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             return re.sub(r'speed=\d+', 'speed=', unescapeHTML(vl.text))
  95
  96         video_link = cfg_xml.find('./videoLink')
  97         if video_link is not None:
  98             formats.append({
  99                 'url': extract_video_url(video_link),
 100                 'ext': xpath_text(cfg_xml, './videoConfig/type', 'type', default='flv'),
 101             })
 102
 103         for item in cfg_xml.findall('./quality/item'):
 104             video_link = item.find('./videoLink')
 105             if video_link is None:
 106                 continue
 107             res = item.find('res')
 108             format_id = None if res is None else res.text
 109             height = int_or_none(self._search_regex(
 110                 r'^(\d+)[pP]', format_id, 'height', default=None))
 111             formats.append({
 112                 'url': self._proto_relative_url(extract_video_url(video_link), 'http:'),
 113                 'format_id': format_id,
 114                 'height': height,
 115             })
 116
 117         self._sort_formats(formats)
 118
 119         thumbnail = self._proto_relative_url(
 120             xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:')
 121         thumbnails = self._extract_thumbnails(cfg_xml)
 122
 123         title = None
 124         if self._TITLE_REGEX:
 125             title = self._html_search_regex(
 126                 self._TITLE_REGEX, webpage, 'title', default=None)
 127         if not title:
 128             title = self._og_search_title(webpage)
 129
 130         age_limit = self._rta_search(webpage) or 18
 131
 132         duration = parse_duration(self._html_search_meta(
 133             'duration', webpage, 'duration', default=None))
 134
 135         def extract_field(pattern, name):
 136             return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None
 137
 138         description = extract_field(self._DESCRIPTION_REGEX, 'description')
 139         uploader = extract_field(self._UPLOADER_REGEX, 'uploader')
 140         view_count = str_to_int(extract_field(self._VIEW_COUNT_REGEX, 'view count'))
 141         comment_count = str_to_int(extract_field(self._COMMENT_COUNT_REGEX, 'comment count'))
 142         average_rating = float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating'))
 143
 144         categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
 145         categories = [c.strip() for c in categories_str.split(',')] if categories_str is not None else []
 146
 147         return {
 148             'id': video_id,
 149             'display_id': display_id,
 150             'title': title,
 151             'description': description,
 152             'thumbnail': thumbnail,
 153             'thumbnails': thumbnails,
 154             'duration': duration,
 155             'age_limit': age_limit,
 156             'uploader': uploader,
 157             'view_count': view_count,
 158             'comment_count': comment_count,
 159             'average_rating': average_rating,
 160             'categories': categories,
 161             'formats': formats,
 162         }
 163
 164
 165 class TNAFlixNetworkEmbedIE(TNAFlixNetworkBaseIE):
 166     _VALID_URL = r'https?://player\.(?:tna|emp)flix\.com/video/(?P<id>\d+)'
 167
 168     _TITLE_REGEX = r'<title>([^<]+)</title>'
 169
 170     _TESTS = [{
 171         'url': 'https://player.tnaflix.com/video/6538',
 172         'info_dict': {
 173             'id': '6538',
 174             'display_id': '6538',
 175             'ext': 'mp4',
 176             'title': 'Educational xxx video',
 177             'thumbnail': r're:https?://.*\.jpg$',
 178             'age_limit': 18,
 179         },
 180         'params': {
 181             'skip_download': True,
 182         },
 183     }, {
 184         'url': 'https://player.empflix.com/video/33051',
 185         'only_matching': True,
 186     }]
 187
 188     @staticmethod
 189     def _extract_urls(webpage):
 190         return [url for _, url in re.findall(
 191             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.(?:tna|emp)flix\.com/video/\d+)\1',
 192             webpage)]
 193
 194
 195 class TNAFlixIE(TNAFlixNetworkBaseIE):
 196     _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
 197
 198     _TITLE_REGEX = r'<title>(.+?) - (?:TNAFlix Porn Videos|TNAFlix\.com)</title>'
 199     _DESCRIPTION_REGEX = r'(?s)>Description:</[^>]+>(.+?)<'
 200     _UPLOADER_REGEX = r'<i>\s*Verified Member\s*</i>\s*<h\d+>(.+?)<'
 201     _CATEGORIES_REGEX = r'(?s)<span[^>]*>Categories:</span>(.+?)</div>'
