yt_dlp/extractor/afreecatv.py

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