yt_dlp/extractor/afreecatv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import functools
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     ExtractorError,
  10     OnDemandPagedList,
  11     date_from_str,
  12     determine_ext,
  13     int_or_none,
  14     qualities,
  15     traverse_obj,
  16     unified_strdate,
  17     unified_timestamp,
  18     update_url_query,
  19     url_or_none,
  20     urlencode_postdata,
  21     xpath_text,
  22 )
  23
  24
  25 class AfreecaTVIE(InfoExtractor):
  26     IE_NAME = 'afreecatv'
  27     IE_DESC = 'afreecatv.com'
  28     _VALID_URL = r'''(?x)
  29                     https?://
  30                         (?:
  31                             (?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
  32                             (?:
  33                                 /app/(?:index|read_ucc_bbs)\.cgi|
  34                                 /player/[Pp]layer\.(?:swf|html)
  35                             )\?.*?\bnTitleNo=|
  36                             vod\.afreecatv\.com/(PLAYER/STATION|player)/
  37                         )
  38                         (?P<id>\d+)
  39                     '''
  40     _NETRC_MACHINE = 'afreecatv'
  41     _TESTS = [{
  42         'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
  43         'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
  44         'info_dict': {
  45             'id': '36164052',
  46             'ext': 'mp4',
  47             'title': '데일리 에이프릴 요정들의 시상식!',
  48             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  49             'uploader': 'dailyapril',
  50             'uploader_id': 'dailyapril',
  51             'upload_date': '20160503',
  52         },
  53         'skip': 'Video is gone',
  54     }, {
  55         'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
  56         'info_dict': {
  57             'id': '36153164',
  58             'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  59             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  60             'uploader': 'dailyapril',
  61             'uploader_id': 'dailyapril',
  62         },
  63         'playlist_count': 2,
  64         'playlist': [{
  65             'md5': 'd8b7c174568da61d774ef0203159bf97',
  66             'info_dict': {
  67                 'id': '36153164_1',
  68                 'ext': 'mp4',
  69                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  70                 'upload_date': '20160502',
  71             },
  72         }, {
  73             'md5': '58f2ce7f6044e34439ab2d50612ab02b',
  74             'info_dict': {
  75                 'id': '36153164_2',
  76                 'ext': 'mp4',
  77                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  78                 'upload_date': '20160502',
  79             },
  80         }],
  81         'skip': 'Video is gone',
  82     }, {
  83         'url': 'http://vod.afreecatv.com/PLAYER/STATION/18650793',
  84         'info_dict': {
  85             'id': '18650793',
  86             'ext': 'mp4',
  87             'title': '오늘은 다르다! 쏘님의 우월한 위아래~ 댄스리액션!',
  88             'thumbnail': r're:^https?://.*\.jpg$',
  89             'uploader': '윈아디',
  90             'uploader_id': 'badkids',
  91             'duration': 107,
  92         },
  93         'params': {
  94             'skip_download': True,
  95         },
  96     }, {
  97         'url': 'http://vod.afreecatv.com/PLAYER/STATION/10481652',
  98         'info_dict': {
  99             'id': '10481652',
 100             'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
 101             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 102             'uploader': 'dailyapril',
 103             'uploader_id': 'dailyapril',
 104             'duration': 6492,
 105         },
 106         'playlist_count': 2,
 107         'playlist': [{
 108             'md5': 'd8b7c174568da61d774ef0203159bf97',
 109             'info_dict': {
 110                 'id': '20160502_c4c62b9d_174361386_1',
 111                 'ext': 'mp4',
 112                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 1)",
 113                 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 114                 'uploader': 'dailyapril',
 115                 'uploader_id': 'dailyapril',
 116                 'upload_date': '20160502',
 117                 'duration': 3601,
 118             },
