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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     fix_xml_ampersands,
   9     float_or_none,
  10     int_or_none,
  11     parse_duration,
  12     str_to_int,
  13     unescapeHTML,
  14     xpath_text,
  15 )
  16
  17
  18 class TNAFlixNetworkBaseIE(InfoExtractor):
  19     # May be overridden in descendants if necessary
  20     _CONFIG_REGEX = [
  21         r'flashvars\.config\s*=\s*escape\("([^"]+)"',
  22         r'<input[^>]+name="config\d?" value="([^"]+)"',
  23     ]
  24     _HOST = 'tna'
  25     _VKEY_SUFFIX = ''
  26     _TITLE_REGEX = r'<input[^>]+name="title" value="([^"]+)"'
  27     _DESCRIPTION_REGEX = r'<input[^>]+name="description" value="([^"]+)"'
  28     _UPLOADER_REGEX = r'<input[^>]+name="username" value="([^"]+)"'
  29     _VIEW_COUNT_REGEX = None
  30     _COMMENT_COUNT_REGEX = None
  31     _AVERAGE_RATING_REGEX = None
  32     _CATEGORIES_REGEX = r'<li[^>]*>\s*<span[^>]+class="infoTitle"[^>]*>Categories:</span>\s*<span[^>]+class="listView"[^>]*>(.+?)</span>\s*</li>'
  33
  34     def _extract_thumbnails(self, flix_xml):
  35
  36         def get_child(elem, names):
  37             for name in names:
  38                 child = elem.find(name)
  39                 if child is not None:
  40                     return child
  41
  42         timeline = get_child(flix_xml, ['timeline', 'rolloverBarImage'])
  43         if timeline is None:
  44             return
  45
  46         pattern_el = get_child(timeline, ['imagePattern', 'pattern'])
  47         if pattern_el is None or not pattern_el.text:
  48             return
  49
  50         first_el = get_child(timeline, ['imageFirst', 'first'])
  51         last_el = get_child(timeline, ['imageLast', 'last'])
  52         if first_el is None or last_el is None:
  53             return
  54
  55         first_text = first_el.text
  56         last_text = last_el.text
  57         if not first_text.isdigit() or not last_text.isdigit():
  58             return
  59
  60         first = int(first_text)
  61         last = int(last_text)
  62         if first > last:
  63             return
  64
  65         width = int_or_none(xpath_text(timeline, './imageWidth', 'thumbnail width'))
  66         height = int_or_none(xpath_text(timeline, './imageHeight', 'thumbnail height'))
  67
  68         return [{
  69             'url': self._proto_relative_url(pattern_el.text.replace('#', compat_str(i)), 'http:'),
  70             'width': width,
  71             'height': height,
  72         } for i in range(first, last + 1)]
  73
  74     def _real_extract(self, url):
  75         mobj = re.match(self._VALID_URL, url)
  76         video_id = mobj.group('id')
  77         display_id = mobj.group('display_id') if 'display_id' in mobj.groupdict() else video_id
  78
  79         webpage = self._download_webpage(url, display_id)
  80
  81         cfg_url = self._proto_relative_url(self._html_search_regex(
  82             self._CONFIG_REGEX, webpage, 'flashvars.config', default=None), 'http:')
  83
  84         if not cfg_url:
  85             inputs = self._hidden_inputs(webpage)
  86             cfg_url = ('https://cdn-fck.%sflix.com/%sflix/%s%s.fid?key=%s&VID=%s&premium=1&vip=1&alpha'
  87                        % (self._HOST, self._HOST, inputs['vkey'], self._VKEY_SUFFIX, inputs['nkey'], video_id))
  88
  89         cfg_xml = self._download_xml(
  90             cfg_url, display_id, 'Downloading metadata',
  91             transform_source=fix_xml_ampersands)
  92
  93         formats = []
  94
  95         def extract_video_url(vl):
  96             # Any URL modification now results in HTTP Error 403: Forbidden
  97             return unescapeHTML(vl.text)
  98
  99         video_link = cfg_xml.find('./videoLink')
 100         if video_link is not None:
 101             formats.append({
 102                 'url': extract_video_url(video_link),
 103                 'ext': xpath_text(cfg_xml, './videoConfig/type', 'type', default='flv'),
 104             })
 105
 106         for item in cfg_xml.findall('./quality/item'):
 107             video_link = item.find('./videoLink')
 108             if video_link is None:
 109                 continue
 110             res = item.find('res')
