yt_dlp/extractor/abc.py

   1 import hashlib
   2 import hmac
   3 import re
   4 import time
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     dict_get,
  10     int_or_none,
  11     js_to_json,
  12     parse_iso8601,
  13     str_or_none,
  14     traverse_obj,
  15     try_get,
  16     unescapeHTML,
  17     update_url_query,
  18     url_or_none,
  19 )
  20
  21
  22 class ABCIE(InfoExtractor):
  23     IE_NAME = 'abc.net.au'
  24     _VALID_URL = r'https?://(?:www\.)?abc\.net\.au/(?:news|btn)/(?:[^/]+/){1,4}(?P<id>\d{5,})'
  25
  26     _TESTS = [{
  27         'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
  28         'md5': 'cb3dd03b18455a661071ee1e28344d9f',
  29         'info_dict': {
  30             'id': '5868334',
  31             'ext': 'mp4',
  32             'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
  33             'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
  34         },
  35         'skip': 'this video has expired',
  36     }, {
  37         'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326',
  38         'md5': '4ebd61bdc82d9a8b722f64f1f4b4d121',
  39         'info_dict': {
  40             'id': 'NvqvPeNZsHU',
  41             'ext': 'mp4',
  42             'upload_date': '20150816',
  43             'uploader': 'ABC News (Australia)',
  44             'description': 'Government backbencher Warren Entsch introduces a cross-party sponsored bill to legalise same-sex marriage, saying the bill is designed to promote "an inclusive Australia, not a divided one.". Read more here: http://ab.co/1Mwc6ef',
  45             'uploader_id': 'NewsOnABC',
  46             'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
  47         },
  48         'add_ie': ['Youtube'],
  49         'skip': 'Not accessible from Travis CI server',
  50     }, {
  51         'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
  52         'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
  53         'info_dict': {
  54             'id': '6880080',
  55             'ext': 'mp3',
  56             'title': 'NAB lifts interest rates, following Westpac and CBA',
  57             'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
  58         },
  59     }, {
  60         'url': 'http://www.abc.net.au/news/2015-10-19/6866214',
  61         'only_matching': True,
  62     }, {
  63         'url': 'https://www.abc.net.au/btn/classroom/wwi-centenary/10527914',
  64         'info_dict': {
  65             'id': '10527914',
  66             'ext': 'mp4',
  67             'title': 'WWI Centenary',
  68             'description': 'md5:c2379ec0ca84072e86b446e536954546',
  69         },
  70     }, {
  71         'url': 'https://www.abc.net.au/news/programs/the-world/2020-06-10/black-lives-matter-protests-spawn-support-for/12342074',
  72         'info_dict': {
  73             'id': '12342074',
  74             'ext': 'mp4',
  75             'title': 'Black Lives Matter protests spawn support for Papuans in Indonesia',
  76             'description': 'md5:2961a17dc53abc558589ccd0fb8edd6f',
  77         },
  78     }, {
  79         'url': 'https://www.abc.net.au/btn/newsbreak/btn-newsbreak-20200814/12560476',
  80         'info_dict': {
  81             'id': 'tDL8Ld4dK_8',
  82             'ext': 'mp4',
  83             'title': 'Fortnite Banned From Apple and Google App Stores',
  84             'description': 'md5:a6df3f36ce8f816b74af4bd6462f5651',
  85             'upload_date': '20200813',
  86             'uploader': 'Behind the News',
  87             'uploader_id': 'behindthenews',
  88         },
  89     }, {
  90         'url': 'https://www.abc.net.au/news/2023-06-25/wagner-boss-orders-troops-back-to-bases-to-avoid-bloodshed/102520540',
  91         'info_dict': {
  92             'id': '102520540',
  93             'title': 'Wagner Group retreating from Russia, leader Prigozhin to move to Belarus',
  94             'ext': 'mp4',
  95             'description': 'Wagner troops leave Rostov-on-Don and\xa0Yevgeny Prigozhin will move to Belarus under a deal brokered by Belarusian President Alexander Lukashenko to end the mutiny.',
  96             'thumbnail': 'https://live-production.wcms.abc-cdn.net.au/0c170f5b57f0105c432f366c0e8e267b?impolicy=wcms_crop_resize&cropH=2813&cropW=5000&xPos=0&yPos=249&width=862&height=485',
  97         },
  98     }]
  99
 100     def _real_extract(self, url):
 101         video_id = self._match_id(url)
 102         webpage = self._download_webpage(url, video_id)
 103
 104         mobj = re.search(r'<a\s+href="(?P<url>[^"]+)"\s+data-duration="\d+"\s+title="Download audio directly">', webpage)
 105         if mobj:
 106             urls_info = mobj.groupdict()
 107             youtube = False
 108             video = False
 109         else:
