yt_dlp/extractor/tnaflix.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     fix_xml_ampersands,
   5     float_or_none,
   6     int_or_none,
   7     parse_duration,
   8     str_to_int,
   9     unescapeHTML,
  10     xpath_text,
  11 )
  12
  13
  14 class TNAFlixNetworkBaseIE(InfoExtractor):
  15     # May be overridden in descendants if necessary
  16     _CONFIG_REGEX = [
  17         r'flashvars\.config\s*=\s*escape\("(?P<url>[^"]+)"',
  18         r'<input[^>]+name="config\d?" value="(?P<url>[^"]+)"',
  19         r'config\s*=\s*(["\'])(?P<url>(?:https?:)?//(?:(?!\1).)+)\1',
  20     ]
  21     _HOST = 'tna'
  22     _VKEY_SUFFIX = ''
  23     _TITLE_REGEX = r'<input[^>]+name="title" value="([^"]+)"'
  24     _DESCRIPTION_REGEX = r'<input[^>]+name="description" value="([^"]+)"'
  25     _UPLOADER_REGEX = r'<input[^>]+name="username" value="([^"]+)"'
  26     _VIEW_COUNT_REGEX = None
  27     _COMMENT_COUNT_REGEX = None
  28     _AVERAGE_RATING_REGEX = None
  29     _CATEGORIES_REGEX = r'<li[^>]*>\s*<span[^>]+class="infoTitle"[^>]*>Categories:</span>\s*<span[^>]+class="listView"[^>]*>(.+?)</span>\s*</li>'
  30
  31     def _extract_thumbnails(self, flix_xml):
  32
  33         def get_child(elem, names):
  34             for name in names:
  35                 child = elem.find(name)
  36                 if child is not None:
  37                     return child
  38
  39         timeline = get_child(flix_xml, ['timeline', 'rolloverBarImage'])
  40         if timeline is None:
  41             return
  42
  43         pattern_el = get_child(timeline, ['imagePattern', 'pattern'])
  44         if pattern_el is None or not pattern_el.text:
  45             return
  46
  47         first_el = get_child(timeline, ['imageFirst', 'first'])
  48         last_el = get_child(timeline, ['imageLast', 'last'])
  49         if first_el is None or last_el is None:
  50             return
  51
  52         first_text = first_el.text
  53         last_text = last_el.text
  54         if not first_text.isdigit() or not last_text.isdigit():
  55             return
  56
  57         first = int(first_text)
  58         last = int(last_text)
  59         if first > last:
  60             return
  61
  62         width = int_or_none(xpath_text(timeline, './imageWidth', 'thumbnail width'))
  63         height = int_or_none(xpath_text(timeline, './imageHeight', 'thumbnail height'))
  64
  65         return [{
  66             'url': self._proto_relative_url(pattern_el.text.replace('#', compat_str(i)), 'http:'),
  67             'width': width,
  68             'height': height,
  69         } for i in range(first, last + 1)]
  70
  71     def _real_extract(self, url):
  72         mobj = self._match_valid_url(url)
  73         video_id = mobj.group('id')
  74         for display_id_key in ('display_id', 'display_id_2'):
  75             if display_id_key in mobj.groupdict():
  76                 display_id = mobj.group(display_id_key)
  77                 if display_id:
  78                     break
  79         else:
  80             display_id = video_id
  81
  82         webpage = self._download_webpage(url, display_id)
  83
  84         cfg_url = self._proto_relative_url(self._html_search_regex(
  85             self._CONFIG_REGEX, webpage, 'flashvars.config', default=None,
  86             group='url'), 'http:')
  87
  88         if not cfg_url:
  89             inputs = self._hidden_inputs(webpage)
  90             cfg_url = ('https://cdn-fck.%sflix.com/%sflix/%s%s.fid?key=%s&VID=%s&premium=1&vip=1&alpha'
  91                        % (self._HOST, self._HOST, inputs['vkey'], self._VKEY_SUFFIX, inputs['nkey'], video_id))
  92
  93         cfg_xml = self._download_xml(
  94             cfg_url, display_id, 'Downloading metadata',
  95             transform_source=fix_xml_ampersands, headers={'Referer': url})
  96
  97         formats = []
  98
  99         def extract_video_url(vl):
 100             # Any URL modification now results in HTTP Error 403: Forbidden
 101             return unescapeHTML(vl.text)
 102
 103         video_link = cfg_xml.find('./videoLink')
 104         if video_link is not None:
 105             formats.append({
 106                 'url': extract_video_url(video_link),
 107                 'ext': xpath_text(cfg_xml, './videoConfig/type', 'type', default='flv'),
 108             })
 109
