| | 1 | # coding: utf-8 |
| | 2 | from __future__ import unicode_literals |
| | 3 | |
| | 4 | import binascii |
| | 5 | import hashlib |
| | 6 | import re |
| | 7 | |
| | 8 | |
| | 9 | from .common import InfoExtractor |
| | 10 | from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7 |
| | 11 | from ..compat import compat_urllib_parse_unquote |
| | 12 | from ..utils import ( |
| | 13 | ExtractorError, |
| | 14 | int_or_none, |
| | 15 | float_or_none, |
| | 16 | mimetype2ext, |
| | 17 | str_or_none, |
| | 18 | try_get, |
| | 19 | unified_timestamp, |
| | 20 | update_url_query, |
| | 21 | url_or_none, |
| | 22 | ) |
| | 23 | |
| | 24 | |
| | 25 | class DRTVIE(InfoExtractor): |
| | 26 | _VALID_URL = r'''(?x) |
| | 27 | https?:// |
| | 28 | (?: |
| | 29 | (?:www\.)?dr\.dk/(?:tv/se|nyheder|radio(?:/ondemand)?)/(?:[^/]+/)*| |
| | 30 | (?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/(?:se|episode|program)/ |
| | 31 | ) |
| | 32 | (?P<id>[\da-z_-]+) |
| | 33 | ''' |
| | 34 | _GEO_BYPASS = False |
| | 35 | _GEO_COUNTRIES = ['DK'] |
| | 36 | IE_NAME = 'drtv' |
| | 37 | _TESTS = [{ |
| | 38 | 'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10', |
| | 39 | 'md5': '25e659cccc9a2ed956110a299fdf5983', |
| | 40 | 'info_dict': { |
| | 41 | 'id': 'klassen-darlig-taber-10', |
| | 42 | 'ext': 'mp4', |
| | 43 | 'title': 'Klassen - Dårlig taber (10)', |
| | 44 | 'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa', |
| | 45 | 'timestamp': 1539085800, |
| | 46 | 'upload_date': '20181009', |
| | 47 | 'duration': 606.84, |
| | 48 | 'series': 'Klassen', |
| | 49 | 'season': 'Klassen I', |
| | 50 | 'season_number': 1, |
| | 51 | 'season_id': 'urn:dr:mu:bundle:57d7e8216187a4031cfd6f6b', |
| | 52 | 'episode': 'Episode 10', |
| | 53 | 'episode_number': 10, |
| | 54 | 'release_year': 2016, |
| | 55 | }, |
| | 56 | 'expected_warnings': ['Unable to download f4m manifest'], |
| | 57 | }, { |
| | 58 | # embed |
| | 59 | 'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang', |
| | 60 | 'info_dict': { |
| | 61 | 'id': 'urn:dr:mu:programcard:57c926176187a50a9c6e83c6', |
| | 62 | 'ext': 'mp4', |
| | 63 | 'title': 'christiania pusher street ryddes drdkrjpo', |
| | 64 | 'description': 'md5:2a71898b15057e9b97334f61d04e6eb5', |
| | 65 | 'timestamp': 1472800279, |
| | 66 | 'upload_date': '20160902', |
| | 67 | 'duration': 131.4, |
| | 68 | }, |
| | 69 | 'params': { |
| | 70 | 'skip_download': True, |
| | 71 | }, |
| | 72 | 'expected_warnings': ['Unable to download f4m manifest'], |
| | 73 | }, { |
| | 74 | # with SignLanguage formats |
| | 75 | 'url': 'https://www.dr.dk/tv/se/historien-om-danmark/-/historien-om-danmark-stenalder', |
| | 76 | 'info_dict': { |
| | 77 | 'id': 'historien-om-danmark-stenalder', |
| | 78 | 'ext': 'mp4', |
| | 79 | 'title': 'Historien om Danmark: Stenalder', |
| | 80 | 'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a', |
| | 81 | 'timestamp': 1546628400, |
| | 82 | 'upload_date': '20190104', |
| | 83 | 'duration': 3502.56, |
| | 84 | 'formats': 'mincount:20', |
| | 85 | }, |
| | 86 | 'params': { |
| | 87 | 'skip_download': True, |
| | 88 | }, |
| | 89 | }, { |
| | 90 | 'url': 'https://www.dr.dk/radio/p4kbh/regionale-nyheder-kh4/p4-nyheder-2019-06-26-17-30-9', |
| | 91 | 'only_matching': True, |
| | 92 | }, { |
| | 93 | 'url': 'https://www.dr.dk/drtv/se/bonderoeven_71769', |
| | 94 | 'info_dict': { |
| | 95 | 'id': '00951930010', |