 111             format_id = None if res is None else res.text
 112             height = int_or_none(self._search_regex(
 113                 r'^(\d+)[pP]', format_id, 'height', default=None))
 114             formats.append({
 115                 'url': self._proto_relative_url(extract_video_url(video_link), 'http:'),
 116                 'format_id': format_id,
 117                 'height': height,
 118             })
 119
 120         self._sort_formats(formats)
 121
 122         thumbnail = self._proto_relative_url(
 123             xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:')
 124         thumbnails = self._extract_thumbnails(cfg_xml)
 125
 126         title = None
 127         if self._TITLE_REGEX:
 128             title = self._html_search_regex(
 129                 self._TITLE_REGEX, webpage, 'title', default=None)
 130         if not title:
 131             title = self._og_search_title(webpage)
 132
 133         age_limit = self._rta_search(webpage) or 18
 134
 135         duration = parse_duration(self._html_search_meta(
 136             'duration', webpage, 'duration', default=None))
 137
 138         def extract_field(pattern, name):
 139             return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None
 140
 141         description = extract_field(self._DESCRIPTION_REGEX, 'description')
 142         uploader = extract_field(self._UPLOADER_REGEX, 'uploader')
 143         view_count = str_to_int(extract_field(self._VIEW_COUNT_REGEX, 'view count'))
 144         comment_count = str_to_int(extract_field(self._COMMENT_COUNT_REGEX, 'comment count'))
 145         average_rating = float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating'))
 146
 147         categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
 148         categories = [c.strip() for c in categories_str.split(',')] if categories_str is not None else []
 149
 150         return {
 151             'id': video_id,
 152             'display_id': display_id,
 153             'title': title,
 154             'description': description,
 155             'thumbnail': thumbnail,
 156             'thumbnails': thumbnails,
 157             'duration': duration,
 158             'age_limit': age_limit,
 159             'uploader': uploader,
 160             'view_count': view_count,
 161             'comment_count': comment_count,
 162             'average_rating': average_rating,
 163             'categories': categories,
 164             'formats': formats,
 165         }
 166
 167
 168 class TNAFlixNetworkEmbedIE(TNAFlixNetworkBaseIE):
 169     _VALID_URL = r'https?://player\.(?:tna|emp)flix\.com/video/(?P<id>\d+)'
 170
 171     _TITLE_REGEX = r'<title>([^<]+)</title>'
 172
 173     _TESTS = [{
 174         'url': 'https://player.tnaflix.com/video/6538',
 175         'info_dict': {
 176             'id': '6538',
 177             'display_id': '6538',
 178             'ext': 'mp4',
 179             'title': 'Educational xxx video',
 180             'thumbnail': r're:https?://.*\.jpg$',
 181             'age_limit': 18,
 182         },
 183         'params': {
 184             'skip_download': True,
 185         },
 186     }, {
 187         'url': 'https://player.empflix.com/video/33051',
 188         'only_matching': True,
 189     }]
 190
 191     @staticmethod
 192     def _extract_urls(webpage):
 193         return [url for _, url in re.findall(
 194             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.(?:tna|emp)flix\.com/video/\d+)\1',
 195             webpage)]
 196
 197
 198 class TNAFlixIE(TNAFlixNetworkBaseIE):
 199     _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
 200
 201     _TITLE_REGEX = r'<title>(.+?) - (?:TNAFlix Porn Videos|TNAFlix\.com)</title>'
 202     _DESCRIPTION_REGEX = r'(?s)>Description:</[^>]+>(.+?)<'
 203     _UPLOADER_REGEX = r'<i>\s*Verified Member\s*</i>\s*<h\d+>(.+?)<'
 204     _CATEGORIES_REGEX = r'(?s)<span[^>]*>Categories:</span>(.+?)</div>'
 205
 206     _TESTS = [{
 207         # anonymous uploader, no categories
 208         'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
 209         'md5': 'ecf3498417d09216374fc5907f9c6ec0',
 210         'info_dict': {
 211             'id': '553878',
 212             'display_id': 'Carmella-Decesare-striptease',
 213             'ext': 'mp4',
