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     url_or_none,
  13     urlencode_postdata,
  14     xpath_text,
  15 )
  16
  17
  18 class AfreecaTVIE(InfoExtractor):
  19     IE_NAME = 'afreecatv'
  20     IE_DESC = 'afreecatv.com'
  21     _VALID_URL = r'''(?x)
  22                     https?://
  23                         (?:
  24                             (?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
  25                             (?:
  26                                 /app/(?:index|read_ucc_bbs)\.cgi|
  27                                 /player/[Pp]layer\.(?:swf|html)
  28                             )\?.*?\bnTitleNo=|
  29                             vod\.afreecatv\.com/PLAYER/STATION/
  30                         )
  31                         (?P<id>\d+)
  32                     '''
  33     _NETRC_MACHINE = 'afreecatv'
  34     _TESTS = [{
  35         'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
  36         'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
  37         'info_dict': {
  38             'id': '36164052',
  39             'ext': 'mp4',
  40             'title': '데일리 에이프릴 요정들의 시상식!',
  41             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  42             'uploader': 'dailyapril',
  43             'uploader_id': 'dailyapril',
  44             'upload_date': '20160503',
  45         },
  46         'skip': 'Video is gone',
  47     }, {
  48         'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
  49         'info_dict': {
  50             'id': '36153164',
  51             'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  52             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  53             'uploader': 'dailyapril',
  54             'uploader_id': 'dailyapril',
  55         },
  56         'playlist_count': 2,
  57         'playlist': [{
  58             'md5': 'd8b7c174568da61d774ef0203159bf97',
  59             'info_dict': {
  60                 'id': '36153164_1',
  61                 'ext': 'mp4',
  62                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  63                 'upload_date': '20160502',
  64             },
  65         }, {
  66             'md5': '58f2ce7f6044e34439ab2d50612ab02b',
  67             'info_dict': {
  68                 'id': '36153164_2',
  69                 'ext': 'mp4',
  70                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  71                 'upload_date': '20160502',
  72             },
  73         }],
  74         'skip': 'Video is gone',
  75     }, {
  76         'url': 'http://vod.afreecatv.com/PLAYER/STATION/18650793',
  77         'info_dict': {
  78             'id': '18650793',
  79             'ext': 'mp4',
  80             'title': '오늘은 다르다! 쏘님의 우월한 위아래~ 댄스리액션!',
  81             'thumbnail': r're:^https?://.*\.jpg$',
  82             'uploader': '윈아디',
  83             'uploader_id': 'badkids',
  84             'duration': 107,
  85         },
  86         'params': {
  87             'skip_download': True,
  88         },
  89     }, {
  90         'url': 'http://vod.afreecatv.com/PLAYER/STATION/10481652',
  91         'info_dict': {
  92             'id': '10481652',
  93             'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  94             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  95             'uploader': 'dailyapril',
  96             'uploader_id': 'dailyapril',
  97             'duration': 6492,
  98         },
  99         'playlist_count': 2,
 100         'playlist': [{
 101             'md5': 'd8b7c174568da61d774ef0203159bf97',
 102             'info_dict': {
 103                 'id': '20160502_c4c62b9d_174361386_1',
 104                 'ext': 'mp4',
 105                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 1)",
 106                 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 107                 'uploader': 'dailyapril',
 108                 'uploader_id': 'dailyapril',
 109                 'upload_date': '20160502',
 110                 'duration': 3601,
 111             },
 112         }, {
 113             'md5': '58f2ce7f6044e34439ab2d50612ab02b',
 114             'info_dict': {
 115                 'id': '20160502_39e739bb_174361386_2',
 116                 'ext': 'mp4',
 117                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 2)",
 118                 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 119                 'uploader': 'dailyapril',
 120                 'uploader_id': 'dailyapril',
 121                 'upload_date': '20160502',
 122                 'duration': 2891,
 123             },
 124         }],
 125         'params': {
 126             'skip_download': True,
 127         },
 128     }, {
 129         # non standard key
 130         'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605',
 131         'info_dict': {
 132             'id': '20170411_BE689A0E_190960999_1_2_h',
 133             'ext': 'mp4',
 134             'title': '혼자사는여자집',
 135             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 136             'uploader': '♥이슬이',
 137             'uploader_id': 'dasl8121',
 138             'upload_date': '20170411',
 139             'duration': 213,
 140         },
 141         'params': {
 142             'skip_download': True,
 143         },
 144     }, {
