_ Git - youtube-dl/blob - youtube_dl/extractor/fourtube.py

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