 214             'title': 'Carmella Decesare - striptease',
 215             'thumbnail': r're:https?://.*\.jpg$',
 216             'duration': 91,
 217             'age_limit': 18,
 218             'categories': ['Porn Stars'],
 219         }
 220     }, {
 221         # non-anonymous uploader, categories
 222         'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
 223         'md5': '0f5d4d490dbfd117b8607054248a07c0',
 224         'info_dict': {
 225             'id': '6538',
 226             'display_id': 'Educational-xxx-video',
 227             'ext': 'mp4',
 228             'title': 'Educational xxx video',
 229             'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
 230             'thumbnail': r're:https?://.*\.jpg$',
 231             'duration': 164,
 232             'age_limit': 18,
 233             'uploader': 'bobwhite39',
 234             'categories': ['Amateur Porn', 'Squirting Videos', 'Teen Girls 18+'],
 235         }
 236     }, {
 237         'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
 238         'only_matching': True,
 239     }]
 240
 241
 242 class EMPFlixIE(TNAFlixNetworkBaseIE):
 243     _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
 244
 245     _HOST = 'emp'
 246     _VKEY_SUFFIX = '-1'
 247     _UPLOADER_REGEX = r'<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)</li>'
 248
 249     _TESTS = [{
 250         'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
 251         'md5': 'b1bc15b6412d33902d6e5952035fcabc',
 252         'info_dict': {
 253             'id': '33051',
 254             'display_id': 'Amateur-Finger-Fuck',
 255             'ext': 'mp4',
 256             'title': 'Amateur Finger Fuck',
 257             'description': 'Amateur solo finger fucking.',
 258             'thumbnail': r're:https?://.*\.jpg$',
 259             'duration': 83,
 260             'age_limit': 18,
 261             'uploader': 'cwbike',
 262             'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'],
 263         }
 264     }, {
 265         'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
 266         'only_matching': True,
 267     }]
 268
 269
 270 class MovieFapIE(TNAFlixNetworkBaseIE):
 271     _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html'
 272
 273     _VIEW_COUNT_REGEX = r'<br>Views\s*<strong>([\d,.]+)</strong>'
 274     _COMMENT_COUNT_REGEX = r'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>'
 275     _AVERAGE_RATING_REGEX = r'Current Rating\s*<br>\s*<strong>([\d.]+)</strong>'
 276     _CATEGORIES_REGEX = r'(?s)<div[^>]+id="vid_info"[^>]*>\s*<div[^>]*>.+?</div>(.*?)<br>'
 277
 278     _TESTS = [{
 279         # normal, multi-format video
 280         'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
 281         'md5': '26624b4e2523051b550067d547615906',
 282         'info_dict': {
 283             'id': 'be9867c9416c19f54a4a',
 284             'display_id': 'experienced-milf-amazing-handjob',
 285             'ext': 'mp4',
 286             'title': 'Experienced MILF Amazing Handjob',
 287             'description': 'Experienced MILF giving an Amazing Handjob',
 288             'thumbnail': r're:https?://.*\.jpg$',
 289             'age_limit': 18,
 290             'uploader': 'darvinfred06',
 291             'view_count': int,
 292             'comment_count': int,
 293             'average_rating': float,
 294             'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'],
 295         }
 296     }, {
 297         # quirky single-format case where the extension is given as fid, but the video is really an flv
 298         'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
 299         'md5': 'fa56683e291fc80635907168a743c9ad',
 300         'info_dict': {
 301             'id': 'e5da0d3edce5404418f5',
 302             'display_id': 'jeune-couple-russe',
 303             'ext': 'flv',
 304             'title': 'Jeune Couple Russe',
 305             'description': 'Amateur',
 306             'thumbnail': r're:https?://.*\.jpg$',
 307             'age_limit': 18,
 308             'uploader': 'whiskeyjar',
 309             'view_count': int,
 310             'comment_count': int,
 311             'average_rating': float,
 312             'categories': ['Amateur', 'Teen'],
 313         }
 314     }]