 145         # PARTIAL_ADULT
 146         'url': 'http://vod.afreecatv.com/PLAYER/STATION/32028439',
 147         'info_dict': {
 148             'id': '20180327_27901457_202289533_1',
 149             'ext': 'mp4',
 150             'title': '[생]빨개요♥ (part 1)',
 151             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 152             'uploader': '[SA]서아',
 153             'uploader_id': 'bjdyrksu',
 154             'upload_date': '20180327',
 155             'duration': 3601,
 156         },
 157         'params': {
 158             'skip_download': True,
 159         },
 160         'expected_warnings': ['adult content'],
 161     }, {
 162         'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
 163         'only_matching': True,
 164     }, {
 165         'url': 'http://vod.afreecatv.com/PLAYER/STATION/15055030',
 166         'only_matching': True,
 167     }]
 168
 169     @staticmethod
 170     def parse_video_key(key):
 171         video_key = {}
 172         m = re.match(r'^(?P<upload_date>\d{8})_\w+_(?P<part>\d+)$', key)
 173         if m:
 174             video_key['upload_date'] = m.group('upload_date')
 175             video_key['part'] = int(m.group('part'))
 176         return video_key
 177
 178     def _real_initialize(self):
 179         self._login()
 180
 181     def _login(self):
 182         username, password = self._get_login_info()
 183         if username is None:
 184             return
 185
 186         login_form = {
 187             'szWork': 'login',
 188             'szType': 'json',
 189             'szUid': username,
 190             'szPassword': password,
 191             'isSaveId': 'false',
 192             'szScriptVar': 'oLoginRet',
 193             'szAction': '',
 194         }
 195
 196         response = self._download_json(
 197             'https://login.afreecatv.com/app/LoginAction.php', None,
 198             'Logging in', data=urlencode_postdata(login_form))
 199
 200         _ERRORS = {
 201             -4: 'Your account has been suspended due to a violation of our terms and policies.',
 202             -5: 'https://member.afreecatv.com/app/user_delete_progress.php',
 203             -6: 'https://login.afreecatv.com/membership/changeMember.php',
 204             -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.",
 205             -9: 'https://member.afreecatv.com/app/pop_login_block.php',
 206             -11: 'https://login.afreecatv.com/afreeca/second_login.php',
 207             -12: 'https://member.afreecatv.com/app/user_security.php',
 208             0: 'The username does not exist or you have entered the wrong password.',
 209             -1: 'The username does not exist or you have entered the wrong password.',
 210             -3: 'You have entered your username/password incorrectly.',
 211             -7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.',
 212             -10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.',
 213             -32008: 'You have failed to log in. Please contact our Help Center.',
 214         }
 215
 216         result = int_or_none(response.get('RESULT'))
 217         if result != 1:
 218             error = _ERRORS.get(result, 'You have failed to log in.')
 219             raise ExtractorError(
 220                 'Unable to login: %s said: %s' % (self.IE_NAME, error),
 221                 expected=True)
 222
 223     def _real_extract(self, url):
 224         video_id = self._match_id(url)
 225
 226         webpage = self._download_webpage(url, video_id)
 227
 228         if re.search(r'alert\(["\']This video has been deleted', webpage):
 229             raise ExtractorError(
 230                 'Video %s has been deleted' % video_id, expected=True)
 231
 232         station_id = self._search_regex(
 233             r'nStationNo\s*=\s*(\d+)', webpage, 'station')
 234         bbs_id = self._search_regex(
 235             r'nBbsNo\s*=\s*(\d+)', webpage, 'bbs')
 236         video_id = self._search_regex(
 237             r'nTitleNo\s*=\s*(\d+)', webpage, 'title', default=video_id)
 238
 239         partial_view = False
 240         for _ in range(2):
 241             query = {
 242                 'nTitleNo': video_id,
 243                 'nStationNo': station_id,
 244                 'nBbsNo': bbs_id,
 245             }
 246             if partial_view:
 247                 query['partialView'] = 'SKIP_ADULT'
 248             video_xml = self._download_xml(
 249                 'http://afbbs.afreecatv.com:8080/api/video/get_video_info.php',
 250                 video_id, 'Downloading video info XML%s'
 251                 % (' (skipping adult)' if partial_view else ''),
 252                 video_id, headers={
 253                     'Referer': url,
 254                 }, query=query)
 255
 256             flag = xpath_text(video_xml, './track/flag', 'flag', default=None)
 257             if flag and flag == 'SUCCEED':
 258                 break
 259             if flag == 'PARTIAL_ADULT':
 260                 self._downloader.report_warning(
 261                     'In accordance with local laws and regulations, underage users are restricted from watching adult content. '
 262                     'Only content suitable for all ages will be downloaded. '
 263                     'Provide account credentials if you wish to download restricted content.')
