yt_dlp/extractor/afreecatv.py

   1 import functools
   2
   3 from .common import InfoExtractor
   4 from ..networking import Request
   5 from ..utils import (
   6     ExtractorError,
   7     OnDemandPagedList,
   8     UserNotLive,
   9     determine_ext,
  10     filter_dict,
  11     int_or_none,
  12     orderedSet,
  13     unified_timestamp,
  14     url_or_none,
  15     urlencode_postdata,
  16     urljoin,
  17 )
  18 from ..utils.traversal import traverse_obj
  19
  20
  21 class AfreecaTVBaseIE(InfoExtractor):
  22     _NETRC_MACHINE = 'afreecatv'
  23
  24     def _perform_login(self, username, password):
  25         login_form = {
  26             'szWork': 'login',
  27             'szType': 'json',
  28             'szUid': username,
  29             'szPassword': password,
  30             'isSaveId': 'false',
  31             'szScriptVar': 'oLoginRet',
  32             'szAction': '',
  33         }
  34
  35         response = self._download_json(
  36             'https://login.afreecatv.com/app/LoginAction.php', None,
  37             'Logging in', data=urlencode_postdata(login_form))
  38
  39         _ERRORS = {
  40             -4: 'Your account has been suspended due to a violation of our terms and policies.',
  41             -5: 'https://member.afreecatv.com/app/user_delete_progress.php',
  42             -6: 'https://login.afreecatv.com/membership/changeMember.php',
  43             -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.",
  44             -9: 'https://member.afreecatv.com/app/pop_login_block.php',
  45             -11: 'https://login.afreecatv.com/afreeca/second_login.php',
  46             -12: 'https://member.afreecatv.com/app/user_security.php',
  47             0: 'The username does not exist or you have entered the wrong password.',
  48             -1: 'The username does not exist or you have entered the wrong password.',
  49             -3: 'You have entered your username/password incorrectly.',
  50             -7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.',
  51             -10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.',
  52             -32008: 'You have failed to log in. Please contact our Help Center.',
  53         }
  54
  55         result = int_or_none(response.get('RESULT'))
  56         if result != 1:
  57             error = _ERRORS.get(result, 'You have failed to log in.')
  58             raise ExtractorError(
  59                 f'Unable to login: {self.IE_NAME} said: {error}',
  60                 expected=True)
  61
  62     def _call_api(self, endpoint, display_id, data=None, headers=None, query=None):
  63         return self._download_json(Request(
  64             f'https://api.m.afreecatv.com/{endpoint}',
  65             data=data, headers=headers, query=query,
  66             extensions={'legacy_ssl': True}), display_id,
  67             'Downloading API JSON', 'Unable to download API JSON')
  68
  69
  70 class AfreecaTVIE(AfreecaTVBaseIE):
  71     IE_NAME = 'afreecatv'
  72     IE_DESC = 'afreecatv.com'
  73     _VALID_URL = r'''(?x)
  74                     https?://
  75                         (?:
  76                             (?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
  77                             (?:
  78                                 /app/(?:index|read_ucc_bbs)\.cgi|
  79                                 /player/[Pp]layer\.(?:swf|html)
  80                             )\?.*?\bnTitleNo=|
  81                             vod\.afreecatv\.com/(PLAYER/STATION|player)/
  82                         )
  83                         (?P<id>\d+)/?(?:$|[?#&])
  84                     '''
  85     _TESTS = [{
  86         'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
  87         'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
  88         'info_dict': {
  89             'id': '36164052',
  90             'ext': 'mp4',
  91             'title': '데일리 에이프릴 요정들의 시상식!',
  92             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  93             'uploader': 'dailyapril',
  94             'uploader_id': 'dailyapril',
  95             'upload_date': '20160503',
  96         },
  97         'skip': 'Video is gone',
  98     }, {
  99         'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
 100         'info_dict': {
 101             'id': '36153164',