 119         }, {
 120             'md5': '58f2ce7f6044e34439ab2d50612ab02b',
 121             'info_dict': {
 122                 'id': '20160502_39e739bb_174361386_2',
 123                 'ext': 'mp4',
 124                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 2)",
 125                 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 126                 'uploader': 'dailyapril',
 127                 'uploader_id': 'dailyapril',
 128                 'upload_date': '20160502',
 129                 'duration': 2891,
 130             },
 131         }],
 132         'params': {
 133             'skip_download': True,
 134         },
 135     }, {
 136         # non standard key
 137         'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605',
 138         'info_dict': {
 139             'id': '20170411_BE689A0E_190960999_1_2_h',
 140             'ext': 'mp4',
 141             'title': '혼자사는여자집',
 142             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 143             'uploader': '♥이슬이',
 144             'uploader_id': 'dasl8121',
 145             'upload_date': '20170411',
 146             'duration': 213,
 147         },
 148         'params': {
 149             'skip_download': True,
 150         },
 151     }, {
 152         # PARTIAL_ADULT
 153         'url': 'http://vod.afreecatv.com/PLAYER/STATION/32028439',
 154         'info_dict': {
 155             'id': '20180327_27901457_202289533_1',
 156             'ext': 'mp4',
 157             'title': '[생]빨개요♥ (part 1)',
 158             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 159             'uploader': '[SA]서아',
 160             'uploader_id': 'bjdyrksu',
 161             'upload_date': '20180327',
 162             'duration': 3601,
 163         },
 164         'params': {
 165             'skip_download': True,
 166         },
 167         'expected_warnings': ['adult content'],
 168     }, {
 169         'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
 170         'only_matching': True,
 171     }, {
 172         'url': 'http://vod.afreecatv.com/PLAYER/STATION/15055030',
 173         'only_matching': True,
 174     }, {
 175         'url': 'http://vod.afreecatv.com/player/15055030',
 176         'only_matching': True,
 177     }]
 178
 179     @staticmethod
 180     def parse_video_key(key):
 181         video_key = {}
 182         m = re.match(r'^(?P<upload_date>\d{8})_\w+_(?P<part>\d+)$', key)
 183         if m:
 184             video_key['upload_date'] = m.group('upload_date')
 185             video_key['part'] = int(m.group('part'))
 186         return video_key
 187
 188     def _perform_login(self, username, password):
 189         login_form = {
 190             'szWork': 'login',
 191             'szType': 'json',
 192             'szUid': username,
 193             'szPassword': password,
 194             'isSaveId': 'false',
 195             'szScriptVar': 'oLoginRet',
 196             'szAction': '',
 197         }
 198
 199         response = self._download_json(
 200             'https://login.afreecatv.com/app/LoginAction.php', None,
 201             'Logging in', data=urlencode_postdata(login_form))
 202
 203         _ERRORS = {
 204             -4: 'Your account has been suspended due to a violation of our terms and policies.',
 205             -5: 'https://member.afreecatv.com/app/user_delete_progress.php',
 206             -6: 'https://login.afreecatv.com/membership/changeMember.php',
 207             -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.",
 208             -9: 'https://member.afreecatv.com/app/pop_login_block.php',
 209             -11: 'https://login.afreecatv.com/afreeca/second_login.php',
 210             -12: 'https://member.afreecatv.com/app/user_security.php',
 211             0: 'The username does not exist or you have entered the wrong password.',
 212             -1: 'The username does not exist or you have entered the wrong password.',
 213             -3: 'You have entered your username/password incorrectly.',
 214             -7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.',
 215             -10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.',
 216             -32008: 'You have failed to log in. Please contact our Help Center.',
 217         }
 218
 219         result = int_or_none(response.get('RESULT'))
 220         if result != 1:
 221             error = _ERRORS.get(result, 'You have failed to log in.')
