yt_dlp/extractor/tnaflix.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     fix_xml_ampersands,
   6     float_or_none,
   7     int_or_none,
   8     parse_duration,
   9     str_to_int,
  10     unescapeHTML,
  11     url_basename,
  12     xpath_text,
  13 )
  14
  15
  16 class TNAFlixNetworkBaseIE(InfoExtractor):
  17     # May be overridden in descendants if necessary
  18     _CONFIG_REGEX = [
  19         r'flashvars\.config\s*=\s*escape\("(?P<url>[^"]+)"',
  20         r'<input[^>]+name="config\d?" value="(?P<url>[^"]+)"',
  21         r'config\s*=\s*(["\'])(?P<url>(?:https?:)?//(?:(?!\1).)+)\1',
  22     ]
  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('#', 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, host = mobj.group('id', 'host')
  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         inputs = self._hidden_inputs(webpage)
  84         query = {}
  85
  86         # check for MovieFap-style config
  87         cfg_url = self._proto_relative_url(self._html_search_regex(
  88             self._CONFIG_REGEX, webpage, 'flashvars.config', default=None,
  89             group='url'), 'http:')
  90
  91         if not cfg_url:
  92             cfg_url = inputs.get('config')
  93
  94         # check for TNAFlix-style config
  95         if not cfg_url and inputs.get('vkey') and inputs.get('nkey'):
  96             cfg_url = f'http://cdn-fck.{host}.com/{host}/{inputs["vkey"]}.fid'
  97             query.update({
  98                 'key': inputs['nkey'],
  99                 'VID': video_id,
 100                 'premium': '1',
 101                 'vip': '1',
 102                 'alpha': '',
 103             })
 104
 105         formats, json_ld = [], {}
 106
 107         # TNAFlix and MovieFap extraction
 108         if cfg_url:
 109             cfg_xml = self._download_xml(
 110                 cfg_url, display_id, 'Downloading metadata',
 111                 transform_source=fix_xml_ampersands, headers={'Referer': url}, query=query)
 112
 113             def extract_video_url(vl):
 114                 # Any URL modification now results in HTTP Error 403: Forbidden
 115                 return unescapeHTML(vl.text)
 116
 117             video_link = cfg_xml.find('./videoLink')
 118             if video_link is not None:
 119                 formats.append({
 120                     'url': extract_video_url(video_link),
 121                     'ext': xpath_text(cfg_xml, './videoConfig/type', 'type', default='flv'),
 122                 })
 123
 124             for item in cfg_xml.findall('./quality/item'):
 125                 video_link = item.find('./videoLink')
 126                 if video_link is None:
 127                     continue
 128                 res = item.find('res')
 129                 format_id = None if res is None else res.text
 130                 height = int_or_none(self._search_regex(
 131                     r'^(\d+)[pP]', format_id, 'height', default=None))
 132                 formats.append({
 133                     'url': self._proto_relative_url(extract_video_url(video_link), 'http:'),
 134                     'format_id': format_id,
 135                     'height': height,
 136                 })
 137
 138             thumbnails = self._extract_thumbnails(cfg_xml) or []
 139             thumbnails.append({
 140                 'url': self._proto_relative_url(xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:'),
 141             })
 142
 143         # check for EMPFlix-style JSON and extract
 144         else:
 145             player = self._download_json(
 146                 f'http://www.{host}.com/ajax/video-player/{video_id}', video_id,
 147                 headers={'Referer': url}).get('html', '')
 148             for mobj in re.finditer(r'<source src="(?P<src>[^"]+)"', player):
 149                 video_url = mobj.group('src')
 150                 height = self._search_regex(r'-(\d+)p\.', url_basename(video_url), 'height', default=None)
 151                 formats.append({
 152                     'url': self._proto_relative_url(video_url, 'http:'),
 153                     'ext': url_basename(video_url).split('.')[-1],