| | 96 | 'ext': 'mp4', |
| | 97 | 'title': 'Bonderøven (1:8)', |
| | 98 | 'description': 'md5:3cf18fc0d3b205745d4505f896af8121', |
| | 99 | 'timestamp': 1546542000, |
| | 100 | 'upload_date': '20190103', |
| | 101 | 'duration': 2576.6, |
| | 102 | }, |
| | 103 | 'params': { |
| | 104 | 'skip_download': True, |
| | 105 | }, |
| | 106 | }, { |
| | 107 | 'url': 'https://www.dr.dk/drtv/episode/bonderoeven_71769', |
| | 108 | 'only_matching': True, |
| | 109 | }, { |
| | 110 | 'url': 'https://dr-massive.com/drtv/se/bonderoeven_71769', |
| | 111 | 'only_matching': True, |
| | 112 | }, { |
| | 113 | 'url': 'https://www.dr.dk/drtv/program/jagten_220924', |
| | 114 | 'only_matching': True, |
| | 115 | }] |
| | 116 | |
| | 117 | def _real_extract(self, url): |
| | 118 | video_id = self._match_id(url) |
| | 119 | |
| | 120 | webpage = self._download_webpage(url, video_id) |
| | 121 | |
| | 122 | if '>Programmet er ikke længere tilgængeligt' in webpage: |
| | 123 | raise ExtractorError( |
| | 124 | 'Video %s is not available' % video_id, expected=True) |
| | 125 | |
| | 126 | video_id = self._search_regex( |
| | 127 | (r'data-(?:material-identifier|episode-slug)="([^"]+)"', |
| | 128 | r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'), |
| | 129 | webpage, 'video id', default=None) |
| | 130 | |
| | 131 | if not video_id: |
| | 132 | video_id = self._search_regex( |
| | 133 | r'(urn(?:%3A|:)dr(?:%3A|:)mu(?:%3A|:)programcard(?:%3A|:)[\da-f]+)', |
| | 134 | webpage, 'urn', default=None) |
| | 135 | if video_id: |
| | 136 | video_id = compat_urllib_parse_unquote(video_id) |
| | 137 | |
| | 138 | _PROGRAMCARD_BASE = 'https://www.dr.dk/mu-online/api/1.4/programcard' |
| | 139 | query = {'expanded': 'true'} |
| | 140 | |
| | 141 | if video_id: |
| | 142 | programcard_url = '%s/%s' % (_PROGRAMCARD_BASE, video_id) |
| | 143 | else: |
| | 144 | programcard_url = _PROGRAMCARD_BASE |
| | 145 | page = self._parse_json( |
| | 146 | self._search_regex( |
| | 147 | r'data\s*=\s*({.+?})\s*(?:;|</script)', webpage, |
| | 148 | 'data'), '1')['cache']['page'] |
| | 149 | page = page[list(page.keys())[0]] |
| | 150 | item = try_get( |
| | 151 | page, (lambda x: x['item'], lambda x: x['entries'][0]['item']), |
| | 152 | dict) |
| | 153 | video_id = item['customId'].split(':')[-1] |
| | 154 | query['productionnumber'] = video_id |
| | 155 | |
| | 156 | data = self._download_json( |
| | 157 | programcard_url, video_id, 'Downloading video JSON', query=query) |
| | 158 | |
| | 159 | title = str_or_none(data.get('Title')) or re.sub( |
| | 160 | r'\s*\|\s*(?:TV\s*\|\s*DR|DRTV)$', '', |
| | 161 | self._og_search_title(webpage)) |
| | 162 | description = self._og_search_description( |
| | 163 | webpage, default=None) or data.get('Description') |
| | 164 | |
| | 165 | timestamp = unified_timestamp( |
| | 166 | data.get('PrimaryBroadcastStartTime') or data.get('SortDateTime')) |
| | 167 | |
| | 168 | thumbnail = None |
| | 169 | duration = None |
| | 170 | |
| | 171 | restricted_to_denmark = False |
| | 172 | |
| | 173 | formats = [] |
| | 174 | subtitles = {} |
| | 175 | |
| | 176 | assets = [] |
| | 177 | primary_asset = data.get('PrimaryAsset') |
| | 178 | if isinstance(primary_asset, dict): |
| | 179 | assets.append(primary_asset) |
| | 180 | secondary_assets = data.get('SecondaryAssets') |
| | 181 | if isinstance(secondary_assets, list): |
| | 182 | for secondary_asset in secondary_assets: |
