yt_dlp/extractor/afreecatv.py

   1 import functools
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     OnDemandPagedList,
   7     UserNotLive,
   8     determine_ext,
   9     filter_dict,
  10     int_or_none,
  11     orderedSet,
  12     unified_timestamp,
  13     url_or_none,
  14     urlencode_postdata,
  15     urljoin,
  16 )
  17 from ..utils.traversal import traverse_obj
  18
  19
  20 class AfreecaTVBaseIE(InfoExtractor):
  21     _NETRC_MACHINE = 'afreecatv'
  22
  23     def _perform_login(self, username, password):
  24         login_form = {
  25             'szWork': 'login',
  26             'szType': 'json',
  27             'szUid': username,
  28             'szPassword': password,
  29             'isSaveId': 'false',
  30             'szScriptVar': 'oLoginRet',
  31             'szAction': '',
  32         }
  33
  34         response = self._download_json(
  35             'https://login.afreecatv.com/app/LoginAction.php', None,
  36             'Logging in', data=urlencode_postdata(login_form))
  37
  38         _ERRORS = {
  39             -4: 'Your account has been suspended due to a violation of our terms and policies.',
  40             -5: 'https://member.afreecatv.com/app/user_delete_progress.php',
  41             -6: 'https://login.afreecatv.com/membership/changeMember.php',
  42             -8: "Hello! AfreecaTV here.\nThe username you have entered belongs to \n an account that requires a legal guardian's consent. \nIf you wish to use our services without restriction, \nplease make sure to go through the necessary verification process.",
  43             -9: 'https://member.afreecatv.com/app/pop_login_block.php',
  44             -11: 'https://login.afreecatv.com/afreeca/second_login.php',
  45             -12: 'https://member.afreecatv.com/app/user_security.php',
  46             0: 'The username does not exist or you have entered the wrong password.',
  47             -1: 'The username does not exist or you have entered the wrong password.',
  48             -3: 'You have entered your username/password incorrectly.',
  49             -7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.',
  50             -10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.',
  51             -32008: 'You have failed to log in. Please contact our Help Center.',
  52         }
  53
  54         result = int_or_none(response.get('RESULT'))
  55         if result != 1:
  56             error = _ERRORS.get(result, 'You have failed to log in.')
  57             raise ExtractorError(
  58                 f'Unable to login: {self.IE_NAME} said: {error}',
  59                 expected=True)
  60
  61
  62 class AfreecaTVIE(AfreecaTVBaseIE):
  63     IE_NAME = 'afreecatv'
  64     IE_DESC = 'afreecatv.com'
  65     _VALID_URL = r'''(?x)
  66                     https?://
  67                         (?:
  68                             (?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
  69                             (?:
  70                                 /app/(?:index|read_ucc_bbs)\.cgi|
  71                                 /player/[Pp]layer\.(?:swf|html)
  72                             )\?.*?\bnTitleNo=|
  73                             vod\.afreecatv\.com/(PLAYER/STATION|player)/
  74                         )
  75                         (?P<id>\d+)
  76                     '''
  77     _TESTS = [{
  78         'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
  79         'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
  80         'info_dict': {
  81             'id': '36164052',
  82             'ext': 'mp4',
  83             'title': '데일리 에이프릴 요정들의 시상식!',
  84             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  85             'uploader': 'dailyapril',
  86             'uploader_id': 'dailyapril',
  87             'upload_date': '20160503',
  88         },
  89         'skip': 'Video is gone',
  90     }, {
  91         'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
  92         'info_dict': {
  93             'id': '36153164',
  94             'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  95             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  96             'uploader': 'dailyapril',
  97             'uploader_id': 'dailyapril',
  98         },
  99         'playlist_count': 2,
 100         'playlist': [{
 101             'md5': 'd8b7c174568da61d774ef0203159bf97',
 102             'info_dict': {
 103                 'id': '36153164_1',
 104                 'ext': 'mp4',
 105                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
 106                 'upload_date': '20160502',
 107             },
 108         }, {
 109             'md5': '58f2ce7f6044e34439ab2d50612ab02b',
 110             'info_dict': {
 111                 'id': '36153164_2',
 112                 'ext': 'mp4',
 113                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
 114                 'upload_date': '20160502',
 115             },
 116         }],
 117         'skip': 'Video is gone',
 118     }, {
 119         # non standard key
 120         'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605',
 121         'info_dict': {
 122             'id': '20170411_BE689A0E_190960999_1_2_h',
 123             'ext': 'mp4',
 124             'title': '혼자사는여자집',
 125             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 126             'uploader': '♥이슬이',
 127             'uploader_id': 'dasl8121',
 128             'upload_date': '20170411',
 129             'timestamp': 1491929865,