 222             raise ExtractorError(
 223                 'Unable to login: %s said: %s' % (self.IE_NAME, error),
 224                 expected=True)
 225
 226     def _real_extract(self, url):
 227         video_id = self._match_id(url)
 228
 229         webpage = self._download_webpage(url, video_id)
 230
 231         if re.search(r'alert\(["\']This video has been deleted', webpage):
 232             raise ExtractorError(
 233                 'Video %s has been deleted' % video_id, expected=True)
 234
 235         station_id = self._search_regex(
 236             r'nStationNo\s*=\s*(\d+)', webpage, 'station')
 237         bbs_id = self._search_regex(
 238             r'nBbsNo\s*=\s*(\d+)', webpage, 'bbs')
 239         video_id = self._search_regex(
 240             r'nTitleNo\s*=\s*(\d+)', webpage, 'title', default=video_id)
 241
 242         partial_view = False
 243         adult_view = False
 244         for _ in range(2):
 245             query = {
 246                 'nTitleNo': video_id,
 247                 'nStationNo': station_id,
 248                 'nBbsNo': bbs_id,
 249             }
 250             if partial_view:
 251                 query['partialView'] = 'SKIP_ADULT'
 252             if adult_view:
 253                 query['adultView'] = 'ADULT_VIEW'
 254             video_xml = self._download_xml(
 255                 'http://afbbs.afreecatv.com:8080/api/video/get_video_info.php',
 256                 video_id, 'Downloading video info XML%s'
 257                 % (' (skipping adult)' if partial_view else ''),
 258                 video_id, headers={
 259                     'Referer': url,
 260                 }, query=query)
 261
 262             flag = xpath_text(video_xml, './track/flag', 'flag', default=None)
 263             if flag and flag == 'SUCCEED':
 264                 break
 265             if flag == 'PARTIAL_ADULT':
 266                 self.report_warning(
 267                     'In accordance with local laws and regulations, underage users are restricted from watching adult content. '
 268                     'Only content suitable for all ages will be downloaded. '
 269                     'Provide account credentials if you wish to download restricted content.')
 270                 partial_view = True
 271                 continue
 272             elif flag == 'ADULT':
 273                 if not adult_view:
 274                     adult_view = True
 275                     continue
 276                 error = 'Only users older than 19 are able to watch this video. Provide account credentials to download this content.'
 277             else:
 278                 error = flag
 279             raise ExtractorError(
 280                 '%s said: %s' % (self.IE_NAME, error), expected=True)
 281         else:
 282             raise ExtractorError('Unable to download video info')
 283
 284         video_element = video_xml.findall('./track/video')[-1]
 285         if video_element is None or video_element.text is None:
 286             raise ExtractorError(
 287                 'Video %s does not exist' % video_id, expected=True)
 288
 289         video_url = video_element.text.strip()
 290
 291         title = xpath_text(video_xml, './track/title', 'title', fatal=True)
 292
 293         uploader = xpath_text(video_xml, './track/nickname', 'uploader')
 294         uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
 295         duration = int_or_none(xpath_text(
 296             video_xml, './track/duration', 'duration'))
 297         thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
 298
 299         common_entry = {
 300             'uploader': uploader,
 301             'uploader_id': uploader_id,
 302             'thumbnail': thumbnail,
 303         }
 304
 305         info = common_entry.copy()
 306         info.update({
 307             'id': video_id,
 308             'title': title,
 309             'duration': duration,
 310         })
 311
 312         if not video_url:
 313             entries = []
 314             file_elements = video_element.findall('./file')
 315             one = len(file_elements) == 1
 316             for file_num, file_element in enumerate(file_elements, start=1):
 317                 file_url = url_or_none(file_element.text)
 318                 if not file_url:
 319                     continue
 320                 key = file_element.get('key', '')
 321                 upload_date = unified_strdate(self._search_regex(
 322                     r'^(\d{8})_', key, 'upload date', default=None))
 323                 if upload_date is not None:
 324                     # sometimes the upload date isn't included in the file name
 325                     # instead, another random ID is, which may parse as a valid
 326                     # date but be wildly out of a reasonable range
