Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/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     determine_ext,
  10     ExtractorError,
  11     int_or_none,
  12     urlencode_postdata,
  13     xpath_text,
  14 )
  15
  16
  17 class AfreecaTVIE(InfoExtractor):
  18     IE_NAME = 'afreecatv'
  19     IE_DESC = 'afreecatv.com'
  20     _VALID_URL = r'''(?x)
  21                     https?://
  22                         (?:
  23                             (?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
  24                             (?:
  25                                 /app/(?:index|read_ucc_bbs)\.cgi|
  26                                 /player/[Pp]layer\.(?:swf|html)
  27                             )\?.*?\bnTitleNo=|
  28                             vod\.afreecatv\.com/PLAYER/STATION/
  29                         )
  30                         (?P<id>\d+)
  31                     '''
  32     _NETRC_MACHINE = 'afreecatv'
  33     _TESTS = [{
  34         'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
  35         'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
  36         'info_dict': {
  37             'id': '36164052',
  38             'ext': 'mp4',
  39             'title': '데일리 에이프릴 요정들의 시상식!',
  40             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  41             'uploader': 'dailyapril',
  42             'uploader_id': 'dailyapril',
  43             'upload_date': '20160503',
  44         },
  45         'skip': 'Video is gone',
  46     }, {
  47         'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
  48         'info_dict': {
  49             'id': '36153164',
  50             'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  51             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  52             'uploader': 'dailyapril',
  53             'uploader_id': 'dailyapril',
  54         },
  55         'playlist_count': 2,
  56         'playlist': [{
  57             'md5': 'd8b7c174568da61d774ef0203159bf97',
  58             'info_dict': {
  59                 'id': '36153164_1',
  60                 'ext': 'mp4',
  61                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  62                 'upload_date': '20160502',
  63             },
  64         }, {
  65             'md5': '58f2ce7f6044e34439ab2d50612ab02b',
  66             'info_dict': {
  67                 'id': '36153164_2',
  68                 'ext': 'mp4',
  69                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  70                 'upload_date': '20160502',
  71             },
  72         }],
  73         'skip': 'Video is gone',
  74     }, {
  75         'url': 'http://vod.afreecatv.com/PLAYER/STATION/18650793',
  76         'info_dict': {
  77             'id': '18650793',
  78             'ext': 'mp4',
  79             'title': '오늘은 다르다! 쏘님의 우월한 위아래~ 댄스리액션!',
  80             'thumbnail': r're:^https?://.*\.jpg$',
  81             'uploader': '윈아디',
  82             'uploader_id': 'badkids',
  83             'duration': 107,
  84         },
  85         'params': {
  86             'skip_download': True,
  87         },
  88     }, {
  89         'url': 'http://vod.afreecatv.com/PLAYER/STATION/10481652',
  90         'info_dict': {
  91             'id': '10481652',
  92             'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  93             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  94             'uploader': 'dailyapril',
  95             'uploader_id': 'dailyapril',
  96             'duration': 6492,
  97         },
  98         'playlist_count': 2,
  99         'playlist': [{
 100             'md5': 'd8b7c174568da61d774ef0203159bf97',
 101             'info_dict': {
 102                 'id': '20160502_c4c62b9d_174361386_1',
 103                 'ext': 'mp4',
 104                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 1)",
 105                 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 106                 'uploader': 'dailyapril',
 107                 'uploader_id': 'dailyapril',
 108                 'upload_date': '20160502',
 109                 'duration': 3601,
 110             },
 111         }, {
 112             'md5': '58f2ce7f6044e34439ab2d50612ab02b',
 113             'info_dict': {
 114                 'id': '20160502_39e739bb_174361386_2',
 115                 'ext': 'mp4',
 116                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 2)",
 117                 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 118                 'uploader': 'dailyapril',
 119                 'uploader_id': 'dailyapril',
 120                 'upload_date': '20160502',
 121                 'duration': 2891,
 122             },
 123         }],
 124         'params': {
 125             'skip_download': True,
 126         },
 127     }, {
 128         # non standard key
 129         'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605',
 130         'info_dict': {
 131             'id': '20170411_BE689A0E_190960999_1_2_h',
 132             'ext': 'mp4',
 133             'title': '혼자사는여자집',
 134             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 135             'uploader': '♥이슬이',
 136             'uploader_id': 'dasl8121',
 137             'upload_date': '20170411',
 138             'duration': 213,
 139         },