 154                     'height': int_or_none(height),
 155                     'format_id': f'{height}p' if height else url_basename(video_url).split('.')[0],
 156                 })
 157             thumbnail = self._proto_relative_url(self._search_regex(
 158                 r'data-poster="([^"]+)"', player, 'thumbnail', default=None), 'http:')
 159             thumbnails = [{'url': thumbnail}] if thumbnail else None
 160             json_ld = self._search_json_ld(webpage, display_id, default={})
 161
 162         def extract_field(pattern, name):
 163             return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None
 164
 165         return {
 166             'id': video_id,
 167             'display_id': display_id,
 168             'title': (extract_field(self._TITLE_REGEX, 'title')
 169                       or self._og_search_title(webpage, default=None)
 170                       or json_ld.get('title')),
 171             'description': extract_field(self._DESCRIPTION_REGEX, 'description') or json_ld.get('description'),
 172             'thumbnails': thumbnails,
 173             'duration': parse_duration(
 174                 self._html_search_meta('duration', webpage, 'duration', default=None)) or json_ld.get('duration'),
 175             'age_limit': self._rta_search(webpage) or 18,
 176             'uploader': extract_field(self._UPLOADER_REGEX, 'uploader') or json_ld.get('uploader'),
 177             'view_count': str_to_int(extract_field(self._VIEW_COUNT_REGEX, 'view count')),
 178             'comment_count': str_to_int(extract_field(self._COMMENT_COUNT_REGEX, 'comment count')),
 179             'average_rating': float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating')),
 180             'categories': list(map(str.strip, (extract_field(self._CATEGORIES_REGEX, 'categories') or '').split(','))),
 181             'formats': formats,
 182         }
 183
 184
 185 class TNAFlixNetworkEmbedIE(TNAFlixNetworkBaseIE):
 186     _VALID_URL = r'https?://player\.(?P<host>tnaflix|empflix)\.com/video/(?P<id>\d+)'
 187     _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.(?:tna|emp)flix\.com/video/\d+)\1']
 188
 189     _TESTS = [{
 190         'url': 'https://player.tnaflix.com/video/6538',
 191         'info_dict': {
 192             'id': '6538',
 193             'display_id': '6538',
 194             'ext': 'mp4',
 195             'title': 'Educational xxx video (G Spot)',
 196             'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
 197             'thumbnail': r're:https?://.*\.jpg$',
 198             'age_limit': 18,
 199             'duration': 164,
 200             'uploader': 'bobwhite39',
 201             'categories': list,
 202         },
 203         'params': {
 204             'skip_download': True,
 205         },
 206     }, {
 207         'url': 'http://player.empflix.com/video/33051',
 208         'only_matching': True,
 209     }]
 210
 211     def _real_extract(self, url):
 212         mobj = self._match_valid_url(url)
 213         video_id, host = mobj.group('id', 'host')
 214         return self.url_result(f'http://www.{host}.com/category/{video_id}/video{video_id}')
 215
 216
 217 class TNAEMPFlixBaseIE(TNAFlixNetworkBaseIE):
 218     _DESCRIPTION_REGEX = r'(?s)>Description:</[^>]+>(.+?)<'
 219     _UPLOADER_REGEX = r'<span>by\s*<a[^>]+\bhref=["\']/profile/[^>]+>([^<]+)<'
 220     _CATEGORIES_REGEX = r'(?s)<span[^>]*>Categories:</span>(.+?)</div>'
 221
 222
 223 class TNAFlixIE(TNAEMPFlixBaseIE):
 224     _VALID_URL = r'https?://(?:www\.)?(?P<host>tnaflix)\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
 225
 226     _TITLE_REGEX = r'<title>(.+?) - (?:TNAFlix Porn Videos|TNAFlix\.com)</title>'
 227
 228     _TESTS = [{
 229         # anonymous uploader, no categories
 230         'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
 231         'md5': '7e569419fe6d69543d01e6be22f5f7c4',
 232         'info_dict': {
 233             'id': '553878',
 234             'display_id': 'Carmella-Decesare-striptease',
 235             'ext': 'mp4',
 236             'title': 'Carmella Decesare - striptease',
 237             'thumbnail': r're:https?://.*\.jpg$',
 238             'duration': 91,
