From 23b6e23002d8bd3af3b2ccb2e1b833c1dd1b3cbf Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 11 Dec 2017 21:36:12 +0100 Subject: [PATCH] [tvnow] fix extraction(closes #7831) --- youtube_dl/extractor/extractors.py | 8 +- youtube_dl/extractor/nowtv.py | 261 ----------------------------- youtube_dl/extractor/tvnow.py | 175 +++++++++++++++++++ 3 files changed, 179 insertions(+), 265 deletions(-) delete mode 100644 youtube_dl/extractor/nowtv.py create mode 100644 youtube_dl/extractor/tvnow.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 99887ee89..fb9f365f2 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -722,10 +722,6 @@ from .nowness import ( NownessPlaylistIE, NownessSeriesIE, ) -from .nowtv import ( - NowTVIE, - NowTVListIE, -) from .noz import NozIE from .npo import ( AndereTijdenIE, @@ -1105,6 +1101,10 @@ from .tvigle import TvigleIE from .tvland import TVLandIE from .tvn24 import TVN24IE from .tvnoe import TVNoeIE +from .tvnow import ( + TVNowIE, + TVNowListIE, +) from .tvp import ( TVPEmbedIE, TVPIE, diff --git a/youtube_dl/extractor/nowtv.py b/youtube_dl/extractor/nowtv.py deleted file mode 100644 index e43b37136..000000000 --- a/youtube_dl/extractor/nowtv.py +++ /dev/null @@ -1,261 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - ExtractorError, - determine_ext, - int_or_none, - parse_iso8601, - parse_duration, - remove_start, -) - - -class NowTVBaseIE(InfoExtractor): - _VIDEO_FIELDS = ( - 'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort', - 'broadcastStartDate', 'seoUrl', 'duration', 'files', - 'format.defaultImage169Format', 'format.defaultImage169Logo') - - def _extract_video(self, info, display_id=None): - video_id = compat_str(info['id']) - - files = info['files'] - if not files: - if info.get('geoblocked', False): - raise ExtractorError( - 'Video %s is not available from your location due to geo restriction' % video_id, - expected=True) - if not info.get('free', True): - raise ExtractorError( - 'Video %s is not available for free' % video_id, expected=True) - - formats = [] - for item in files['items']: - if determine_ext(item['path']) != 'f4v': - continue - app, play_path = remove_start(item['path'], '/').split('/', 1) - formats.append({ - 'url': 'rtmpe://fms.rtl.de', - 'app': app, - 'play_path': 'mp4:%s' % play_path, - 'ext': 'flv', - 'page_url': 'http://rtlnow.rtl.de', - 'player_url': 'http://cdn.static-fra.de/now/vodplayer.swf', - 'tbr': int_or_none(item.get('bitrate')), - }) - self._sort_formats(formats) - - title = info['title'] - description = info.get('articleLong') or info.get('articleShort') - timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ') - duration = parse_duration(info.get('duration')) - - f = info.get('format', {}) - thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo') - - return { - 'id': video_id, - 'display_id': display_id or info.get('seoUrl'), - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'duration': duration, - 'formats': formats, - } - - -class NowTVIE(NowTVBaseIE): - _WORKING = False - _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P[^/]+)/(?:(?:list/[^/]+|jahr/\d{4}/\d{1,2})/)?(?P[^/]+)/(?:player|preview)' - - _TESTS = [{ - # rtl - 'url': 'http://www.nowtv.de/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/player', - 'info_dict': { - 'id': '203519', - 'display_id': 'bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit', - 'ext': 'flv', - 'title': 'Inka Bause stellt die neuen Bauern vor', - 'description': 'md5:e234e1ed6d63cf06be5c070442612e7e', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432580700, - 'upload_date': '20150525', - 'duration': 2786, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # rtl2 - 'url': 'http://www.nowtv.de/rtl2/berlin-tag-nacht/berlin-tag-nacht-folge-934/player', - 'info_dict': { - 'id': '203481', - 'display_id': 'berlin-tag-nacht/berlin-tag-nacht-folge-934', - 'ext': 'flv', - 'title': 'Berlin - Tag & Nacht (Folge 934)', - 'description': 'md5:c85e88c2e36c552dfe63433bc9506dd0', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432666800, - 'upload_date': '20150526', - 'duration': 2641, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # rtlnitro - 'url': 'http://www.nowtv.de/rtlnitro/alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00/player', - 'info_dict': { - 'id': '165780', - 'display_id': 'alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00', - 'ext': 'flv', - 'title': 'Hals- und Beinbruch', - 'description': 'md5:b50d248efffe244e6f56737f0911ca57', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432415400, - 'upload_date': '20150523', - 'duration': 