 110             mobj = re.search(r'<a href="(?P<url>http://www\.youtube\.com/watch\?v=[^"]+)"><span><strong>External Link:</strong>',
 111                              webpage)
 112             if mobj is None:
 113                 mobj = re.search(r'<iframe width="100%" src="(?P<url>//www\.youtube-nocookie\.com/embed/[^?"]+)', webpage)
 114             if mobj:
 115                 urls_info = mobj.groupdict()
 116                 youtube = True
 117                 video = True
 118
 119         if mobj is None:
 120             mobj = re.search(r'(?P<type>)"(?:sources|files|renditions)":\s*(?P<json_data>\[[^\]]+\])', webpage)
 121             if mobj is None:
 122                 mobj = re.search(
 123                     r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
 124                     webpage)
 125                 if mobj is None:
 126                     expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>', webpage, 'expired', None)
 127                     if expired:
 128                         raise ExtractorError(f'{self.IE_NAME} said: {expired}', expected=True)
 129                     raise ExtractorError('Unable to extract video urls')
 130
 131             urls_info = self._parse_json(
 132                 mobj.group('json_data'), video_id, transform_source=js_to_json)
 133             youtube = mobj.group('type') == 'YouTube'
 134             video = mobj.group('type') == 'Video' or traverse_obj(
 135                 urls_info, (0, ('contentType', 'MIMEType')), get_all=False) == 'video/mp4'
 136
 137         if not isinstance(urls_info, list):
 138             urls_info = [urls_info]
 139
 140         if youtube:
 141             return self.playlist_result([
 142                 self.url_result(url_info['url']) for url_info in urls_info])
 143
 144         formats = []
 145         for url_info in urls_info:
 146             height = int_or_none(url_info.get('height'))
 147             bitrate = int_or_none(url_info.get('bitrate'))
 148             width = int_or_none(url_info.get('width'))
 149             format_id = None
 150             mobj = re.search(r'_(?:(?P<height>\d+)|(?P<bitrate>\d+)k)\.mp4$', url_info['url'])
 151             if mobj:
 152                 height_from_url = mobj.group('height')
 153                 if height_from_url:
 154                     height = height or int_or_none(height_from_url)
 155                     width = width or int_or_none(url_info.get('label'))
 156                 else:
 157                     bitrate = bitrate or int_or_none(mobj.group('bitrate'))
 158                     format_id = str_or_none(url_info.get('label'))
 159             formats.append({
 160                 'url': url_info['url'],
 161                 'vcodec': url_info.get('codec') if video else 'none',
 162                 'width': width,
 163                 'height': height,
 164                 'tbr': bitrate,
 165                 'filesize': int_or_none(url_info.get('filesize')),
 166                 'format_id': format_id,
 167             })
 168
 169         return {
 170             'id': video_id,
 171             'title': self._og_search_title(webpage),
 172             'formats': formats,
 173             'description': self._og_search_description(webpage),
 174             'thumbnail': self._og_search_thumbnail(webpage),
 175         }
 176
 177
 178 class ABCIViewIE(InfoExtractor):
 179     IE_NAME = 'abc.net.au:iview'
 180     _VALID_URL = r'https?://iview\.abc\.net\.au/(?:[^/]+/)*video/(?P<id>[^/?#]+)'
 181     _GEO_COUNTRIES = ['AU']
 182
 183     _TESTS = [{
 184         'url': 'https://iview.abc.net.au/show/utopia/series/1/video/CO1211V001S00',
 185         'md5': '52a942bfd7a0b79a6bfe9b4ce6c9d0ed',
 186         'info_dict': {
 187             'id': 'CO1211V001S00',
 188             'ext': 'mp4',
 189             'title': 'Series 1 Ep 1 Wood For The Trees',
 190             'series': 'Utopia',
 191             'description': 'md5:0cfb2c183c1b952d1548fd65c8a95c00',
 192             'upload_date': '20230726',
 193             'uploader_id': 'abc1',
 194             'series_id': 'CO1211V',
 195             'episode_id': 'CO1211V001S00',
 196             'season_number': 1,
 197             'season': 'Season 1',
 198             'episode_number': 1,
 199             'episode': 'Wood For The Trees',
 200             'thumbnail': 'https://cdn.iview.abc.net.au/thumbs/i/co/CO1211V001S00_5ad8353f4df09_1280.jpg',
 201             'timestamp': 1690403700,
 202         },
 203         'params': {
 204             'skip_download': True,
 205         },
 206     }, {
 207         'note': 'No episode name',
 208         'url': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00',
 209         'md5': '67715ce3c78426b11ba167d875ac6abf',
 210         'info_dict': {