 102             'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
 103             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 104             'uploader': 'dailyapril',
 105             'uploader_id': 'dailyapril',
 106         },
 107         'playlist_count': 2,
 108         'playlist': [{
 109             'md5': 'd8b7c174568da61d774ef0203159bf97',
 110             'info_dict': {
 111                 'id': '36153164_1',
 112                 'ext': 'mp4',
 113                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
 114                 'upload_date': '20160502',
 115             },
 116         }, {
 117             'md5': '58f2ce7f6044e34439ab2d50612ab02b',
 118             'info_dict': {
 119                 'id': '36153164_2',
 120                 'ext': 'mp4',
 121                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
 122                 'upload_date': '20160502',
 123             },
 124         }],
 125         'skip': 'Video is gone',
 126     }, {
 127         # non standard key
 128         'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605',
 129         'info_dict': {
 130             'id': '20170411_BE689A0E_190960999_1_2_h',
 131             'ext': 'mp4',
 132             'title': '혼자사는여자집',
 133             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 134             'uploader': '♥이슬이',
 135             'uploader_id': 'dasl8121',
 136             'upload_date': '20170411',
 137             'timestamp': 1491929865,
 138             'duration': 213,
 139         },
 140         'params': {
 141             'skip_download': True,
 142         },
 143     }, {
 144         # adult content
 145         'url': 'https://vod.afreecatv.com/player/97267690',
 146         'info_dict': {
 147             'id': '20180327_27901457_202289533_1',
 148             'ext': 'mp4',
 149             'title': '[생]빨개요♥ (part 1)',
 150             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 151             'uploader': '[SA]서아',
 152             'uploader_id': 'bjdyrksu',
 153             'upload_date': '20180327',
 154             'duration': 3601,
 155         },
 156         'params': {
 157             'skip_download': True,
 158         },
 159         'skip': 'The VOD does not exist',
 160     }, {
 161         'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
 162         'only_matching': True,
 163     }, {
 164         'url': 'https://vod.afreecatv.com/player/96753363',
 165         'info_dict': {
 166             'id': '20230108_9FF5BEE1_244432674_1',
 167             'ext': 'mp4',
 168             'uploader_id': 'rlantnghks',
 169             'uploader': '페이즈으',
 170             'duration': 10840,
 171             'thumbnail': r're:https?://videoimg\.afreecatv\.com/.+',
 172             'upload_date': '20230108',
 173             'timestamp': 1673218805,
 174             'title': '젠지 페이즈',
 175         },
 176         'params': {
 177             'skip_download': True,
 178         },
 179     }, {
 180         # adult content
 181         'url': 'https://vod.afreecatv.com/player/70395877',
 182         'only_matching': True,
 183     }, {
 184         # subscribers only
 185         'url': 'https://vod.afreecatv.com/player/104647403',
 186         'only_matching': True,
 187     }, {
 188         # private
 189         'url': 'https://vod.afreecatv.com/player/81669846',
 190         'only_matching': True,
 191     }]
 192
 193     def _real_extract(self, url):
 194         video_id = self._match_id(url)
 195         data = self._call_api(
 196             'station/video/a/view', video_id, headers={'Referer': url},
 197             data=urlencode_postdata({
 198                 'nTitleNo': video_id,
 199                 'nApiLevel': 10,
 200             }))['data']
 201
 202         error_code = traverse_obj(data, ('code', {int}))
 203         if error_code == -6221:
 204             raise ExtractorError('The VOD does not exist', expected=True)
 205         elif error_code == -6205:
 206             raise ExtractorError('This VOD is private', expected=True)
 207
 208         common_info = traverse_obj(data, {
 209             'title': ('title', {str}),
 210             'uploader': ('writer_nick', {str}),
 211             'uploader_id': ('bj_id', {str}),