 239             'age_limit': 18,
 240             'categories': list,
 241         },
 242     }, {
 243         # non-anonymous uploader, categories
 244         'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
 245         'md5': 'add5a9fa7f4da53d3e9d0845ac58f20c',
 246         'info_dict': {
 247             'id': '6538',
 248             'display_id': 'Educational-xxx-video',
 249             'ext': 'mp4',
 250             'title': 'Educational xxx video (G Spot)',
 251             'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
 252             'thumbnail': r're:https?://.*\.jpg$',
 253             'duration': 164,
 254             'age_limit': 18,
 255             'uploader': 'bobwhite39',
 256             'categories': list,
 257         },
 258     }, {
 259         'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
 260         'only_matching': True,
 261     }]
 262
 263
 264 class EMPFlixIE(TNAEMPFlixBaseIE):
 265     _VALID_URL = r'https?://(?:www\.)?(?P<host>empflix)\.com/(?:videos/(?P<display_id>.+?)-|[^/]+/(?P<display_id_2>[^/]+)/video)(?P<id>[0-9]+)'
 266
 267     _TESTS = [{
 268         'url': 'http://www.empflix.com/amateur-porn/Amateur-Finger-Fuck/video33051',
 269         'md5': 'd761c7b26601bd14476cd9512f2654fc',
 270         'info_dict': {
 271             'id': '33051',
 272             'display_id': 'Amateur-Finger-Fuck',
 273             'ext': 'mp4',
 274             'title': 'Amateur Finger Fuck',
 275             'description': 'Amateur solo finger fucking.',
 276             'thumbnail': r're:https?://.*\.jpg$',
 277             'duration': 83,
 278             'age_limit': 18,
 279             'categories': list,
 280         },
 281     }, {
 282         'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
 283         'only_matching': True,
 284     }, {
 285         'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
 286         'only_matching': True,
 287     }]
 288
 289
 290 class MovieFapIE(TNAFlixNetworkBaseIE):
 291     _VALID_URL = r'https?://(?:www\.)?(?P<host>moviefap)\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html'
 292
 293     _VIEW_COUNT_REGEX = r'<br>Views\s*<strong>([\d,.]+)</strong>'
 294     _COMMENT_COUNT_REGEX = r'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>'
 295     _AVERAGE_RATING_REGEX = r'Current Rating\s*<br>\s*<strong>([\d.]+)</strong>'
 296     _CATEGORIES_REGEX = r'(?s)<div[^>]+id="vid_info"[^>]*>\s*<div[^>]*>.+?</div>(.*?)<br>'
 297
 298     _TESTS = [{
 299         # normal, multi-format video
 300         'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
 301         'md5': '26624b4e2523051b550067d547615906',
 302         'info_dict': {
 303             'id': 'be9867c9416c19f54a4a',
 304             'display_id': 'experienced-milf-amazing-handjob',
 305             'ext': 'mp4',
 306             'title': 'Experienced MILF Amazing Handjob',
 307             'description': 'Experienced MILF giving an Amazing Handjob',
 308             'thumbnail': r're:https?://.*\.jpg$',
 309             'age_limit': 18,
 310             'uploader': 'darvinfred06',
 311             'view_count': int,
 312             'comment_count': int,
 313             'average_rating': float,
 314             'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'],
 315         },
 316     }, {
 317         # quirky single-format case where the extension is given as fid, but the video is really an flv
 318         'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
 319         'md5': 'fa56683e291fc80635907168a743c9ad',
 320         'info_dict': {
 321             'id': 'e5da0d3edce5404418f5',
 322             'display_id': 'jeune-couple-russe',
 323             'ext': 'flv',
 324             'title': 'Jeune Couple Russe',
 325             'description': 'Amateur',
 326             'thumbnail': r're:https?://.*\.jpg$',
 327             'age_limit': 18,
 328             'uploader': 'whiskeyjar',
 329             'view_count': int,
 330             'comment_count': int,
 331             'average_rating': float,
 332             'categories': ['Amateur', 'Teen'],
 333         },
 334         'skip': 'This video does not exist',
 335     }]