 211             'id': 'LE1927H001S00',
 212             'ext': 'mp4',
 213             'title': 'Series 11 Ep 1',
 214             'series': 'Gruen',
 215             'description': 'md5:52cc744ad35045baf6aded2ce7287f67',
 216             'upload_date': '20190925',
 217             'uploader_id': 'abc1',
 218             'series_id': 'LE1927H',
 219             'episode_id': 'LE1927H001S00',
 220             'season_number': 11,
 221             'season': 'Season 11',
 222             'episode_number': 1,
 223             'episode': 'Episode 1',
 224             'thumbnail': 'https://cdn.iview.abc.net.au/thumbs/i/le/LE1927H001S00_5d954fbd79e25_1280.jpg',
 225             'timestamp': 1569445289,
 226         },
 227         'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
 228         'params': {
 229             'skip_download': True,
 230         },
 231     }, {
 232         'note': 'No episode number',
 233         'url': 'https://iview.abc.net.au/show/four-corners/series/2022/video/NC2203H039S00',
 234         'md5': '77cb7d8434440e3b28fbebe331c2456a',
 235         'info_dict': {
 236             'id': 'NC2203H039S00',
 237             'ext': 'mp4',
 238             'title': 'Series 2022 Locking Up Kids',
 239             'series': 'Four Corners',
 240             'description': 'md5:54829ca108846d1a70e1fcce2853e720',
 241             'upload_date': '20221114',
 242             'uploader_id': 'abc1',
 243             'series_id': 'NC2203H',
 244             'episode_id': 'NC2203H039S00',
 245             'season_number': 2022,
 246             'season': 'Season 2022',
 247             'episode': 'Locking Up Kids',
 248             'thumbnail': 'https://cdn.iview.abc.net.au/thumbs/i/nc/NC2203H039S00_636d8a0944a22_1920.jpg',
 249             'timestamp': 1668460497,
 250
 251         },
 252         'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
 253         'params': {
 254             'skip_download': True,
 255         },
 256     }, {
 257         'note': 'No episode name or number',
 258         'url': 'https://iview.abc.net.au/show/landline/series/2021/video/RF2004Q043S00',
 259         'md5': '2e17dec06b13cc81dc119d2565289396',
 260         'info_dict': {
 261             'id': 'RF2004Q043S00',
 262             'ext': 'mp4',
 263             'title': 'Series 2021',
 264             'series': 'Landline',
 265             'description': 'md5:c9f30d9c0c914a7fd23842f6240be014',
 266             'upload_date': '20211205',
 267             'uploader_id': 'abc1',
 268             'series_id': 'RF2004Q',
 269             'episode_id': 'RF2004Q043S00',
 270             'season_number': 2021,
 271             'season': 'Season 2021',
 272             'thumbnail': 'https://cdn.iview.abc.net.au/thumbs/i/rf/RF2004Q043S00_61a950639dbc0_1920.jpg',
 273             'timestamp': 1638710705,
 274
 275         },
 276         'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
 277         'params': {
 278             'skip_download': True,
 279         },
 280     }]
 281
 282     def _real_extract(self, url):
 283         video_id = self._match_id(url)
 284         video_params = self._download_json(
 285             'https://iview.abc.net.au/api/programs/' + video_id, video_id)
 286         title = unescapeHTML(video_params.get('title') or video_params['seriesTitle'])
 287         stream = next(s for s in video_params['playlist'] if s.get('type') in ('program', 'livestream'))
 288
 289         house_number = video_params.get('episodeHouseNumber') or video_id
 290         path = f'/auth/hls/sign?ts={int(time.time())}&hn={house_number}&d=android-tablet'
 291         sig = hmac.new(
 292             b'android.content.res.Resources',
 293             path.encode(), hashlib.sha256).hexdigest()
 294         token = self._download_webpage(
 295             f'http://iview.abc.net.au{path}&sig={sig}', video_id)
 296
 297         def tokenize_url(url, token):
 298             return update_url_query(url, {
 299                 'hdnea': token,
 300             })
 301
 302         for sd in ('1080', '720', 'sd', 'sd-low'):
 303             sd_url = try_get(
 304                 stream, lambda x: x['streams']['hls'][sd], str)
 305             if not sd_url:
 306                 continue
 307             formats = self._extract_m3u8_formats(
 308                 tokenize_url(sd_url, token), video_id, 'mp4',
 309                 entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
 310             if formats:
 311                 break
 312
 313         subtitles = {}
 314         src_vtt = stream.get('captions', {}).get('src-vtt')
 315         if src_vtt:
 316             subtitles['en'] = [{
 317                 'url': src_vtt,
 318                 'ext': 'vtt',
 319             }]
 320
 321         is_live = video_params.get('livestream') == '1'