 264                 partial_view = True
 265                 continue
 266             elif flag == 'ADULT':
 267                 error = 'Only users older than 19 are able to watch this video. Provide account credentials to download this content.'
 268             else:
 269                 error = flag
 270             raise ExtractorError(
 271                 '%s said: %s' % (self.IE_NAME, error), expected=True)
 272         else:
 273             raise ExtractorError('Unable to download video info')
 274
 275         video_element = video_xml.findall(compat_xpath('./track/video'))[-1]
 276         if video_element is None or video_element.text is None:
 277             raise ExtractorError(
 278                 'Video %s video does not exist' % video_id, expected=True)
 279
 280         video_url = video_element.text.strip()
 281
 282         title = xpath_text(video_xml, './track/title', 'title', fatal=True)
 283
 284         uploader = xpath_text(video_xml, './track/nickname', 'uploader')
 285         uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
 286         duration = int_or_none(xpath_text(
 287             video_xml, './track/duration', 'duration'))
 288         thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
 289
 290         common_entry = {
 291             'uploader': uploader,
 292             'uploader_id': uploader_id,
 293             'thumbnail': thumbnail,
 294         }
 295
 296         info = common_entry.copy()
 297         info.update({
 298             'id': video_id,
 299             'title': title,
 300             'duration': duration,
 301         })
 302
 303         if not video_url:
 304             entries = []
 305             file_elements = video_element.findall(compat_xpath('./file'))
 306             one = len(file_elements) == 1
 307             for file_num, file_element in enumerate(file_elements, start=1):
 308                 file_url = url_or_none(file_element.text)
 309                 if not file_url:
 310                     continue
 311                 key = file_element.get('key', '')
 312                 upload_date = self._search_regex(
 313                     r'^(\d{8})_', key, 'upload date', default=None)
 314                 file_duration = int_or_none(file_element.get('duration'))
 315                 format_id = key if key else '%s_%s' % (video_id, file_num)
 316                 if determine_ext(file_url) == 'm3u8':
 317                     formats = self._extract_m3u8_formats(
 318                         file_url, video_id, 'mp4', entry_protocol='m3u8_native',
 319                         m3u8_id='hls',
 320                         note='Downloading part %d m3u8 information' % file_num)
 321                 else:
 322                     formats = [{
 323                         'url': file_url,
 324                         'format_id': 'http',
 325                     }]
 326                 if not formats:
 327                     continue
 328                 self._sort_formats(formats)
 329                 file_info = common_entry.copy()
 330                 file_info.update({
 331                     'id': format_id,
 332                     'title': title if one else '%s (part %d)' % (title, file_num),
 333                     'upload_date': upload_date,
 334                     'duration': file_duration,
 335                     'formats': formats,
 336                 })
 337                 entries.append(file_info)
 338             entries_info = info.copy()
 339             entries_info.update({
 340                 '_type': 'multi_video',
 341                 'entries': entries,
 342             })
 343             return entries_info
 344
 345         info = {
 346             'id': video_id,
 347             'title': title,
 348             'uploader': uploader,
 349             'uploader_id': uploader_id,
 350             'duration': duration,
 351             'thumbnail': thumbnail,
 352         }
 353
 354         if determine_ext(video_url) == 'm3u8':
 355             info['formats'] = self._extract_m3u8_formats(
 356                 video_url, video_id, 'mp4', entry_protocol='m3u8_native',
 357                 m3u8_id='hls')
 358         else:
 359             app, playpath = video_url.split('mp4:')
 360             info.update({
 361                 'url': app,
 362                 'ext': 'flv',
 363                 'play_path': 'mp4:' + playpath,
 364                 'rtmp_live': True,  # downloading won't end without this
 365             })
 366
 367         return info