 130             'duration': 213,
 131         },
 132         'params': {
 133             'skip_download': True,
 134         },
 135     }, {
 136         # adult content
 137         'url': 'https://vod.afreecatv.com/player/97267690',
 138         'info_dict': {
 139             'id': '20180327_27901457_202289533_1',
 140             'ext': 'mp4',
 141             'title': '[생]빨개요♥ (part 1)',
 142             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 143             'uploader': '[SA]서아',
 144             'uploader_id': 'bjdyrksu',
 145             'upload_date': '20180327',
 146             'duration': 3601,
 147         },
 148         'params': {
 149             'skip_download': True,
 150         },
 151         'skip': 'The VOD does not exist',
 152     }, {
 153         'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
 154         'only_matching': True,
 155     }, {
 156         'url': 'https://vod.afreecatv.com/player/96753363',
 157         'info_dict': {
 158             'id': '20230108_9FF5BEE1_244432674_1',
 159             'ext': 'mp4',
 160             'uploader_id': 'rlantnghks',
 161             'uploader': '페이즈으',
 162             'duration': 10840,
 163             'thumbnail': r're:https?://videoimg\.afreecatv\.com/.+',
 164             'upload_date': '20230108',
 165             'timestamp': 1673218805,
 166             'title': '젠지 페이즈',
 167         },
 168         'params': {
 169             'skip_download': True,
 170         },
 171     }, {
 172         # adult content
 173         'url': 'https://vod.afreecatv.com/player/70395877',
 174         'only_matching': True,
 175     }, {
 176         # subscribers only
 177         'url': 'https://vod.afreecatv.com/player/104647403',
 178         'only_matching': True,
 179     }, {
 180         # private
 181         'url': 'https://vod.afreecatv.com/player/81669846',
 182         'only_matching': True,
 183     }]
 184
 185     def _real_extract(self, url):
 186         video_id = self._match_id(url)
 187         data = self._download_json(
 188             'https://api.m.afreecatv.com/station/video/a/view', video_id,
 189             headers={'Referer': url}, data=urlencode_postdata({
 190                 'nTitleNo': video_id,
 191                 'nApiLevel': 10,
 192             }), impersonate=True)['data']
 193
 194         error_code = traverse_obj(data, ('code', {int}))
 195         if error_code == -6221:
 196             raise ExtractorError('The VOD does not exist', expected=True)
 197         elif error_code == -6205:
 198             raise ExtractorError('This VOD is private', expected=True)
 199
 200         common_info = traverse_obj(data, {
 201             'title': ('title', {str}),
 202             'uploader': ('writer_nick', {str}),
 203             'uploader_id': ('bj_id', {str}),
 204             'duration': ('total_file_duration', {functools.partial(int_or_none, scale=1000)}),
 205             'thumbnail': ('thumb', {url_or_none}),
 206         })
 207
 208         entries = []
 209         for file_num, file_element in enumerate(
 210                 traverse_obj(data, ('files', lambda _, v: url_or_none(v['file']))), start=1):
 211             file_url = file_element['file']
 212             if determine_ext(file_url) == 'm3u8':
 213                 formats = self._extract_m3u8_formats(
 214                     file_url, video_id, 'mp4', m3u8_id='hls',
 215                     note=f'Downloading part {file_num} m3u8 information')
 216             else:
 217                 formats = [{
 218                     'url': file_url,
 219                     'format_id': 'http',
 220                 }]
 221
 222             entries.append({
 223                 **common_info,
 224                 'id': file_element.get('file_info_key') or f'{video_id}_{file_num}',
 225                 'title': f'{common_info.get("title") or "Untitled"} (part {file_num})',
 226                 'formats': formats,
 227                 **traverse_obj(file_element, {
 228                     'duration': ('duration', {functools.partial(int_or_none, scale=1000)}),
 229                     'timestamp': ('file_start', {unified_timestamp}),
 230                 }),
 231             })
 232
 233         if traverse_obj(data, ('adult_status', {str})) == 'notLogin':
 234             if not entries:
 235                 self.raise_login_required(
 236                     'Only users older than 19 are able to watch this video', method='password')
 237             self.report_warning(
 238                 'In accordance with local laws and regulations, underage users are '
 239                 'restricted from watching adult content. Only content suitable for all '
 240                 f'ages will be downloaded. {self._login_hint("password")}')
 241
 242         if not entries and traverse_obj(data, ('sub_upload_type', {str})):
 243             self.raise_login_required('This VOD is for subscribers only', method='password')
 244
 245         if len(entries) == 1:
 246             return {
 247                 **entries[0],
 248                 'title': common_info.get('title'),
 249             }
 250
 251         common_info['timestamp'] = traverse_obj(entries, (..., 'timestamp'), get_all=False)
 252
 253         return self.playlist_result(entries, video_id, multi_video=True, **common_info)
 254
 255
 256 class AfreecaTVLiveIE(AfreecaTVBaseIE):
 257     IE_NAME = 'afreecatv:live'
 258     IE_DESC = 'afreecatv.com livestreams'
 259     _VALID_URL = r'https?://play\.afreeca(?:tv)?\.com/(?P<id>[^/]+)(?:/(?P<bno>\d+))?'