 110         for item in cfg_xml.findall('./quality/item'):
 111             video_link = item.find('./videoLink')
 112             if video_link is None:
 113                 continue
 114             res = item.find('res')
 115             format_id = None if res is None else res.text
 116             height = int_or_none(self._search_regex(
 117                 r'^(\d+)[pP]', format_id, 'height', default=None))
 118             formats.append({
 119                 'url': self._proto_relative_url(extract_video_url(video_link), 'http:'),
 120                 'format_id': format_id,
 121                 'height': height,
 122             })
 123
 124         self._sort_formats(formats)
 125
 126         thumbnail = self._proto_relative_url(
 127             xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:')
 128         thumbnails = self._extract_thumbnails(cfg_xml)
 129
 130         title = None
 131         if self._TITLE_REGEX:
 132             title = self._html_search_regex(
 133                 self._TITLE_REGEX, webpage, 'title', default=None)
 134         if not title:
 135             title = self._og_search_title(webpage)
 136
 137         age_limit = self._rta_search(webpage) or 18
 138
 139         duration = parse_duration(self._html_search_meta(
 140             'duration', webpage, 'duration', default=None))
 141
 142         def extract_field(pattern, name):
 143             return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None
 144
 145         description = extract_field(self._DESCRIPTION_REGEX, 'description')
 146         uploader = extract_field(self._UPLOADER_REGEX, 'uploader')
 147         view_count = str_to_int(extract_field(self._VIEW_COUNT_REGEX, 'view count'))
 148         comment_count = str_to_int(extract_field(self._COMMENT_COUNT_REGEX, 'comment count'))
 149         average_rating = float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating'))
 150
 151         categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
 152         categories = [c.strip() for c in categories_str.split(',')] if categories_str is not None else []
 153
 154         return {
 155             'id': video_id,
 156             'display_id': display_id,
 157             'title': title,
 158             'description': description,
 159             'thumbnail': thumbnail,
 160             'thumbnails': thumbnails,
 161             'duration': duration,
 162             'age_limit': age_limit,
 163             'uploader': uploader,
 164             'view_count': view_count,
 165             'comment_count': comment_count,
 166             'average_rating': average_rating,
 167             'categories': categories,
 168             'formats': formats,
 169         }
 170
 171
 172 class TNAFlixNetworkEmbedIE(TNAFlixNetworkBaseIE):
 173     _VALID_URL = r'https?://player\.(?:tna|emp)flix\.com/video/(?P<id>\d+)'
 174     _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.(?:tna|emp)flix\.com/video/\d+)\1']
 175
 176     _TITLE_REGEX = r'<title>([^<]+)</title>'
 177
 178     _TESTS = [{
 179         'url': 'https://player.tnaflix.com/video/6538',
 180         'info_dict': {
 181             'id': '6538',
 182             'display_id': '6538',
 183             'ext': 'mp4',
 184             'title': 'Educational xxx video',
 185             'thumbnail': r're:https?://.*\.jpg$',
 186             'age_limit': 18,
 187         },
 188         'params': {
 189             'skip_download': True,
 190         },
 191     }, {
 192         'url': 'https://player.empflix.com/video/33051',
 193         'only_matching': True,
 194     }]
 195
 196
 197 class TNAEMPFlixBaseIE(TNAFlixNetworkBaseIE):
 198     _DESCRIPTION_REGEX = r'(?s)>Description:</[^>]+>(.+?)<'
 199     _UPLOADER_REGEX = r'<span>by\s*<a[^>]+\bhref=["\']/profile/[^>]+>([^<]+)<'
 200     _CATEGORIES_REGEX = r'(?s)<span[^>]*>Categories:</span>(.+?)</div>'
 201
 202
 203 class TNAFlixIE(TNAEMPFlixBaseIE):
 204     _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
 205
 206     _TITLE_REGEX = r'<title>(.+?) - (?:TNAFlix Porn Videos|TNAFlix\.com)</title>'
 207
 208     _TESTS = [{
 209         # anonymous uploader, no categories
 210         'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
 211         'md5': '7e569419fe6d69543d01e6be22f5f7c4',
 212         'info_dict': {
 213             'id': '553878',
 214             'display_id': 'Carmella-Decesare-striptease',