 327                     parsed_date = date_from_str(upload_date)
 328                     if parsed_date.year < 2000 or parsed_date.year >= 2100:
 329                         upload_date = None
 330                 file_duration = int_or_none(file_element.get('duration'))
 331                 format_id = key if key else '%s_%s' % (video_id, file_num)
 332                 if determine_ext(file_url) == 'm3u8':
 333                     formats = self._extract_m3u8_formats(
 334                         file_url, video_id, 'mp4', entry_protocol='m3u8_native',
 335                         m3u8_id='hls',
 336                         note='Downloading part %d m3u8 information' % file_num)
 337                 else:
 338                     formats = [{
 339                         'url': file_url,
 340                         'format_id': 'http',
 341                     }]
 342                 if not formats and not self.get_param('ignore_no_formats'):
 343                     continue
 344                 self._sort_formats(formats)
 345                 file_info = common_entry.copy()
 346                 file_info.update({
 347                     'id': format_id,
 348                     'title': title if one else '%s (part %d)' % (title, file_num),
 349                     'upload_date': upload_date,
 350                     'duration': file_duration,
 351                     'formats': formats,
 352                 })
 353                 entries.append(file_info)
 354             entries_info = info.copy()
 355             entries_info.update({
 356                 '_type': 'multi_video',
 357                 'entries': entries,
 358             })
 359             return entries_info
 360
 361         info = {
 362             'id': video_id,
 363             'title': title,
 364             'uploader': uploader,
 365             'uploader_id': uploader_id,
 366             'duration': duration,
 367             'thumbnail': thumbnail,
 368         }
 369
 370         if determine_ext(video_url) == 'm3u8':
 371             info['formats'] = self._extract_m3u8_formats(
 372                 video_url, video_id, 'mp4', entry_protocol='m3u8_native',
 373                 m3u8_id='hls')
 374         else:
 375             app, playpath = video_url.split('mp4:')
 376             info.update({
 377                 'url': app,
 378                 'ext': 'flv',
 379                 'play_path': 'mp4:' + playpath,
 380                 'rtmp_live': True,  # downloading won't end without this
 381             })
 382
 383         return info
 384
 385
 386 class AfreecaTVLiveIE(AfreecaTVIE):
 387
 388     IE_NAME = 'afreecatv:live'
 389     _VALID_URL = r'https?://play\.afreeca(?:tv)?\.com/(?P<id>[^/]+)(?:/(?P<bno>\d+))?'
 390     _TESTS = [{
 391         'url': 'https://play.afreecatv.com/pyh3646/237852185',
 392         'info_dict': {
 393             'id': '237852185',
 394             'ext': 'mp4',
 395             'title': '【 우루과이 오늘은 무슨일이? 】',
 396             'uploader': '박진우[JINU]',
 397             'uploader_id': 'pyh3646',
 398             'timestamp': 1640661495,
 399             'is_live': True,
 400         },
 401         'skip': 'Livestream has ended',
 402     }, {
 403         'url': 'http://play.afreeca.com/pyh3646/237852185',
 404         'only_matching': True,
 405     }, {
 406         'url': 'http://play.afreeca.com/pyh3646',
 407         'only_matching': True,
 408     }]
 409
 410     _LIVE_API_URL = 'https://live.afreecatv.com/afreeca/player_live_api.php'
 411
 412     _QUALITIES = ('sd', 'hd', 'hd2k', 'original')
 413
 414     def _real_extract(self, url):
 415         broadcaster_id, broadcast_no = self._match_valid_url(url).group('id', 'bno')
 416         password = self.get_param('videopassword')
 417
 418         info = self._download_json(self._LIVE_API_URL, broadcaster_id, fatal=False,
 419                                    data=urlencode_postdata({'bid': broadcaster_id})) or {}
 420         channel_info = info.get('CHANNEL') or {}
 421         broadcaster_id = channel_info.get('BJID') or broadcaster_id
 422         broadcast_no = channel_info.get('BNO') or broadcast_no
 423         password_protected = channel_info.get('BPWD')
 424         if not broadcast_no:
 425             raise ExtractorError(f'Unable to extract broadcast number ({broadcaster_id} may not be live)', expected=True)
 426         if password_protected == 'Y' and password is None:
 427             raise ExtractorError(
 428                 'This livestream is protected by a password, use the --video-password option',
 429                 expected=True)
 430
 431         formats = []
 432         quality_key = qualities(self._QUALITIES)
 433         for quality_str in self._QUALITIES:
 434             params = {
 435                 'bno': broadcast_no,
 436                 'stream_type': 'common',
