import binascii import hashlib import re from .common import InfoExtractor from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7 from ..compat import compat_urllib_parse_unquote from ..utils import ( ExtractorError, int_or_none, float_or_none, mimetype2ext, str_or_none, try_get, unified_timestamp, update_url_query, url_or_none, ) class DRTVIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?: (?:www\.)?dr\.dk/(?:tv/se|nyheder|(?:radio|lyd)(?:/ondemand)?)/(?:[^/]+/)*| (?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/(?:se|episode|program)/ ) (?P[\da-z_-]+) ''' _GEO_BYPASS = False _GEO_COUNTRIES = ['DK'] IE_NAME = 'drtv' _TESTS = [{ 'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10', 'md5': '25e659cccc9a2ed956110a299fdf5983', 'info_dict': { 'id': 'klassen-darlig-taber-10', 'ext': 'mp4', 'title': 'Klassen - Dårlig taber (10)', 'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa', 'timestamp': 1539085800, 'upload_date': '20181009', 'duration': 606.84, 'series': 'Klassen', 'season': 'Klassen I', 'season_number': 1, 'season_id': 'urn:dr:mu:bundle:57d7e8216187a4031cfd6f6b', 'episode': 'Episode 10', 'episode_number': 10, 'release_year': 2016, }, 'expected_warnings': ['Unable to download f4m manifest'], 'skip': 'this video has been removed', }, { # embed 'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang', 'info_dict': { 'id': 'urn:dr:mu:programcard:57c926176187a50a9c6e83c6', 'ext': 'mp4', 'title': 'christiania pusher street ryddes drdkrjpo', 'description': 'md5:2a71898b15057e9b97334f61d04e6eb5', 'timestamp': 1472800279, 'upload_date': '20160902', 'duration': 131.4, }, 'params': { 'skip_download': True, }, 'expected_warnings': ['Unable to download f4m manifest'], }, { # with SignLanguage formats 'url': 'https://www.dr.dk/tv/se/historien-om-danmark/-/historien-om-danmark-stenalder', 'info_dict': { 'id': '00831690010', 'ext': 'mp4', 'title': 'Historien om Danmark: Stenalder', 'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a', 'timestamp': 1546628400, 'upload_date': '20190104', 'duration': 3504.618, 'formats': 'mincount:20', 'release_year': 2017, 'season_id': 'urn:dr:mu:bundle:5afc03ad6187a4065ca5fd35', 'season_number': 1, 'season': 'Historien om Danmark', 'series': 'Historien om Danmark', }, 'params': { 'skip_download': True, }, }, { 'url': 'https://www.dr.dk/lyd/p4kbh/regionale-nyheder-kh4/p4-nyheder-2019-06-26-17-30-9', 'only_matching': True, }, { 'url': 'https://www.dr.dk/drtv/se/bonderoeven_71769', 'info_dict': { 'id': '00951930010', 'ext': 'mp4', 'title': 'Bonderøven 2019 (1:8)', 'description': 'md5:b6dcfe9b6f0bea6703e9a0092739a5bd', 'timestamp': 1603188600, 'upload_date': '20201020', 'duration': 2576.6, 'season': 'Bonderøven 2019', 'season_id': 'urn:dr:mu:bundle:5c201667a11fa01ca4528ce5', 'release_year': 2019, 'season_number': 2019, 'series': 'Frank & Kastaniegaarden' }, 'params': { 'skip_download': True, }, }, { 'url': 'https://www.dr.dk/drtv/episode/bonderoeven_71769', 'only_matching': True, }, { 'url': 'https://dr-massive.com/drtv/se/bonderoeven_71769', 'only_matching': True, }, { 'url': 'https://www.dr.dk/drtv/program/jagten_220924', 'only_matching': True, }, { 'url': 'https://www.dr.dk/lyd/p4aarhus/regionale-nyheder-ar4/regionale-nyheder-2022-05-05-12-30-3', 'info_dict': { 'id': 'urn:dr:mu:programcard:6265cb2571401424d0360113', 'title': "Regionale nyheder", 'ext': 'mp4', 'duration': 120.043, 'series': 'P4 Østjylland regionale nyheder', 'timestamp': 1651746600, 'season': 'Regionale nyheder', 'release_year': 0, 'season_id': 'urn:dr:mu:bundle:61c26889539f0201586b73c5', 'description': '', 'upload_date': '20220505', }, 'params': { 'skip_download': True, }, }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) if '>Programmet er ikke længere tilgængeligt' in webpage: raise ExtractorError( 'Video %s is not available' % video_id, expected=True) video_id = self._search_regex( (r'data-(?:material-identifier|episode-slug)="([^"]+)"', r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'), webpage, 'video id', default=None) if not video_id: video_id = self._search_regex( r'(urn(?:%3A|:)dr(?:%3A|:)mu(?:%3A|:)programcard(?:%3A|:)[\da-f]+)', webpage, 'urn', default=None) if video_id: video_id = compat_urllib_parse_unquote(video_id) _PROGRAMCARD_BASE = 'https://www.dr.dk/mu-online/api/1.4/programcard' query = {'expanded': 'true'} if video_id: programcard_url = '%s/%s' % (_PROGRAMCARD_BASE, video_id) else: programcard_url = _PROGRAMCARD_BASE page = self._parse_json( self._search_regex( r'data\s*=\s*({.+?})\s*(?:;|[\da-z-]+)' _GEO_COUNTRIES = ['DK'] _TEST = { 'url': 'https://www.dr.dk/tv/live/dr1', 'info_dict': { 'id': 'dr1', 'ext': 'mp4', 'title': 're:^DR1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', }, 'params': { # m3u8 download 'skip_download': True, }, } def _real_extract(self, url): channel_id = self._match_id(url) channel_data = self._download_json( 'https://www.dr.dk/mu-online/api/1.0/channel/' + channel_id, channel_id) title = channel_data['Title'] formats = [] for streaming_server in channel_data.get('StreamingServers', []): server = streaming_server.get('Server') if not server: continue link_type = streaming_server.get('LinkType') for quality in streaming_server.get('Qualities', []): for stream in quality.get('Streams', []): stream_path = stream.get('Stream') if not stream_path: continue stream_url = update_url_query( '%s/%s' % (server, stream_path), {'b': ''}) if link_type == 'HLS': formats.extend(self._extract_m3u8_formats( stream_url, channel_id, 'mp4', m3u8_id=link_type, fatal=False, live=True)) elif link_type == 'HDS': formats.extend(self._extract_f4m_formats(update_url_query( '%s/%s' % (server, stream_path), {'hdcore': '3.7.0'}), channel_id, f4m_id=link_type, fatal=False)) self._sort_formats(formats) return { 'id': channel_id, 'title': title, 'thumbnail': channel_data.get('PrimaryImageUri'), 'formats': formats, 'is_live': True, }