 140         'params': {
 141             'skip_download': True,
 142         },
 143     }, {
 144         # PARTIAL_ADULT
 145         'url': 'http://vod.afreecatv.com/PLAYER/STATION/32028439',
 146         'info_dict': {
 147             'id': '20180327_27901457_202289533_1',
 148             'ext': 'mp4',
 149             'title': '[생]빨개요♥ (part 1)',
 150             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 151             'uploader': '[SA]서아',
 152             'uploader_id': 'bjdyrksu',
 153             'upload_date': '20180327',
 154             'duration': 3601,
 155         },
 156         'params': {
 157             'skip_download': True,
 158         },
 159         'expected_warnings': ['adult content'],
 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': 'http://vod.afreecatv.com/PLAYER/STATION/15055030',
 165         'only_matching': True,
 166     }]
 167
 168     @staticmethod
 169     def parse_video_key(key):
 170         video_key = {}
 171         m = re.match(r'^(?P<upload_date>\d{8})_\w+_(?P<part>\d+)$', key)
 172         if m:
 173             video_key['upload_date'] = m.group('upload_date')
 174             video_key['part'] = int(m.group('part'))
 175         return video_key
 176
 177     def _real_initialize(self):
 178         self._login()
 179
 180     def _login(self):
 181         username, password = self._get_login_info()
 182         if username is None:
 183             return
 184
 185         login_form = {
 186             'szWork': 'login',
 187             'szType': 'json',
 188             'szUid': username,
 189             'szPassword': password,
 190             'isSaveId': 'false',
 191             'szScriptVar': 'oLoginRet',
 192             'szAction': '',
 193         }
 194
 195         response = self._download_json(
 196             'https://login.afreecatv.com/app/LoginAction.php', None,
 197             'Logging in', data=urlencode_postdata(login_form))
 198
 199         _ERRORS = {
 200             -4: 'Your account has been suspended due to a violation of our terms and policies.',
 201             -5: 'https://member.afreecatv.com/app/user_delete_progress.php',
 202             -6: 'https://login.afreecatv.com/membership/changeMember.php',
 203             -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.",
 204             -9: 'https://member.afreecatv.com/app/pop_login_block.php',
 205             -11: 'https://login.afreecatv.com/afreeca/second_login.php',
 206             -12: 'https://member.afreecatv.com/app/user_security.php',
 207             0: 'The username does not exist or you have entered the wrong password.',
 208             -1: 'The username does not exist or you have entered the wrong password.',
 209             -3: 'You have entered your username/password incorrectly.',
 210             -7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.',
 211             -10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.',
 212             -32008: 'You have failed to log in. Please contact our Help Center.',
 213         }
 214
 215         result = int_or_none(response.get('RESULT'))
 216         if result != 1:
 217             error = _ERRORS.get(result, 'You have failed to log in.')
 218             raise ExtractorError(
 219                 'Unable to login: %s said: %s' % (self.IE_NAME, error),
 220                 expected=True)
 221
 222     def _real_extract(self, url):
 223         video_id = self._match_id(url)
 224
 225         webpage = self._download_webpage(url, video_id)
 226
 227         if re.search(r'alert\(["\']This video has been deleted', webpage):
 228             raise ExtractorError(
 229                 'Video %s has been deleted' % video_id, expected=True)
 230
 231         station_id = self._search_regex(
 232             r'nStationNo\s*=\s*(\d+)', webpage, 'station')
 233         bbs_id = self._search_regex(
 234             r'nBbsNo\s*=\s*(\d+)', webpage, 'bbs')
 235         video_id = self._search_regex(
 236             r'nTitleNo\s*=\s*(\d+)', webpage, 'title', default=video_id)
 237
 238         partial_view = False
 239         for _ in range(2):
 240             query = {
 241                 'nTitleNo': video_id,
 242                 'nStationNo': station_id,
 243                 'nBbsNo': bbs_id,
 244             }
 245             if partial_view:
 246                 query['partialView'] = 'SKIP_ADULT'
 247             video_xml = self._download_xml(
 248                 'http://afbbs.afreecatv.com:8080/api/video/get_video_info.php',
 249                 video_id, 'Downloading video info XML%s'
 250                 % (' (skipping adult)' if partial_view else ''),
 251                 video_id, headers={
 252                     'Referer': url,
 253                 }, query=query)
 254
 255             flag = xpath_text(video_xml, './track/flag', 'flag', default=None)
 256             if flag and flag == 'SUCCEED':
 257                 break
 258             if flag == 'PARTIAL_ADULT':
 259                 self._downloader.report_warning(
 260                     'In accordance with local laws and regulations, underage users are restricted from watching adult content. '
 261                     'Only content suitable for all ages will be downloaded. '
 262                     'Provide account credentials if you wish to download restricted content.')
