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     xpath_text,
  13 )
  14
  15
  16 class AfreecaTVIE(InfoExtractor):
  17     IE_NAME = 'afreecatv'
  18     IE_DESC = 'afreecatv.com'
  19     _VALID_URL = r'''(?x)
  20                     https?://
  21                         (?:
  22                             (?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
  23                             (?:
  24                                 /app/(?:index|read_ucc_bbs)\.cgi|
  25                                 /player/[Pp]layer\.(?:swf|html)
  26                             )\?.*?\bnTitleNo=|
  27                             vod\.afreecatv\.com/PLAYER/STATION/
  28                         )
  29                         (?P<id>\d+)
  30                     '''
  31     _TESTS = [{
  32         'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
  33         'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
  34         'info_dict': {
  35             'id': '36164052',
  36             'ext': 'mp4',
  37             'title': '데일리 에이프릴 요정들의 시상식!',
  38             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  39             'uploader': 'dailyapril',
  40             'uploader_id': 'dailyapril',
  41             'upload_date': '20160503',
  42         },
  43         'skip': 'Video is gone',
  44     }, {
  45         'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
  46         'info_dict': {
  47             'id': '36153164',
  48             'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  49             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  50             'uploader': 'dailyapril',
  51             'uploader_id': 'dailyapril',
  52         },
  53         'playlist_count': 2,
  54         'playlist': [{
  55             'md5': 'd8b7c174568da61d774ef0203159bf97',
  56             'info_dict': {
  57                 'id': '36153164_1',
  58                 'ext': 'mp4',
  59                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  60                 'upload_date': '20160502',
  61             },
  62         }, {
  63             'md5': '58f2ce7f6044e34439ab2d50612ab02b',
  64             'info_dict': {
  65                 'id': '36153164_2',
  66                 'ext': 'mp4',
  67                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  68                 'upload_date': '20160502',
  69             },
  70         }],
  71         'skip': 'Video is gone',
  72     }, {
  73         'url': 'http://vod.afreecatv.com/PLAYER/STATION/18650793',
  74         'info_dict': {
  75             'id': '18650793',
  76             'ext': 'mp4',
  77             'title': '오늘은 다르다! 쏘님의 우월한 위아래~ 댄스리액션!',
  78             'thumbnail': r're:^https?://.*\.jpg$',
  79             'uploader': '윈아디',
  80             'uploader_id': 'badkids',
  81             'duration': 107,
  82         },
  83         'params': {
  84             'skip_download': True,
  85         },
  86     }, {
  87         'url': 'http://vod.afreecatv.com/PLAYER/STATION/10481652',
  88         'info_dict': {
  89             'id': '10481652',
  90             'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  91             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  92             'uploader': 'dailyapril',
  93             'uploader_id': 'dailyapril',
  94             'duration': 6492,
  95         },
  96         'playlist_count': 2,
  97         'playlist': [{
  98             'md5': 'd8b7c174568da61d774ef0203159bf97',
  99             'info_dict': {
 100                 'id': '20160502_c4c62b9d_174361386_1',
 101                 'ext': 'mp4',
 102                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 1)",
 103                 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 104                 'uploader': 'dailyapril',
 105                 'uploader_id': 'dailyapril',
 106                 'upload_date': '20160502',
 107                 'duration': 3601,
 108             },
 109         }, {
 110             'md5': '58f2ce7f6044e34439ab2d50612ab02b',
 111             'info_dict': {
 112                 'id': '20160502_39e739bb_174361386_2',
 113                 'ext': 'mp4',
 114                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 2)",
 115                 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 116                 'uploader': 'dailyapril',
 117                 'uploader_id': 'dailyapril',
 118                 'upload_date': '20160502',
 119                 'duration': 2891,
 120             },
 121         }],
 122         'params': {
 123             'skip_download': True,
 124         },
 125     }, {
 126         # non standard key
 127         'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605',
 128         'info_dict': {
 129             'id': '20170411_BE689A0E_190960999_1_2_h',
 130             'ext': 'mp4',
 131             'title': '혼자사는여자집',
 132             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 133             'uploader': '♥이슬이',
 134             'uploader_id': 'dasl8121',
 135             'upload_date': '20170411',
 136             'duration': 213,
 137         },
 138         'params': {
 139             'skip_download': True,
 140         },
 141     }, {
 142         # adult video
 143         'url': 'http://vod.afreecatv.com/PLAYER/STATION/26542731',
 144         'info_dict': {
 145             'id': '20171001_F1AE1711_196617479_1',
 146             'ext': 'mp4',
 147             'title': '[생]서아 초심 찾기 방송 (part 1)',
 148             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
 149             'uploader': 'BJ서아',
 150             'uploader_id': 'bjdyrksu',
 151             'upload_date': '20171001',
 152             'duration': 3600,
 153             'age_limit': 18,
 154         },
 155         'params': {
 156             'skip_download': True,
 157         },
 158     }, {
 159         'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
