yt_dlp/extractor/fourtube.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_b64decode,
   6     compat_str,
   7     compat_urllib_parse_unquote,
   8     compat_urlparse,
   9 )
  10 from ..utils import (
  11     int_or_none,
  12     parse_duration,
  13     parse_iso8601,
  14     str_or_none,
  15     str_to_int,
  16     try_get,
  17     unified_timestamp,
  18     url_or_none,
  19 )
  20
  21
  22 class FourTubeBaseIE(InfoExtractor):
  23     def _extract_formats(self, url, video_id, media_id, sources):
  24         token_url = 'https://%s/%s/desktop/%s' % (
  25             self._TKN_HOST, media_id, '+'.join(sources))
  26
  27         parsed_url = compat_urlparse.urlparse(url)
  28         tokens = self._download_json(token_url, video_id, data=b'', headers={
  29             'Origin': '%s://%s' % (parsed_url.scheme, parsed_url.hostname),
  30             'Referer': url,
  31         })
  32         formats = [{
  33             'url': tokens[format]['token'],
  34             'format_id': format + 'p',
  35             'resolution': format + 'p',
  36             'quality': int(format),
  37         } for format in sources]
  38         return formats
  39
  40     def _real_extract(self, url):
  41         mobj = self._match_valid_url(url)
  42         kind, video_id, display_id = mobj.group('kind', 'id', 'display_id')
  43
  44         if kind == 'm' or not display_id:
  45             url = self._URL_TEMPLATE % video_id
  46
  47         webpage = self._download_webpage(url, video_id)
  48
  49         title = self._html_search_meta('name', webpage)
  50         timestamp = parse_iso8601(self._html_search_meta(
  51             'uploadDate', webpage))
  52         thumbnail = self._html_search_meta('thumbnailUrl', webpage)
  53         uploader_id = self._html_search_regex(
  54             r'<a class="item-to-subscribe" href="[^"]+/(?:channel|user)s?/([^/"]+)" title="Go to [^"]+ page">',
  55             webpage, 'uploader id', fatal=False)
  56         uploader = self._html_search_regex(
  57             r'<a class="item-to-subscribe" href="[^"]+/(?:channel|user)s?/[^/"]+" title="Go to ([^"]+) page">',
  58             webpage, 'uploader', fatal=False)
  59
  60         categories_html = self._search_regex(
  61             r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="[^"]*?list[^"]*?">(.*?)</ul>',
  62             webpage, 'categories', fatal=False)
  63         categories = None
  64         if categories_html:
  65             categories = [
  66                 c.strip() for c in re.findall(
  67                     r'(?s)<li><a.*?>(.*?)</a>', categories_html)]
  68
  69         view_count = str_to_int(self._search_regex(
  70             r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:([0-9,]+)">',
  71             webpage, 'view count', default=None))
  72         like_count = str_to_int(self._search_regex(
  73             r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserLikes:([0-9,]+)">',
  74             webpage, 'like count', default=None))
  75         duration = parse_duration(self._html_search_meta('duration', webpage))
  76
  77         media_id = self._search_regex(
  78             r'<button[^>]+data-id=(["\'])(?P<id>\d+)\1[^>]+data-quality=', webpage,
  79             'media id', default=None, group='id')
  80         sources = [
  81             quality
  82             for _, quality in re.findall(r'<button[^>]+data-quality=(["\'])(.+?)\1', webpage)]
  83         if not (media_id and sources):
  84             player_js = self._download_webpage(
  85                 self._search_regex(
  86                     r'<script[^>]id=(["\'])playerembed\1[^>]+src=(["\'])(?P<url>.+?)\2',
  87                     webpage, 'player JS', group='url'),
  88                 video_id, 'Downloading player JS')
  89             params_js = self._search_regex(
  90                 r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)',
  91                 player_js, 'initialization parameters')
  92             params = self._parse_json('[%s]' % params_js, video_id)
  93             media_id = params[0]
  94             sources = ['%s' % p for p in params[2]]
  95
  96         formats = self._extract_formats(url, video_id, media_id, sources)
  97
  98         return {
  99             'id': video_id,