 212             'duration': ('total_file_duration', {functools.partial(int_or_none, scale=1000)}),
 213             'thumbnail': ('thumb', {url_or_none}),
 214         })
 215
 216         entries = []
 217         for file_num, file_element in enumerate(
 218                 traverse_obj(data, ('files', lambda _, v: url_or_none(v['file']))), start=1):
 219             file_url = file_element['file']
 220             if determine_ext(file_url) == 'm3u8':
 221                 formats = self._extract_m3u8_formats(
 222                     file_url, video_id, 'mp4', m3u8_id='hls',
 223                     note=f'Downloading part {file_num} m3u8 information')
 224             else:
 225                 formats = [{
 226                     'url': file_url,
 227                     'format_id': 'http',
 228                 }]
 229
 230             entries.append({
 231                 **common_info,
 232                 'id': file_element.get('file_info_key') or f'{video_id}_{file_num}',
 233                 'title': f'{common_info.get("title") or "Untitled"} (part {file_num})',
 234                 'formats': formats,
 235                 **traverse_obj(file_element, {
 236                     'duration': ('duration', {functools.partial(int_or_none, scale=1000)}),
 237                     'timestamp': ('file_start', {unified_timestamp}),
 238                 }),
 239             })
 240
 241         if traverse_obj(data, ('adult_status', {str})) == 'notLogin':
 242             if not entries:
 243                 self.raise_login_required(
 244                     'Only users older than 19 are able to watch this video', method='password')
 245             self.report_warning(
 246                 'In accordance with local laws and regulations, underage users are '
 247                 'restricted from watching adult content. Only content suitable for all '
 248                 f'ages will be downloaded. {self._login_hint("password")}')
 249
 250         if not entries and traverse_obj(data, ('sub_upload_type', {str})):
 251             self.raise_login_required('This VOD is for subscribers only', method='password')
 252
 253         if len(entries) == 1:
 254             return {
 255                 **entries[0],
 256                 'title': common_info.get('title'),
 257             }
 258
 259         common_info['timestamp'] = traverse_obj(entries, (..., 'timestamp'), get_all=False)
 260
 261         return self.playlist_result(entries, video_id, multi_video=True, **common_info)
 262
 263
 264 class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
 265     IE_NAME = 'afreecatv:catchstory'
 266     IE_DESC = 'afreecatv.com catch story'
 267     _VALID_URL = r'https?://vod\.afreecatv\.com/player/(?P<id>\d+)/catchstory'
 268     _TESTS = [{
 269         'url': 'https://vod.afreecatv.com/player/103247/catchstory',
 270         'info_dict': {
 271             'id': '103247',
 272         },
 273         'playlist_count': 2,
 274     }]
 275
 276     def _real_extract(self, url):
 277         video_id = self._match_id(url)
 278         data = self._call_api(
 279             'catchstory/a/view', video_id, headers={'Referer': url},
 280             query={'aStoryListIdx': '', 'nStoryIdx': video_id})
 281
 282         return self.playlist_result(self._entries(data), video_id)
 283
 284     @staticmethod
 285     def _entries(data):
 286         # 'files' is always a list with 1 element
 287         yield from traverse_obj(data, (
 288             'data', lambda _, v: v['story_type'] == 'catch',
 289             'catch_list', lambda _, v: v['files'][0]['file'], {
 290                 'id': ('files', 0, 'file_info_key', {str}),
 291                 'url': ('files', 0, 'file', {url_or_none}),
 292                 'duration': ('files', 0, 'duration', {functools.partial(int_or_none, scale=1000)}),
 293                 'title': ('title', {str}),
 294                 'uploader': ('writer_nick', {str}),
 295                 'uploader_id': ('writer_id', {str}),
 296                 'thumbnail': ('thumb', {url_or_none}),
 297                 'timestamp': ('write_timestamp', {int_or_none}),
 298             }))
 299
 300
 301 class AfreecaTVLiveIE(AfreecaTVBaseIE):
 302     IE_NAME = 'afreecatv:live'
 303     IE_DESC = 'afreecatv.com livestreams'
 304     _VALID_URL = r'https?://play\.afreeca(?:tv)?\.com/(?P<id>[^/]+)(?:/(?P<bno>\d+))?'
