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