 260     _TESTS = [{
 261         'url': 'https://play.afreecatv.com/pyh3646/237852185',
 262         'info_dict': {
 263             'id': '237852185',
 264             'ext': 'mp4',
 265             'title': '【 우루과이 오늘은 무슨일이? 】',
 266             'uploader': '박진우[JINU]',
 267             'uploader_id': 'pyh3646',
 268             'timestamp': 1640661495,
 269             'is_live': True,
 270         },
 271         'skip': 'Livestream has ended',
 272     }, {
 273         'url': 'https://play.afreecatv.com/pyh3646/237852185',
 274         'only_matching': True,
 275     }, {
 276         'url': 'https://play.afreecatv.com/pyh3646',
 277         'only_matching': True,
 278     }]
 279
 280     _LIVE_API_URL = 'https://live.afreecatv.com/afreeca/player_live_api.php'
 281     _WORKING_CDNS = [
 282         'gcp_cdn',  # live-global-cdn-v02.afreecatv.com
 283         'gs_cdn_pc_app',  # pc-app.stream.afreecatv.com
 284         'gs_cdn_mobile_web',  # mobile-web.stream.afreecatv.com
 285         'gs_cdn_pc_web',  # pc-web.stream.afreecatv.com
 286     ]
 287     _BAD_CDNS = [
 288         'gs_cdn',  # chromecast.afreeca.gscdn.com (cannot resolve)
 289         'gs_cdn_chromecast',  # chromecast.stream.afreecatv.com (HTTP Error 400)
 290         'azure_cdn',  # live-global-cdn-v01.afreecatv.com (cannot resolve)
 291         'aws_cf',  # live-global-cdn-v03.afreecatv.com (cannot resolve)
 292         'kt_cdn',  # kt.stream.afreecatv.com (HTTP Error 400)
 293     ]
 294
 295     def _extract_formats(self, channel_info, broadcast_no, aid):
 296         stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.afreecatv.com'
 297
 298         # If user has not passed CDN IDs, try API-provided CDN ID followed by other working CDN IDs
 299         default_cdn_ids = orderedSet([
 300             *traverse_obj(channel_info, ('CDN', {str}, all, lambda _, v: v not in self._BAD_CDNS)),
 301             *self._WORKING_CDNS,
 302         ])
 303         cdn_ids = self._configuration_arg('cdn', default_cdn_ids)
 304
 305         for attempt, cdn_id in enumerate(cdn_ids, start=1):
 306             m3u8_url = traverse_obj(self._download_json(
 307                 urljoin(stream_base_url, 'broad_stream_assign.html'), broadcast_no,
 308                 f'Downloading {cdn_id} stream info', f'Unable to download {cdn_id} stream info',
 309                 fatal=False, query={
 310                     'return_type': cdn_id,
 311                     'broad_key': f'{broadcast_no}-common-master-hls',
 312                 }), ('view_url', {url_or_none}))
 313             try:
 314                 return self._extract_m3u8_formats(
 315                     m3u8_url, broadcast_no, 'mp4', m3u8_id='hls', query={'aid': aid},
 316                     headers={'Referer': 'https://play.afreecatv.com/'})
 317             except ExtractorError as e:
 318                 if attempt == len(cdn_ids):
 319                     raise
 320                 self.report_warning(
 321                     f'{e.cause or e.msg}. Retrying... (attempt {attempt} of {len(cdn_ids)})')
 322
 323     def _real_extract(self, url):
 324         broadcaster_id, broadcast_no = self._match_valid_url(url).group('id', 'bno')
 325         channel_info = traverse_obj(self._download_json(
 326             self._LIVE_API_URL, broadcaster_id, data=urlencode_postdata({'bid': broadcaster_id})),
 327             ('CHANNEL', {dict})) or {}
 328
 329         broadcaster_id = channel_info.get('BJID') or broadcaster_id
 330         broadcast_no = channel_info.get('BNO') or broadcast_no
 331         if not broadcast_no:
 332             raise UserNotLive(video_id=broadcaster_id)
 333
 334         password = self.get_param('videopassword')
 335         if channel_info.get('BPWD') == 'Y' and password is None:
 336             raise ExtractorError(
 337                 'This livestream is protected by a password, use the --video-password option',
 338                 expected=True)
 339
 340         token_info = traverse_obj(self._download_json(
 341             self._LIVE_API_URL, broadcast_no, 'Downloading access token for stream',