| | 183 | if isinstance(secondary_asset, dict): |
| | 184 | assets.append(secondary_asset) |
| | 185 | |
| | 186 | def hex_to_bytes(hex): |
| | 187 | return binascii.a2b_hex(hex.encode('ascii')) |
| | 188 | |
| | 189 | def decrypt_uri(e): |
| | 190 | n = int(e[2:10], 16) |
| | 191 | a = e[10 + n:] |
| | 192 | data = hex_to_bytes(e[10:10 + n]) |
| | 193 | key = hashlib.sha256(('%s:sRBzYNXBzkKgnjj8pGtkACch' % a).encode('utf-8')).digest() |
| | 194 | iv = hex_to_bytes(a) |
| | 195 | decrypted = unpad_pkcs7(aes_cbc_decrypt_bytes(data, key, iv)) |
| | 196 | return decrypted.decode('utf-8').split('?')[0] |
| | 197 | |
| | 198 | for asset in assets: |
| | 199 | kind = asset.get('Kind') |
| | 200 | if kind == 'Image': |
| | 201 | thumbnail = url_or_none(asset.get('Uri')) |
| | 202 | elif kind in ('VideoResource', 'AudioResource'): |
| | 203 | duration = float_or_none(asset.get('DurationInMilliseconds'), 1000) |
| | 204 | restricted_to_denmark = asset.get('RestrictedToDenmark') |
| | 205 | asset_target = asset.get('Target') |
| | 206 | for link in asset.get('Links', []): |
| | 207 | uri = link.get('Uri') |
| | 208 | if not uri: |
| | 209 | encrypted_uri = link.get('EncryptedUri') |
| | 210 | if not encrypted_uri: |
| | 211 | continue |
| | 212 | try: |
| | 213 | uri = decrypt_uri(encrypted_uri) |
| | 214 | except Exception: |
| | 215 | self.report_warning( |
| | 216 | 'Unable to decrypt EncryptedUri', video_id) |
| | 217 | continue |
| | 218 | uri = url_or_none(uri) |
| | 219 | if not uri: |
| | 220 | continue |
| | 221 | target = link.get('Target') |
| | 222 | format_id = target or '' |
| | 223 | if asset_target in ('SpokenSubtitles', 'SignLanguage', 'VisuallyInterpreted'): |
| | 224 | preference = -1 |
| | 225 | format_id += '-%s' % asset_target |
| | 226 | elif asset_target == 'Default': |
| | 227 | preference = 1 |
| | 228 | else: |
| | 229 | preference = None |
| | 230 | if target == 'HDS': |
| | 231 | f4m_formats = self._extract_f4m_formats( |
| | 232 | uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43', |
| | 233 | video_id, preference, f4m_id=format_id, fatal=False) |
| | 234 | if kind == 'AudioResource': |
| | 235 | for f in f4m_formats: |
| | 236 | f['vcodec'] = 'none' |
| | 237 | formats.extend(f4m_formats) |
| | 238 | elif target == 'HLS': |
| | 239 | formats.extend(self._extract_m3u8_formats( |
| | 240 | uri, video_id, 'mp4', entry_protocol='m3u8_native', |
| | 241 | quality=preference, m3u8_id=format_id, |
| | 242 | fatal=False)) |
| | 243 | else: |
| | 244 | bitrate = link.get('Bitrate') |
| | 245 | if bitrate: |
| | 246 | format_id += '-%s' % bitrate |
| | 247 | formats.append({ |
| | 248 | 'url': uri, |
| | 249 | 'format_id': format_id, |
| | 250 | 'tbr': int_or_none(bitrate), |
| | 251 | 'ext': link.get('FileFormat'), |
| | 252 | 'vcodec': 'none' if kind == 'AudioResource' else None, |
| | 253 | 'quality': preference, |
| | 254 | }) |
| | 255 | subtitles_list = asset.get('SubtitlesList') or asset.get('Subtitleslist') |
| | 256 | if isinstance(subtitles_list, list): |
| | 257 | LANGS = { |
| | 258 | 'Danish': 'da', |
| | 259 | } |
| | 260 | for subs in subtitles_list: |
| | 261 | if not isinstance(subs, dict): |
| | 262 | continue |
| | 263 | sub_uri = url_or_none(subs.get('Uri')) |
| | 264 | if not sub_uri: |
| | 265 | continue |
| | 266 | lang = subs.get('Language') or 'da' |