 215             'ext': 'mp4',
 216             'title': 'Carmella Decesare - striptease',
 217             'thumbnail': r're:https?://.*\.jpg$',
 218             'duration': 91,
 219             'age_limit': 18,
 220             'categories': ['Porn Stars'],
 221         }
 222     }, {
 223         # non-anonymous uploader, categories
 224         'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
 225         'md5': '0f5d4d490dbfd117b8607054248a07c0',
 226         'info_dict': {
 227             'id': '6538',
 228             'display_id': 'Educational-xxx-video',
 229             'ext': 'mp4',
 230             'title': 'Educational xxx video',
 231             'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
 232             'thumbnail': r're:https?://.*\.jpg$',
 233             'duration': 164,
 234             'age_limit': 18,
 235             'uploader': 'bobwhite39',
 236             'categories': list,
 237         }
 238     }, {
 239         'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
 240         'only_matching': True,
 241     }]
 242
 243
 244 class EMPFlixIE(TNAEMPFlixBaseIE):
 245     _VALID_URL = r'https?://(?:www\.)?empflix\.com/(?:videos/(?P<display_id>.+?)-|[^/]+/(?P<display_id_2>[^/]+)/video)(?P<id>[0-9]+)'
 246
 247     _HOST = 'emp'
 248     _VKEY_SUFFIX = '-1'
 249
 250     _TESTS = [{
 251         'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
 252         'md5': 'bc30d48b91a7179448a0bda465114676',
 253         'info_dict': {
 254             'id': '33051',
 255             'display_id': 'Amateur-Finger-Fuck',
 256             'ext': 'mp4',
 257             'title': 'Amateur Finger Fuck',
 258             'description': 'Amateur solo finger fucking.',
 259             'thumbnail': r're:https?://.*\.jpg$',
 260             'duration': 83,
 261             'age_limit': 18,
 262             'uploader': 'cwbike',
 263             'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'],
 264         }
 265     }, {
 266         'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
 267         'only_matching': True,
 268     }, {
 269         'url': 'https://www.empflix.com/amateur-porn/Amateur-Finger-Fuck/video33051',
 270         'only_matching': True,
 271     }]
 272
 273
 274 class MovieFapIE(TNAFlixNetworkBaseIE):
 275     _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html'
 276
 277     _VIEW_COUNT_REGEX = r'<br>Views\s*<strong>([\d,.]+)</strong>'
 278     _COMMENT_COUNT_REGEX = r'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>'
 279     _AVERAGE_RATING_REGEX = r'Current Rating\s*<br>\s*<strong>([\d.]+)</strong>'
 280     _CATEGORIES_REGEX = r'(?s)<div[^>]+id="vid_info"[^>]*>\s*<div[^>]*>.+?</div>(.*?)<br>'
 281
 282     _TESTS = [{
 283         # normal, multi-format video
 284         'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
 285         'md5': '26624b4e2523051b550067d547615906',
 286         'info_dict': {
 287             'id': 'be9867c9416c19f54a4a',
 288             'display_id': 'experienced-milf-amazing-handjob',
 289             'ext': 'mp4',
 290             'title': 'Experienced MILF Amazing Handjob',
 291             'description': 'Experienced MILF giving an Amazing Handjob',
 292             'thumbnail': r're:https?://.*\.jpg$',
 293             'age_limit': 18,
 294             'uploader': 'darvinfred06',
 295             'view_count': int,
 296             'comment_count': int,
 297             'average_rating': float,
 298             'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'],
 299         }
 300     }, {
 301         # quirky single-format case where the extension is given as fid, but the video is really an flv
 302         'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
 303         'md5': 'fa56683e291fc80635907168a743c9ad',
 304         'info_dict': {
 305             'id': 'e5da0d3edce5404418f5',
 306             'display_id': 'jeune-couple-russe',
 307             'ext': 'flv',
 308             'title': 'Jeune Couple Russe',
 309             'description': 'Amateur',
 310             'thumbnail': r're:https?://.*\.jpg$',
 311             'age_limit': 18,
 312             'uploader': 'whiskeyjar',
 313             'view_count': int,
 314             'comment_count': int,
 315             'average_rating': float,
 316             'categories': ['Amateur', 'Teen'],
 317         }
 318     }]