 100             'title': title,
 101             'formats': formats,
 102             'categories': categories,
 103             'thumbnail': thumbnail,
 104             'uploader': uploader,
 105             'uploader_id': uploader_id,
 106             'timestamp': timestamp,
 107             'like_count': like_count,
 108             'view_count': view_count,
 109             'duration': duration,
 110             'age_limit': 18,
 111         }
 112
 113
 114 class FourTubeIE(FourTubeBaseIE):
 115     IE_NAME = '4tube'
 116     _VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?4tube\.com/(?:videos|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
 117     _URL_TEMPLATE = 'https://www.4tube.com/videos/%s/video'
 118     _TKN_HOST = 'token.4tube.com'
 119     _TESTS = [{
 120         'url': 'http://www.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black',
 121         'md5': '6516c8ac63b03de06bc8eac14362db4f',
 122         'info_dict': {
 123             'id': '209733',
 124             'ext': 'mp4',
 125             'title': 'Hot Babe Holly Michaels gets her ass stuffed by black',
 126             'uploader': 'WCP Club',
 127             'uploader_id': 'wcp-club',
 128             'upload_date': '20131031',
 129             'timestamp': 1383263892,
 130             'duration': 583,
 131             'view_count': int,
 132             'like_count': int,
 133             'categories': list,
 134             'age_limit': 18,
 135         },
 136     }, {
 137         'url': 'http://www.4tube.com/embed/209733',
 138         'only_matching': True,
 139     }, {
 140         'url': 'http://m.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black',
 141         'only_matching': True,
 142     }]
 143
 144
 145 class FuxIE(FourTubeBaseIE):
 146     _VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?fux\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
 147     _URL_TEMPLATE = 'https://www.fux.com/video/%s/video'
 148     _TKN_HOST = 'token.fux.com'
 149     _TESTS = [{
 150         'url': 'https://www.fux.com/video/195359/awesome-fucking-kitchen-ends-cum-swallow',
 151         'info_dict': {
 152             'id': '195359',
 153             'ext': 'mp4',
 154             'title': 'Awesome fucking in the kitchen ends with cum swallow',
 155             'uploader': 'alenci2342',
 156             'uploader_id': 'alenci2342',
 157             'upload_date': '20131230',
 158             'timestamp': 1388361660,
 159             'duration': 289,
 160             'view_count': int,
 161             'like_count': int,
 162             'categories': list,
 163             'age_limit': 18,
 164         },
 165         'params': {
 166             'skip_download': True,
 167         },
 168     }, {
 169         'url': 'https://www.fux.com/embed/195359',
 170         'only_matching': True,
 171     }, {
 172         'url': 'https://www.fux.com/video/195359/awesome-fucking-kitchen-ends-cum-swallow',
 173         'only_matching': True,
 174     }]
 175
 176
 177 class PornTubeIE(FourTubeBaseIE):
 178     _VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?porntube\.com/(?:videos/(?P<display_id>[^/]+)_|embed/)(?P<id>\d+)'
 179     _URL_TEMPLATE = 'https://www.porntube.com/videos/video_%s'
 180     _TKN_HOST = 'tkn.porntube.com'
 181     _TESTS = [{
 182         'url': 'https://www.porntube.com/videos/teen-couple-doing-anal_7089759',
 183         'info_dict': {
 184             'id': '7089759',
 185             'ext': 'mp4',
 186             'title': 'Teen couple doing anal',
 187             'uploader': 'Alexy',
 188             'uploader_id': '91488',
 189             'upload_date': '20150606',
 190             'timestamp': 1433595647,
 191             'duration': 5052,
 192             'view_count': int,
 193             'like_count': int,
 194             'age_limit': 18,
 195         },
 196         'params': {
 197             'skip_download': True,
 198         },
 199     }, {
 200         'url': 'https://www.porntube.com/videos/squirting-teen-ballerina-ecg_1331406',
 201         'info_dict': {
 202             'id': '1331406',
 203             'ext': 'mp4',
 204             'title': 'Squirting Teen Ballerina on ECG',
 205             'uploader': 'Exploited College Girls',
 206             'uploader_id': '665',