 322
 323         return {
 324             'id': video_id,
 325             'title': title,
 326             'description': video_params.get('description'),
 327             'thumbnail': video_params.get('thumbnail'),
 328             'duration': int_or_none(video_params.get('eventDuration')),
 329             'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),
 330             'series': unescapeHTML(video_params.get('seriesTitle')),
 331             'series_id': video_params.get('seriesHouseNumber') or video_id[:7],
 332             'season_number': int_or_none(self._search_regex(
 333                 r'\bSeries\s+(\d+)\b', title, 'season number', default=None)),
 334             'episode_number': int_or_none(self._search_regex(
 335                 r'\bEp\s+(\d+)\b', title, 'episode number', default=None)),
 336             'episode_id': house_number,
 337             'episode': self._search_regex(
 338                 r'^(?:Series\s+\d+)?\s*(?:Ep\s+\d+)?\s*(.*)$', title, 'episode', default='') or None,
 339             'uploader_id': video_params.get('channel'),
 340             'formats': formats,
 341             'subtitles': subtitles,
 342             'is_live': is_live,
 343         }
 344
 345
 346 class ABCIViewShowSeriesIE(InfoExtractor):
 347     IE_NAME = 'abc.net.au:iview:showseries'
 348     _VALID_URL = r'https?://iview\.abc\.net\.au/show/(?P<id>[^/]+)(?:/series/\d+)?$'
 349     _GEO_COUNTRIES = ['AU']
 350
 351     _TESTS = [{
 352         'url': 'https://iview.abc.net.au/show/upper-middle-bogan',
 353         'info_dict': {
 354             'id': '124870-1',
 355             'title': 'Series 1',
 356             'description': 'md5:93119346c24a7c322d446d8eece430ff',
 357             'series': 'Upper Middle Bogan',
 358             'season': 'Series 1',
 359             'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$',
 360         },
 361         'playlist_count': 8,
 362     }, {
 363         'url': 'https://iview.abc.net.au/show/upper-middle-bogan',
 364         'info_dict': {
 365             'id': 'CO1108V001S00',
 366             'ext': 'mp4',
 367             'title': 'Series 1 Ep 1 I\'m A Swan',
 368             'description': 'md5:7b676758c1de11a30b79b4d301e8da93',
 369             'series': 'Upper Middle Bogan',
 370             'uploader_id': 'abc1',
 371             'upload_date': '20210630',
 372             'timestamp': 1625036400,
 373         },
 374         'params': {
 375             'noplaylist': True,
 376             'skip_download': 'm3u8',
 377         },
 378     }, {
 379         # 'videoEpisodes' is a dict with `items` key
 380         'url': 'https://iview.abc.net.au/show/7-30-mark-humphries-satire',
 381         'info_dict': {
 382             'id': '178458-0',
 383             'title': 'Episodes',
 384             'description': 'Satirist Mark Humphries brings his unique perspective on current political events for 7.30.',
 385             'series': '7.30 Mark Humphries Satire',
 386             'season': 'Episodes',
 387             'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$',
 388         },
 389         'playlist_count': 15,
 390     }]
 391
 392     def _real_extract(self, url):
 393         show_id = self._match_id(url)
 394         webpage = self._download_webpage(url, show_id)
 395         webpage_data = self._search_regex(
 396             r'window\.__INITIAL_STATE__\s*=\s*[\'"](.+?)[\'"]\s*;',
 397             webpage, 'initial state')
 398         video_data = self._parse_json(
 399             unescapeHTML(webpage_data).encode().decode('unicode_escape'), show_id)
 400         video_data = video_data['route']['pageData']['_embedded']
 401
 402         highlight = try_get(video_data, lambda x: x['highlightVideo']['shareUrl'])
 403         if not self._yes_playlist(show_id, bool(highlight), video_label='highlight video'):
 404             return self.url_result(highlight, ie=ABCIViewIE.ie_key())
 405
 406         series = video_data['selectedSeries']
 407         return {
 408             '_type': 'playlist',
 409             'entries': [self.url_result(episode_url, ABCIViewIE)
 410                         for episode_url in traverse_obj(series, (
 411                             '_embedded', 'videoEpisodes', (None, 'items'), ..., 'shareUrl', {url_or_none}))],
 412             'id': series.get('id'),
 413             'title': dict_get(series, ('title', 'displaySubtitle')),
 414             'description': series.get('description'),
 415             'series': dict_get(series, ('showTitle', 'displayTitle')),
 416             'season': dict_get(series, ('title', 'displaySubtitle')),
 417             'thumbnail': traverse_obj(
 418                 series, 'thumbnail', ('images', lambda _, v: v['name'] == 'seriesThumbnail', 'url'), get_all=False),
 419         }