 305     _TESTS = [{
 306         'url': 'https://play.afreecatv.com/pyh3646/237852185',
 307         'info_dict': {
 308             'id': '237852185',
 309             'ext': 'mp4',
 310             'title': '【 우루과이 오늘은 무슨일이? 】',
 311             'uploader': '박진우[JINU]',
 312             'uploader_id': 'pyh3646',
 313             'timestamp': 1640661495,
 314             'is_live': True,
 315         },
 316         'skip': 'Livestream has ended',
 317     }, {
 318         'url': 'https://play.afreecatv.com/pyh3646/237852185',
 319         'only_matching': True,
 320     }, {
 321         'url': 'https://play.afreecatv.com/pyh3646',
 322         'only_matching': True,
 323     }]
 324
 325     _LIVE_API_URL = 'https://live.afreecatv.com/afreeca/player_live_api.php'
 326     _WORKING_CDNS = [
 327         'gcp_cdn',  # live-global-cdn-v02.afreecatv.com
 328         'gs_cdn_pc_app',  # pc-app.stream.afreecatv.com
 329         'gs_cdn_mobile_web',  # mobile-web.stream.afreecatv.com
 330         'gs_cdn_pc_web',  # pc-web.stream.afreecatv.com
 331     ]
 332     _BAD_CDNS = [
 333         'gs_cdn',  # chromecast.afreeca.gscdn.com (cannot resolve)
 334         'gs_cdn_chromecast',  # chromecast.stream.afreecatv.com (HTTP Error 400)
 335         'azure_cdn',  # live-global-cdn-v01.afreecatv.com (cannot resolve)
 336         'aws_cf',  # live-global-cdn-v03.afreecatv.com (cannot resolve)
 337         'kt_cdn',  # kt.stream.afreecatv.com (HTTP Error 400)
 338     ]
 339
 340     def _extract_formats(self, channel_info, broadcast_no, aid):
 341         stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.afreecatv.com'
 342
 343         # If user has not passed CDN IDs, try API-provided CDN ID followed by other working CDN IDs
 344         default_cdn_ids = orderedSet([
 345             *traverse_obj(channel_info, ('CDN', {str}, all, lambda _, v: v not in self._BAD_CDNS)),
 346             *self._WORKING_CDNS,
 347         ])
 348         cdn_ids = self._configuration_arg('cdn', default_cdn_ids)
 349
 350         for attempt, cdn_id in enumerate(cdn_ids, start=1):
 351             m3u8_url = traverse_obj(self._download_json(
 352                 urljoin(stream_base_url, 'broad_stream_assign.html'), broadcast_no,
 353                 f'Downloading {cdn_id} stream info', f'Unable to download {cdn_id} stream info',
 354                 fatal=False, query={
 355                     'return_type': cdn_id,
 356                     'broad_key': f'{broadcast_no}-common-master-hls',
 357                 }), ('view_url', {url_or_none}))
 358             try:
 359                 return self._extract_m3u8_formats(
 360                     m3u8_url, broadcast_no, 'mp4', m3u8_id='hls', query={'aid': aid},
 361                     headers={'Referer': 'https://play.afreecatv.com/'})
 362             except ExtractorError as e:
 363                 if attempt == len(cdn_ids):
 364                     raise
 365                 self.report_warning(
 366                     f'{e.cause or e.msg}. Retrying... (attempt {attempt} of {len(cdn_ids)})')
 367
 368     def _real_extract(self, url):
 369         broadcaster_id, broadcast_no = self._match_valid_url(url).group('id', 'bno')
 370         channel_info = traverse_obj(self._download_json(
 371             self._LIVE_API_URL, broadcaster_id, data=urlencode_postdata({'bid': broadcaster_id})),
 372             ('CHANNEL', {dict})) or {}
 373
 374         broadcaster_id = channel_info.get('BJID') or broadcaster_id
 375         broadcast_no = channel_info.get('BNO') or broadcast_no
 376         if not broadcast_no:
 377             raise UserNotLive(video_id=broadcaster_id)
 378
 379         password = self.get_param('videopassword')
 380         if channel_info.get('BPWD') == 'Y' and password is None:
 381             raise ExtractorError(
 382                 'This livestream is protected by a password, use the --video-password option',
 383                 expected=True)
 384
 385         token_info = traverse_obj(self._download_json(
 386             self._LIVE_API_URL, broadcast_no, 'Downloading access token for stream',