 437                 'type': 'aid',
 438                 'quality': quality_str,
 439             }
 440             if password is not None:
 441                 params['pwd'] = password
 442             aid_response = self._download_json(
 443                 self._LIVE_API_URL, broadcast_no, fatal=False,
 444                 data=urlencode_postdata(params),
 445                 note=f'Downloading access token for {quality_str} stream',
 446                 errnote=f'Unable to download access token for {quality_str} stream')
 447             aid = traverse_obj(aid_response, ('CHANNEL', 'AID'))
 448             if not aid:
 449                 continue
 450
 451             stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.afreecatv.com'
 452             stream_info = self._download_json(
 453                 f'{stream_base_url}/broad_stream_assign.html', broadcast_no, fatal=False,
 454                 query={
 455                     'return_type': channel_info.get('CDN', 'gcp_cdn'),
 456                     'broad_key': f'{broadcast_no}-common-{quality_str}-hls',
 457                 },
 458                 note=f'Downloading metadata for {quality_str} stream',
 459                 errnote=f'Unable to download metadata for {quality_str} stream') or {}
 460
 461             if stream_info.get('view_url'):
 462                 formats.append({
 463                     'format_id': quality_str,
 464                     'url': update_url_query(stream_info['view_url'], {'aid': aid}),
 465                     'ext': 'mp4',
 466                     'protocol': 'm3u8',
 467                     'quality': quality_key(quality_str),
 468                 })
 469
 470         self._sort_formats(formats)
 471
 472         station_info = self._download_json(
 473             'https://st.afreecatv.com/api/get_station_status.php', broadcast_no,
 474             query={'szBjId': broadcaster_id}, fatal=False,
 475             note='Downloading channel metadata', errnote='Unable to download channel metadata') or {}
 476
 477         return {
 478             'id': broadcast_no,
 479             'title': channel_info.get('TITLE') or station_info.get('station_title'),
 480             'uploader': channel_info.get('BJNICK') or station_info.get('station_name'),
 481             'uploader_id': broadcaster_id,
 482             'timestamp': unified_timestamp(station_info.get('broad_start')),
 483             'formats': formats,
 484             'is_live': True,
 485         }
 486
 487
 488 class AfreecaTVUserIE(InfoExtractor):
 489     IE_NAME = 'afreecatv:user'
 490     _VALID_URL = r'https?://bj\.afreeca(?:tv)?\.com/(?P<id>[^/]+)/vods/?(?P<slug_type>[^/]+)?'
 491     _TESTS = [{
 492         'url': 'https://bj.afreecatv.com/ryuryu24/vods/review',
 493         'info_dict': {
 494             '_type': 'playlist',
 495             'id': 'ryuryu24',
 496             'title': 'ryuryu24 - review',
 497         },
 498         'playlist_count': 218,
 499     }, {
 500         'url': 'https://bj.afreecatv.com/parang1995/vods/highlight',
 501         'info_dict': {
 502             '_type': 'playlist',
 503             'id': 'parang1995',
 504             'title': 'parang1995 - highlight',
 505         },
 506         'playlist_count': 997,
 507     }, {
 508         'url': 'https://bj.afreecatv.com/ryuryu24/vods',
 509         'info_dict': {
 510             '_type': 'playlist',
 511             'id': 'ryuryu24',
 512             'title': 'ryuryu24 - all',
 513         },
 514         'playlist_count': 221,
 515     }, {
 516         'url': 'https://bj.afreecatv.com/ryuryu24/vods/balloonclip',
 517         'info_dict': {
 518             '_type': 'playlist',
 519             'id': 'ryuryu24',
 520             'title': 'ryuryu24 - balloonclip',
 521         },
 522         'playlist_count': 0,
 523     }]
 524     _PER_PAGE = 60
 525
 526     def _fetch_page(self, user_id, user_type, page):
 527         page += 1
 528         info = self._download_json(f'https://bjapi.afreecatv.com/api/{user_id}/vods/{user_type}', user_id,
 529                                    query={'page': page, 'per_page': self._PER_PAGE, 'orderby': 'reg_date'},
 530                                    note=f'Downloading {user_type} video page {page}')
 531         for item in info['data']:
 532             yield self.url_result(
 533                 f'https://vod.afreecatv.com/player/{item["title_no"]}/', AfreecaTVIE, item['title_no'])
 534
 535     def _real_extract(self, url):
 536         user_id, user_type = self._match_valid_url(url).group('id', 'slug_type')
 537         user_type = user_type or 'all'
 538         entries = OnDemandPagedList(functools.partial(self._fetch_page, user_id, user_type), self._PER_PAGE)
 539         return self.playlist_result(entries, user_id, f'{user_id} - {user_type}')