 160         'only_matching': True,
 161     }, {
 162         'url': 'http://vod.afreecatv.com/PLAYER/STATION/15055030',
 163         'only_matching': True,
 164     }]
 165
 166     @staticmethod
 167     def parse_video_key(key):
 168         video_key = {}
 169         m = re.match(r'^(?P<upload_date>\d{8})_\w+_(?P<part>\d+)$', key)
 170         if m:
 171             video_key['upload_date'] = m.group('upload_date')
 172             video_key['part'] = int(m.group('part'))
 173         return video_key
 174
 175     def _real_extract(self, url):
 176         video_id = self._match_id(url)
 177
 178         webpage = self._download_webpage(url, video_id)
 179
 180         if re.search(r'alert\(["\']This video has been deleted', webpage):
 181             raise ExtractorError(
 182                 'Video %s has been deleted' % video_id, expected=True)
 183
 184         station_id = self._search_regex(
 185             r'nStationNo\s*=\s*(\d+)', webpage, 'station')
 186         bbs_id = self._search_regex(
 187             r'nBbsNo\s*=\s*(\d+)', webpage, 'bbs')
 188         video_id = self._search_regex(
 189             r'nTitleNo\s*=\s*(\d+)', webpage, 'title', default=video_id)
 190
 191         video_xml = self._download_xml(
 192             'http://afbbs.afreecatv.com:8080/api/video/get_video_info.php',
 193             video_id, headers={
 194                 'Referer': 'http://vod.afreecatv.com/embed.php',
 195             }, query={
 196                 'nTitleNo': video_id,
 197                 'nStationNo': station_id,
 198                 'nBbsNo': bbs_id,
 199                 'partialView': 'SKIP_ADULT',
 200             })
 201
 202         flag = xpath_text(video_xml, './track/flag', 'flag', default=None)
 203         if flag and flag != 'SUCCEED':
 204             raise ExtractorError(
 205                 '%s said: %s' % (self.IE_NAME, flag), expected=True)
 206
 207         video_element = video_xml.findall(compat_xpath('./track/video'))[-1]
 208         if video_element is None or video_element.text is None:
 209             raise ExtractorError(
 210                 'Video %s video does not exist' % video_id, expected=True)
 211
 212         video_url = video_element.text.strip()
 213
 214         title = xpath_text(video_xml, './track/title', 'title', fatal=True)
 215
 216         uploader = xpath_text(video_xml, './track/nickname', 'uploader')
 217         uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
 218         duration = int_or_none(xpath_text(
 219             video_xml, './track/duration', 'duration'))
 220         thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
 221
 222         common_entry = {
 223             'uploader': uploader,
 224             'uploader_id': uploader_id,
 225             'thumbnail': thumbnail,
 226         }
 227
 228         info = common_entry.copy()
 229         info.update({
 230             'id': video_id,
 231             'title': title,
 232             'duration': duration,
 233         })
 234
 235         if not video_url:
 236             entries = []
 237             file_elements = video_element.findall(compat_xpath('./file'))
 238             one = len(file_elements) == 1
 239             for file_num, file_element in enumerate(file_elements, start=1):
 240                 file_url = file_element.text
 241                 if not file_url:
 242                     continue
 243                 key = file_element.get('key', '')
 244                 upload_date = self._search_regex(
 245                     r'^(\d{8})_', key, 'upload date', default=None)
 246                 file_duration = int_or_none(file_element.get('duration'))
 247                 format_id = key if key else '%s_%s' % (video_id, file_num)
 248                 if determine_ext(file_url) == 'm3u8':
 249                     formats = self._extract_m3u8_formats(
 250                         file_url, video_id, 'mp4', entry_protocol='m3u8_native',
 251                         m3u8_id='hls',
 252                         note='Downloading part %d m3u8 information' % file_num)
 253                 else:
 254                     formats = [{
 255                         'url': file_url,
 256                         'format_id': 'http',
 257                     }]
 258                 if not formats:
 259                     continue
 260                 self._sort_formats(formats)
 261                 file_info = common_entry.copy()
 262                 file_info.update({
 263                     'id': format_id,
 264                     'title': title if one else '%s (part %d)' % (title, file_num),
 265                     'upload_date': upload_date,
 266                     'duration': file_duration,
 267                     'formats': formats,
 268                 })
 269                 entries.append(file_info)
 270             entries_info = info.copy()
 271             entries_info.update({
 272                 '_type': 'multi_video',
 273                 'entries': entries,
 274             })
 275             return entries_info
 276
 277         info = {
 278             'id': video_id,
 279             'title': title,
 280             'uploader': uploader,
 281             'uploader_id': uploader_id,
 282             'duration': duration,
 283             'thumbnail': thumbnail,
 284         }
 285
 286         if determine_ext(video_url) == 'm3u8':
 287             info['formats'] = self._extract_m3u8_formats(
 288                 video_url, video_id, 'mp4', entry_protocol='m3u8_native',
 289                 m3u8_id='hls')
 290         else:
 291             app, playpath = video_url.split('mp4:')
 292             info.update({
 293                 'url': app,
 294                 'ext': 'flv',
 295                 'play_path': 'mp4:' + playpath,
 296                 'rtmp_live': True,  # downloading won't end without this
 297             })
 298
 299         return info