2742, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # superrtl - 'url': 'http://www.nowtv.de/superrtl/medicopter-117/angst/player', - 'info_dict': { - 'id': '99205', - 'display_id': 'medicopter-117/angst', - 'ext': 'flv', - 'title': 'Angst!', - 'description': 'md5:30cbc4c0b73ec98bcd73c9f2a8c17c4e', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1222632900, - 'upload_date': '20080928', - 'duration': 3025, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # ntv - 'url': 'http://www.nowtv.de/ntv/ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch/player', - 'info_dict': { - 'id': '203521', - 'display_id': 'ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch', - 'ext': 'flv', - 'title': 'Thema u.a.: Der erste Blick: Die Apple Watch', - 'description': 'md5:4312b6c9d839ffe7d8caf03865a531af', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432751700, - 'upload_date': '20150527', - 'duration': 1083, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # vox - 'url': 'http://www.nowtv.de/vox/der-hundeprofi/buero-fall-chihuahua-joel/player', - 'info_dict': { - 'id': '128953', - 'display_id': 'der-hundeprofi/buero-fall-chihuahua-joel', - 'ext': 'flv', - 'title': "Büro-Fall / Chihuahua 'Joel'", - 'description': 'md5:e62cb6bf7c3cc669179d4f1eb279ad8d', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432408200, - 'upload_date': '20150523', - 'duration': 3092, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - 'url': 'http://www.nowtv.de/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/preview', - 'only_matching': True, - }, { - 'url': 'http://www.nowtv.at/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/preview?return=/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit', - 'only_matching': True, - }, { - 'url': 'http://www.nowtv.de/rtl2/echtzeit/list/aktuell/schnelles-geld-am-ende-der-welt/player', - 'only_matching': True, - }, { - 'url': 'http://www.nowtv.de/rtl2/zuhause-im-glueck/jahr/2015/11/eine-erschuetternde-diagnose/player', - 'only_matching': True, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = '%s/%s' % (mobj.group('show_id'), mobj.group('id')) - - info = self._download_json( - 'https://api.nowtv.de/v3/movies/%s?fields=%s' - % (display_id, ','.join(self._VIDEO_FIELDS)), display_id) - - return self._extract_video(info, display_id) - - -class NowTVListIE(NowTVBaseIE): - _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P[^/]+)/list/(?P[^?/#&]+)$' - - _SHOW_FIELDS = ('title', ) - _SEASON_FIELDS = ('id', 'headline', 'seoheadline', ) - - _TESTS = [{ - 'url': 'http://www.nowtv.at/rtl/stern-tv/list/aktuell', - 'info_dict': { - 'id': '17006', - 'title': 'stern TV - Aktuell', - }, - 'playlist_count': 1, - }, { - 'url': 'http://www.nowtv.at/rtl/das-supertalent/list/free-staffel-8', - 'info_dict': { - 'id': '20716', - 'title': 'Das Supertalent - FREE Staffel 8', - }, - 'playlist_count': 14, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - show_id = mobj.group('show_id') - season_id = mobj.group('id') - - fields = [] - fields.extend(self._SHOW_FIELDS) - fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS) - fields.extend( - 'formatTabs.formatTabPages.container.movies.%s' % field - for field in self._VIDEO_FIELDS) - - list_info = self._download_json( - 'https://api.nowtv.de/v3/formats/seo?fields=%s&name=%s.php' - % (','.join(fields), show_id), - season_id) - - season = next( - season for season in list_info['formatTabs']['items'] - if season.get('seoheadline') == season_id) - - title = '%s - %s' % (list_info['title'], season['headline']) - - entries = [] - for container in season['formatTabPages']['items']: - for info in ((container.get('container') or {}).get('movies') or {}).get('items') or []: - entries.append(self._extract_video(info)) - - return self.playlist_result( - entries, compat_str(season.get('id') or season_id), title) diff --git a/youtube_dl/extractor/tvnow.py b/youtube_dl/extractor/tvnow.py new file mode 100644 index 000000000..e2169f2bc --- /dev/null +++ b/youtube_dl/extractor/tvnow.py @@ -0,0 +1,175 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + ExtractorError, + parse_iso8601, + parse_duration, + update_url_query, +) + + +class TVNowBaseIE(InfoExtractor): + _VIDEO_FIELDS = ( + 'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort', + 'broadcastStartDate', 'isDrm', 'duration', 'manifest.dashclear', + 'format.defaultImage169Format', 'format.defaultImage169Logo') + + def _call_api(self, path, video_id, query): + return self._download_json( + 'https://api.tvnow.de/v3/' + path, + video_id, query=query) + + def _extract_video(self, info, display_id): + video_id = compat_str(info['id']) + title = info['title'] + + mpd_url = info['manifest']['dashclear'] + if not mpd_url: + if info.get('isDrm'): + raise ExtractorError( + 'Video %s is DRM protected' % video_id, expected=True) + if info.get('geoblocked'): + raise ExtractorError( + 'Video %s is not available from your location due to geo restriction' % video_id, + expected=True) + if not info.get('free', True): + raise ExtractorError( + 'Video %s is not available for free' % video_id, expected=True) + + mpd_url = update_url_query(mpd_url, {'filter': ''}) + formats = self._extract_mpd_formats(mpd_url, video_id, mpd_id='dash', fatal=False) + formats.extend(self._extract_ism_formats( + mpd_url.replace('dash.', 'hss.').replace('/.mpd', '/Manifest'), + video_id, ism_id='mss', fatal=False)) + formats.extend(self._extract_m3u8_formats( + mpd_url.replace('dash.', 'hls.').replace('/.mpd', '/.m3u8'), + video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) + self._sort_formats(formats) + + description = info.get('articleLong') or info.get('articleShort') + timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ') + duration = parse_duration(info.get('duration')) + + f = info.get('format', {}) + thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo') + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'formats': formats, + } + + +class TVNowIE(TVNowBaseIE): + _VALID_URL = r'https?://(?:www\.)?tvnow\.(?:de|at|ch)/(?:rtl(?:2|plus)?|nitro|superrtl|ntv|vox)/(?P[^/]+)/(?:(?:list/[^/]+|jahr/\d{4}/\d{1,2})/)?(?P[^/]+)/(?:player|preview)' + + _TESTS = [{ + # rtl + 'url': 'https://www.tvnow.de/rtl/alarm-fuer-cobra-11/freier-fall/player?return=/rtl', + 'info_dict': { + 'id': '385314', + 'display_id': 'alarm-fuer-cobra-11/freier-fall', + 'ext': 'mp4', + 'title': 'Freier Fall', + 'description': 'md5:8c2d8f727261adf7e0dc18366124ca02', + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1512677700, + 'upload_date': '20171207', + 'duration': 2862.0, + }, + }, { + # rtl2 + 'url': 'https://www.tvnow.de/rtl2/armes-deutschland/episode-0008/player', + 'only_matching': 'True', + }, { + # rtlnitro + 'url': 'https://www.tvnow.de/nitro/alarm-fuer-cobra-11-die-autobahnpolizei/auf-eigene-faust-pilot/player', + 'only_matching': 'True', + }, { + # superrtl + 'url': 'https://www.tvnow.de/superrtl/die-lustigsten-schlamassel-der-welt/u-a-ketchup-effekt/player', + 'only_matching': 'True', + }, { + # ntv + 'url': 'https://www.tvnow.de/ntv/startup-news/goetter-in-weiss/player', + 'only_matching': 'True', + }, { + # vox + 'url': 'https://www.tvnow.de/vox/auto-mobil/neues-vom-automobilmarkt-2017-11-19-17-00-00/player', + 'only_matching': 'True', + }, { + # rtlplus + 'url': 'https://www.tvnow.de/rtlplus/op-ruft-dr-bruckner/die-vernaehte-frau/player', + 'only_matching': 'True', + }] + + def _real_extract(self, url): + display_id = '%s/%s' % re.match(self._VALID_URL, url).groups() + + info = self._call_api( + 'movies/' + display_id, display_id, query={ + 'fields': ','.join(self._VIDEO_FIELDS), + }) + + return self._extract_video(info, display_id) + + +class TVNowListIE(TVNowBaseIE): + _VALID_URL = r'(?Phttps?://(?:www\.)?tvnow\.(?:de|at|ch)/(?:rtl(?:2|plus)?|nitro|superrtl|ntv|vox)/(?P[^/]+)/)list/(?P[^?/#&]+)$' + + _SHOW_FIELDS = ('title', ) + _SEASON_FIELDS = ('id', 'headline', 'seoheadline', ) + _VIDEO_FIELDS = ('id', 'headline', 'seoUrl', ) + + _TESTS = [{ + 'url': 'https://www.tvnow.de/rtl/30-minuten-deutschland/list/aktuell', + 'info_dict': { + 'id': '28296', + 'title': '30 Minuten Deutschland - Aktuell', + }, + 'playlist_mincount': 1, + }] + + def _real_extract(self, url): + base_url, show_id, season_id = re.match(self._VALID_URL, url).groups() + + fields = [] + fields.extend(self._SHOW_FIELDS) + fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS) + fields.extend( + 'formatTabs.formatTabPages.container.movies.%s' % field + for field in self._VIDEO_FIELDS) + + list_info = self._call_api( + 'formats/seo', season_id, query={ + 'fields': ','.join(fields), + 'name': show_id + '.php' + }) + + season = next( + season for season in list_info['formatTabs']['items'] + if season.get('seoheadline') == season_id) + + title = '%s - %s' % (list_info['title'], season['headline']) + + entries = [] + for container in season['formatTabPages']['items']: + for info in ((container.get('container') or {}).get('movies') or {}).get('items') or []: + seo_url = info.get('seoUrl') + if not seo_url: + continue + entries.append(self.url_result( + base_url + seo_url + '/player', 'TVNow', info.get('id'))) + + return self.playlist_result( + entries, compat_str(season.get('id') or season_id), title)