinemassacre_get_info(url) - elif mobj.group('teamfourstar'): - site_info = self._teamfourstar_get_info(url) + return { + '_type': 'url_transparent', + 'display_id': display_id, + 'title': video_title, + 'description': video_description, + 'upload_date': video_date, + 'thumbnail': video_thumbnail, + 'url': playerdata_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") +class TeamFourIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?' + _TEST = { + 'url': 'http://teamfourstar.com/video/a-moment-with-tfs-episode-4/', + 'info_dict': { + 'id': 'TeamFourStar-5292a02f20bfa', + 'ext': 'mp4', + 'upload_date': '20130401', + 'description': 'Check out this and more on our website: http://teamfourstar.com\nTFS Store: http://sharkrobot.com/team-four-star\nFollow on Twitter: http://twitter.com/teamfourstar\nLike on FB: http://facebook.com/teamfourstar', + 'title': 'A Moment With TFS Episode 4', + } + } - if site_info: - swm_info.update(site_info) + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) - return swm_info + playerdata_url = self._search_regex( + r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', + webpage, 'player data URL') + + video_title = self._html_search_regex( + r'<div class="heroheadingtitle">(?P<title>.+?)</div>', + webpage, 'title') + video_date = unified_strdate(self._html_search_regex( + r'<div class="heroheadingdate">(?P<date>.+?)</div>', + webpage, 'date', fatal=False)) + video_description = self._html_search_regex( + r'(?s)<div class="postcontent">(?P<description>.+?)</div>', + webpage, 'description', fatal=False) + video_thumbnail = self._og_search_thumbnail(webpage) + + return { + '_type': 'url_transparent', + 'display_id': display_id, + 'title': video_title, + 'description': video_description, + 'upload_date': video_date, + 'thumbnail': video_thumbnail, + 'url': playerdata_url, + }