 387             'Unable to download access token for stream', data=urlencode_postdata(filter_dict({
 388                 'bno': broadcast_no,
 389                 'stream_type': 'common',
 390                 'type': 'aid',
 391                 'quality': 'master',
 392                 'pwd': password,
 393             }))), ('CHANNEL', {dict})) or {}
 394         aid = token_info.get('AID')
 395         if not aid:
 396             result = token_info.get('RESULT')
 397             if result == 0:
 398                 raise ExtractorError('This livestream has ended', expected=True)
 399             elif result == -6:
 400                 self.raise_login_required('This livestream is for subscribers only', method='password')
 401             raise ExtractorError('Unable to extract access token')
 402
 403         formats = self._extract_formats(channel_info, broadcast_no, aid)
 404
 405         station_info = traverse_obj(self._download_json(
 406             'https://st.afreecatv.com/api/get_station_status.php', broadcast_no,
 407             'Downloading channel metadata', 'Unable to download channel metadata',
 408             query={'szBjId': broadcaster_id}, fatal=False), {dict}) or {}
 409
 410         return {
 411             'id': broadcast_no,
 412             'title': channel_info.get('TITLE') or station_info.get('station_title'),
 413             'uploader': channel_info.get('BJNICK') or station_info.get('station_name'),
 414             'uploader_id': broadcaster_id,
 415             'timestamp': unified_timestamp(station_info.get('broad_start')),
 416             'formats': formats,
 417             'is_live': True,
 418             'http_headers': {'Referer': url},
 419         }
 420
 421
 422 class AfreecaTVUserIE(InfoExtractor):
 423     IE_NAME = 'afreecatv:user'
 424     _VALID_URL = r'https?://bj\.afreeca(?:tv)?\.com/(?P<id>[^/]+)/vods/?(?P<slug_type>[^/]+)?'
 425     _TESTS = [{
 426         'url': 'https://bj.afreecatv.com/ryuryu24/vods/review',
 427         'info_dict': {
 428             '_type': 'playlist',
 429             'id': 'ryuryu24',
 430             'title': 'ryuryu24 - review',
 431         },
 432         'playlist_count': 218,
 433     }, {
 434         'url': 'https://bj.afreecatv.com/parang1995/vods/highlight',
 435         'info_dict': {
 436             '_type': 'playlist',
 437             'id': 'parang1995',
 438             'title': 'parang1995 - highlight',
 439         },
 440         'playlist_count': 997,
 441     }, {
 442         'url': 'https://bj.afreecatv.com/ryuryu24/vods',
 443         'info_dict': {
 444             '_type': 'playlist',
 445             'id': 'ryuryu24',
 446             'title': 'ryuryu24 - all',
 447         },
 448         'playlist_count': 221,
 449     }, {
 450         'url': 'https://bj.afreecatv.com/ryuryu24/vods/balloonclip',
 451         'info_dict': {
 452             '_type': 'playlist',
 453             'id': 'ryuryu24',
 454             'title': 'ryuryu24 - balloonclip',
 455         },
 456         'playlist_count': 0,
 457     }]
 458     _PER_PAGE = 60
 459
 460     def _fetch_page(self, user_id, user_type, page):
 461         page += 1
 462         info = self._download_json(f'https://bjapi.afreecatv.com/api/{user_id}/vods/{user_type}', user_id,
 463                                    query={'page': page, 'per_page': self._PER_PAGE, 'orderby': 'reg_date'},
 464                                    note=f'Downloading {user_type} video page {page}')
 465         for item in info['data']:
 466             yield self.url_result(
 467                 f'https://vod.afreecatv.com/player/{item["title_no"]}/', AfreecaTVIE, item['title_no'])
 468
 469     def _real_extract(self, url):
 470         user_id, user_type = self._match_valid_url(url).group('id', 'slug_type')
 471         user_type = user_type or 'all'
 472         entries = OnDemandPagedList(functools.partial(self._fetch_page, user_id, user_type), self._PER_PAGE)
 473         return self.playlist_result(entries, user_id, f'{user_id} - {user_type}')