 207             'channel': 'Exploited College Girls',
 208             'channel_id': '665',
 209             'upload_date': '20130920',
 210             'timestamp': 1379685485,
 211             'duration': 851,
 212             'view_count': int,
 213             'like_count': int,
 214             'age_limit': 18,
 215         },
 216         'params': {
 217             'skip_download': True,
 218         },
 219     }, {
 220         'url': 'https://www.porntube.com/embed/7089759',
 221         'only_matching': True,
 222     }, {
 223         'url': 'https://m.porntube.com/videos/teen-couple-doing-anal_7089759',
 224         'only_matching': True,
 225     }]
 226
 227     def _real_extract(self, url):
 228         mobj = self._match_valid_url(url)
 229         video_id, display_id = mobj.group('id', 'display_id')
 230
 231         webpage = self._download_webpage(url, display_id)
 232
 233         video = self._parse_json(
 234             self._search_regex(
 235                 r'INITIALSTATE\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
 236                 webpage, 'data', group='value'), video_id,
 237             transform_source=lambda x: compat_urllib_parse_unquote(
 238                 compat_b64decode(x).decode('utf-8')))['page']['video']
 239
 240         title = video['title']
 241         media_id = video['mediaId']
 242         sources = [compat_str(e['height'])
 243                    for e in video['encodings'] if e.get('height')]
 244         formats = self._extract_formats(url, video_id, media_id, sources)
 245
 246         thumbnail = url_or_none(video.get('masterThumb'))
 247         uploader = try_get(video, lambda x: x['user']['username'], compat_str)
 248         uploader_id = str_or_none(try_get(
 249             video, lambda x: x['user']['id'], int))
 250         channel = try_get(video, lambda x: x['channel']['name'], compat_str)
 251         channel_id = str_or_none(try_get(
 252             video, lambda x: x['channel']['id'], int))
 253         like_count = int_or_none(video.get('likes'))
 254         dislike_count = int_or_none(video.get('dislikes'))
 255         view_count = int_or_none(video.get('playsQty'))
 256         duration = int_or_none(video.get('durationInSeconds'))
 257         timestamp = unified_timestamp(video.get('publishedAt'))
 258
 259         return {
 260             'id': video_id,
 261             'title': title,
 262             'formats': formats,
 263             'thumbnail': thumbnail,
 264             'uploader': uploader or channel,
 265             'uploader_id': uploader_id or channel_id,
 266             'channel': channel,
 267             'channel_id': channel_id,
 268             'timestamp': timestamp,
 269             'like_count': like_count,
 270             'dislike_count': dislike_count,
 271             'view_count': view_count,
 272             'duration': duration,
 273             'age_limit': 18,
 274         }
 275
 276
 277 class PornerBrosIE(FourTubeBaseIE):
 278     _VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?pornerbros\.com/(?:videos/(?P<display_id>[^/]+)_|embed/)(?P<id>\d+)'
 279     _URL_TEMPLATE = 'https://www.pornerbros.com/videos/video_%s'
 280     _TKN_HOST = 'token.pornerbros.com'
 281     _TESTS = [{
 282         'url': 'https://www.pornerbros.com/videos/skinny-brunette-takes-big-cock-down-her-anal-hole_181369',
 283         'md5': '6516c8ac63b03de06bc8eac14362db4f',
 284         'info_dict': {
 285             'id': '181369',
 286             'ext': 'mp4',
 287             'title': 'Skinny brunette takes big cock down her anal hole',
 288             'uploader': 'PornerBros HD',
 289             'uploader_id': 'pornerbros-hd',
 290             'upload_date': '20130130',
 291             'timestamp': 1359527401,
 292             'duration': 1224,
 293             'view_count': int,
 294             'categories': list,
 295             'age_limit': 18,
 296         },
 297         'params': {
 298             'skip_download': True,
 299         },
 300     }, {
 301         'url': 'https://www.pornerbros.com/embed/181369',
 302         'only_matching': True,
 303     }, {
 304         'url': 'https://m.pornerbros.com/videos/skinny-brunette-takes-big-cock-down-her-anal-hole_181369',
 305         'only_matching': True,
 306     }]