 342             'Unable to download access token for stream', data=urlencode_postdata(filter_dict({
 343                 'bno': broadcast_no,
 344                 'stream_type': 'common',
 345                 'type': 'aid',
 346                 'quality': 'master',
 347                 'pwd': password,
 348             }))), ('CHANNEL', {dict})) or {}
 349         aid = token_info.get('AID')
 350         if not aid:
 351             result = token_info.get('RESULT')
 352             if result == 0:
 353                 raise ExtractorError('This livestream has ended', expected=True)
 354             elif result == -6:
 355                 self.raise_login_required('This livestream is for subscribers only', method='password')
 356             raise ExtractorError('Unable to extract access token')
 357
 358         formats = self._extract_formats(channel_info, broadcast_no, aid)
 359
 360         station_info = traverse_obj(self._download_json(
 361             'https://st.afreecatv.com/api/get_station_status.php', broadcast_no,
 362             'Downloading channel metadata', 'Unable to download channel metadata',
 363             query={'szBjId': broadcaster_id}, fatal=False), {dict}) or {}
 364
 365         return {
 366             'id': broadcast_no,
 367             'title': channel_info.get('TITLE') or station_info.get('station_title'),
 368             'uploader': channel_info.get('BJNICK') or station_info.get('station_name'),
 369             'uploader_id': broadcaster_id,
 370             'timestamp': unified_timestamp(station_info.get('broad_start')),
 371             'formats': formats,
 372             'is_live': True,
 373             'http_headers': {'Referer': url},
 374         }
 375
 376
 377 class AfreecaTVUserIE(InfoExtractor):
 378     IE_NAME = 'afreecatv:user'
 379     _VALID_URL = r'https?://bj\.afreeca(?:tv)?\.com/(?P<id>[^/]+)/vods/?(?P<slug_type>[^/]+)?'
 380     _TESTS = [{
 381         'url': 'https://bj.afreecatv.com/ryuryu24/vods/review',
 382         'info_dict': {
 383             '_type': 'playlist',
 384             'id': 'ryuryu24',
 385             'title': 'ryuryu24 - review',
 386         },
 387         'playlist_count': 218,
 388     }, {
 389         'url': 'https://bj.afreecatv.com/parang1995/vods/highlight',
 390         'info_dict': {
 391             '_type': 'playlist',
 392             'id': 'parang1995',
 393             'title': 'parang1995 - highlight',
 394         },
 395         'playlist_count': 997,
 396     }, {
 397         'url': 'https://bj.afreecatv.com/ryuryu24/vods',
 398         'info_dict': {
 399             '_type': 'playlist',
 400             'id': 'ryuryu24',
 401             'title': 'ryuryu24 - all',
 402         },
 403         'playlist_count': 221,
 404     }, {
 405         'url': 'https://bj.afreecatv.com/ryuryu24/vods/balloonclip',
 406         'info_dict': {
 407             '_type': 'playlist',
 408             'id': 'ryuryu24',
 409             'title': 'ryuryu24 - balloonclip',
 410         },
 411         'playlist_count': 0,
 412     }]
 413     _PER_PAGE = 60
 414
 415     def _fetch_page(self, user_id, user_type, page):
 416         page += 1
 417         info = self._download_json(f'https://bjapi.afreecatv.com/api/{user_id}/vods/{user_type}', user_id,
 418                                    query={'page': page, 'per_page': self._PER_PAGE, 'orderby': 'reg_date'},
 419                                    note=f'Downloading {user_type} video page {page}')
 420         for item in info['data']:
 421             yield self.url_result(
 422                 f'https://vod.afreecatv.com/player/{item["title_no"]}/', AfreecaTVIE, item['title_no'])
 423
 424     def _real_extract(self, url):
 425         user_id, user_type = self._match_valid_url(url).group('id', 'slug_type')
 426         user_type = user_type or 'all'
 427         entries = OnDemandPagedList(functools.partial(self._fetch_page, user_id, user_type), self._PER_PAGE)
 428         return self.playlist_result(entries, user_id, f'{user_id} - {user_type}')