 263                 partial_view = True
 264                 continue
 265             elif flag == 'ADULT':
 266                 error = 'Only users older than 19 are able to watch this video. Provide account credentials to download this content.'
 267             else:
 268                 error = flag
 269             raise ExtractorError(
 270                 '%s said: %s' % (self.IE_NAME, error), expected=True)
 271         else:
 272             raise ExtractorError('Unable to download video info')
 273
 274         video_element = video_xml.findall(compat_xpath('./track/video'))[-1]
 275         if video_element is None or video_element.text is None:
 276             raise ExtractorError(
 277                 'Video %s video does not exist' % video_id, expected=True)
 278
 279         video_url = video_element.text.strip()
 280
 281         title = xpath_text(video_xml, './track/title', 'title', fatal=True)
 282
 283         uploader = xpath_text(video_xml, './track/nickname', 'uploader')
 284         uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
 285         duration = int_or_none(xpath_text(
 286             video_xml, './track/duration', 'duration'))
 287         thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
 288
 289         common_entry = {
 290             'uploader': uploader,
 291             'uploader_id': uploader_id,
 292             'thumbnail': thumbnail,
 293         }
 294
 295         info = common_entry.copy()
 296         info.update({
 297             'id': video_id,
 298             'title': title,
 299             'duration': duration,
 300         })
 301
 302         if not video_url:
 303             entries = []
 304             file_elements = video_element.findall(compat_xpath('./file'))
 305             one = len(file_elements) == 1
 306             for file_num, file_element in enumerate(file_elements, start=1):
 307                 file_url = file_element.text
 308                 if not file_url:
 309                     continue
 310                 key = file_element.get('key', '')
 311                 upload_date = self._search_regex(
 312                     r'^(\d{8})_', key, 'upload date', default=None)
 313                 file_duration = int_or_none(file_element.get('duration'))
 314                 format_id = key if key else '%s_%s' % (video_id, file_num)
 315                 if determine_ext(file_url) == 'm3u8':
 316                     formats = self._extract_m3u8_formats(
 317                         file_url, video_id, 'mp4', entry_protocol='m3u8_native',
 318                         m3u8_id='hls',
 319                         note='Downloading part %d m3u8 information' % file_num)
 320                 else:
 321                     formats = [{
 322                         'url': file_url,
 323                         'format_id': 'http',
 324                     }]
 325                 if not formats:
 326                     continue
 327                 self._sort_formats(formats)
 328                 file_info = common_entry.copy()
 329                 file_info.update({
 330                     'id': format_id,
 331                     'title': title if one else '%s (part %d)' % (title, file_num),
 332                     'upload_date': upload_date,
 333                     'duration': file_duration,
 334                     'formats': formats,
 335                 })
 336                 entries.append(file_info)
 337             entries_info = info.copy()
 338             entries_info.update({
 339                 '_type': 'multi_video',
 340                 'entries': entries,
 341             })
 342             return entries_info
 343
 344         info = {
 345             'id': video_id,
 346             'title': title,
 347             'uploader': uploader,
 348             'uploader_id': uploader_id,
 349             'duration': duration,
 350             'thumbnail': thumbnail,
 351         }
 352
 353         if determine_ext(video_url) == 'm3u8':
 354             info['formats'] = self._extract_m3u8_formats(
 355                 video_url, video_id, 'mp4', entry_protocol='m3u8_native',
 356                 m3u8_id='hls')
 357         else:
 358             app, playpath = video_url.split('mp4:')
 359             info.update({
 360                 'url': app,
 361                 'ext': 'flv',
 362                 'play_path': 'mp4:' + playpath,
 363                 'rtmp_live': True,  # downloading won't end without this
 364             })
 365
 366         return info