 202
 203     _TESTS = [{
 204         # anonymous uploader, no categories
 205         'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
 206         'md5': 'ecf3498417d09216374fc5907f9c6ec0',
 207         'info_dict': {
 208             'id': '553878',
 209             'display_id': 'Carmella-Decesare-striptease',
 210             'ext': 'mp4',
 211             'title': 'Carmella Decesare - striptease',
 212             'thumbnail': r're:https?://.*\.jpg$',
 213             'duration': 91,
 214             'age_limit': 18,
 215             'categories': ['Porn Stars'],
 216         }
 217     }, {
 218         # non-anonymous uploader, categories
 219         'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
 220         'md5': '0f5d4d490dbfd117b8607054248a07c0',
 221         'info_dict': {
 222             'id': '6538',
 223             'display_id': 'Educational-xxx-video',
 224             'ext': 'mp4',
 225             'title': 'Educational xxx video',
 226             'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
 227             'thumbnail': r're:https?://.*\.jpg$',
 228             'duration': 164,
 229             'age_limit': 18,
 230             'uploader': 'bobwhite39',
 231             'categories': ['Amateur Porn', 'Squirting Videos', 'Teen Girls 18+'],
 232         }
 233     }, {
 234         'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
 235         'only_matching': True,
 236     }]
 237
 238
 239 class EMPFlixIE(TNAFlixNetworkBaseIE):
 240     _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
 241
 242     _UPLOADER_REGEX = r'<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)</li>'
 243
 244     _TESTS = [{
 245         'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
 246         'md5': 'b1bc15b6412d33902d6e5952035fcabc',
 247         'info_dict': {
 248             'id': '33051',
 249             'display_id': 'Amateur-Finger-Fuck',
 250             'ext': 'mp4',
 251             'title': 'Amateur Finger Fuck',
 252             'description': 'Amateur solo finger fucking.',
 253             'thumbnail': r're:https?://.*\.jpg$',
 254             'duration': 83,
 255             'age_limit': 18,
 256             'uploader': 'cwbike',
 257             'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'],
 258         }
 259     }, {
 260         'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
 261         'only_matching': True,
 262     }]
 263
 264
 265 class MovieFapIE(TNAFlixNetworkBaseIE):
 266     _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html'
 267
 268     _VIEW_COUNT_REGEX = r'<br>Views\s*<strong>([\d,.]+)</strong>'
 269     _COMMENT_COUNT_REGEX = r'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>'
 270     _AVERAGE_RATING_REGEX = r'Current Rating\s*<br>\s*<strong>([\d.]+)</strong>'
 271     _CATEGORIES_REGEX = r'(?s)<div[^>]+id="vid_info"[^>]*>\s*<div[^>]*>.+?</div>(.*?)<br>'
 272
 273     _TESTS = [{
 274         # normal, multi-format video
 275         'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
 276         'md5': '26624b4e2523051b550067d547615906',
 277         'info_dict': {
 278             'id': 'be9867c9416c19f54a4a',
 279             'display_id': 'experienced-milf-amazing-handjob',
 280             'ext': 'mp4',
 281             'title': 'Experienced MILF Amazing Handjob',
 282             'description': 'Experienced MILF giving an Amazing Handjob',
 283             'thumbnail': r're:https?://.*\.jpg$',
 284             'age_limit': 18,
 285             'uploader': 'darvinfred06',
 286             'view_count': int,
 287             'comment_count': int,
 288             'average_rating': float,
 289             'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'],
 290         }
 291     }, {
 292         # quirky single-format case where the extension is given as fid, but the video is really an flv
 293         'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
 294         'md5': 'fa56683e291fc80635907168a743c9ad',
 295         'info_dict': {
 296             'id': 'e5da0d3edce5404418f5',
 297             'display_id': 'jeune-couple-russe',
 298             'ext': 'flv',
 299             'title': 'Jeune Couple Russe',
 300             'description': 'Amateur',
 301             'thumbnail': r're:https?://.*\.jpg$',
 302             'age_limit': 18,
 303             'uploader': 'whiskeyjar',
 304             'view_count': int,
 305             'comment_count': int,
 306             'average_rating': float,
 307             'categories': ['Amateur', 'Teen'],
 308         }
 309     }]