| | 267 | subtitles.setdefault(LANGS.get(lang, lang), []).append({ |
| | 268 | 'url': sub_uri, |
| | 269 | 'ext': mimetype2ext(subs.get('MimeType')) or 'vtt' |
| | 270 | }) |
| | 271 | |
| | 272 | if not formats and restricted_to_denmark: |
| | 273 | self.raise_geo_restricted( |
| | 274 | 'Unfortunately, DR is not allowed to show this program outside Denmark.', |
| | 275 | countries=self._GEO_COUNTRIES) |
| | 276 | |
| | 277 | self._sort_formats(formats) |
| | 278 | |
| | 279 | return { |
| | 280 | 'id': video_id, |
| | 281 | 'title': title, |
| | 282 | 'description': description, |
| | 283 | 'thumbnail': thumbnail, |
| | 284 | 'timestamp': timestamp, |
| | 285 | 'duration': duration, |
| | 286 | 'formats': formats, |
| | 287 | 'subtitles': subtitles, |
| | 288 | 'series': str_or_none(data.get('SeriesTitle')), |
| | 289 | 'season': str_or_none(data.get('SeasonTitle')), |
| | 290 | 'season_number': int_or_none(data.get('SeasonNumber')), |
| | 291 | 'season_id': str_or_none(data.get('SeasonUrn')), |
| | 292 | 'episode': str_or_none(data.get('EpisodeTitle')), |
| | 293 | 'episode_number': int_or_none(data.get('EpisodeNumber')), |
| | 294 | 'release_year': int_or_none(data.get('ProductionYear')), |
| | 295 | } |
| | 296 | |
| | 297 | |
| | 298 | class DRTVLiveIE(InfoExtractor): |
| | 299 | IE_NAME = 'drtv:live' |
| | 300 | _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv|TV)/live/(?P<id>[\da-z-]+)' |
| | 301 | _GEO_COUNTRIES = ['DK'] |
| | 302 | _TEST = { |
| | 303 | 'url': 'https://www.dr.dk/tv/live/dr1', |
| | 304 | 'info_dict': { |
| | 305 | 'id': 'dr1', |
| | 306 | 'ext': 'mp4', |
| | 307 | 'title': 're:^DR1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', |
| | 308 | }, |
| | 309 | 'params': { |
| | 310 | # m3u8 download |
| | 311 | 'skip_download': True, |
| | 312 | }, |
| | 313 | } |
| | 314 | |
| | 315 | def _real_extract(self, url): |
| | 316 | channel_id = self._match_id(url) |
| | 317 | channel_data = self._download_json( |
| | 318 | 'https://www.dr.dk/mu-online/api/1.0/channel/' + channel_id, |
| | 319 | channel_id) |
| | 320 | title = channel_data['Title'] |
| | 321 | |
| | 322 | formats = [] |
| | 323 | for streaming_server in channel_data.get('StreamingServers', []): |
| | 324 | server = streaming_server.get('Server') |
| | 325 | if not server: |
| | 326 | continue |
| | 327 | link_type = streaming_server.get('LinkType') |
| | 328 | for quality in streaming_server.get('Qualities', []): |
| | 329 | for stream in quality.get('Streams', []): |
| | 330 | stream_path = stream.get('Stream') |
| | 331 | if not stream_path: |
| | 332 | continue |
| | 333 | stream_url = update_url_query( |
| | 334 | '%s/%s' % (server, stream_path), {'b': ''}) |
| | 335 | if link_type == 'HLS': |
| | 336 | formats.extend(self._extract_m3u8_formats( |
| | 337 | stream_url, channel_id, 'mp4', |
| | 338 | m3u8_id=link_type, fatal=False, live=True)) |
| | 339 | elif link_type == 'HDS': |
| | 340 | formats.extend(self._extract_f4m_formats(update_url_query( |
| | 341 | '%s/%s' % (server, stream_path), {'hdcore': '3.7.0'}), |
| | 342 | channel_id, f4m_id=link_type, fatal=False)) |
| | 343 | self._sort_formats(formats) |
| | 344 | |
| | 345 | return { |
| | 346 | 'id': channel_id, |
| | 347 | 'title': title, |
| | 348 | 'thumbnail': channel_data.get('PrimaryImageUri'), |
| | 349 | 'formats': formats, |
| | 350 | 'is_live': True, |
| | 351 | } |
projects / yt-dlp.git / blame_incremental