_ 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     xpath_text,
  14 )
  15
  16
  17 class TNAFlixNetworkBaseIE(InfoExtractor):
  18     # May be overridden in descendants if necessary
  19     _CONFIG_REGEX = [
  20         r'flashvars\.config\s*=\s*escape\("([^"]+)"',
  21         r'<input[^>]+name="config\d?" value="([^"]+)"',
  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('#', 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 = re.match(self._VALID_URL, url)
  73         video_id = mobj.group('id')
  74         display_id = mobj.group('display_id') if 'display_id' in mobj.groupdict() else video_id
  75
  76         webpage = self._download_webpage(url, display_id)
  77
  78         cfg_url = self._proto_relative_url(self._html_search_regex(
  79             self._CONFIG_REGEX, webpage, 'flashvars.config', default=None), 'http:')
  80
  81         if not cfg_url:
  82             inputs = self._hidden_inputs(webpage)
  83             cfg_url = 'https://cdn-fck.tnaflix.com/tnaflix/%s.fid?key=%s' % (inputs['vkey'], inputs['nkey'])
  84
  85         cfg_xml = self._download_xml(
  86             cfg_url, display_id, 'Downloading metadata',
  87             transform_source=fix_xml_ampersands)
  88
  89         formats = []
  90
  91         def extract_video_url(vl):
  92             return re.sub('speed=\d+', 'speed=', vl.text)
  93
  94         video_link = cfg_xml.find('./videoLink')
  95         if video_link is not None:
  96             formats.append({
  97                 'url': extract_video_url(video_link),
  98                 'ext': xpath_text(cfg_xml, './videoConfig/type', 'type', default='flv'),
  99             })
 100
 101         for item in cfg_xml.findall('./quality/item'):
 102             video_link = item.find('./videoLink')
 103             if video_link is None:
 104                 continue
 105             res = item.find('res')
 106             format_id = None if res is None else res.text
 107             height = int_or_none(self._search_regex(
 108                 r'^(\d+)[pP]', format_id, 'height', default=None))
 109             formats.append({
 110                 'url': self._proto_relative_url(extract_video_url(video_link), 'http:'),
 111                 'format_id': format_id,
 112                 'height': height,
 113             })
 114
 115         self._sort_formats(formats)
 116
 117         thumbnail = self._proto_relative_url(
 118             xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:')
 119         thumbnails = self._extract_thumbnails(cfg_xml)
 120
 121         title = None
 122         if self._TITLE_REGEX:
 123             title = self._html_search_regex(
 124                 self._TITLE_REGEX, webpage, 'title', default=None)
 125         if not title:
 126             title = self._og_search_title(webpage)
 127
 128         age_limit = self._rta_search(webpage) or 18
 129
 130         duration = parse_duration(self._html_search_meta(
 131             'duration', webpage, 'duration', default=None))
 132
 133         def extract_field(pattern, name):
 134             return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None
 135
 136         description = extract_field(self._DESCRIPTION_REGEX, 'description')
 137         uploader = extract_field(self._UPLOADER_REGEX, 'uploader')
 138         view_count = str_to_int(extract_field(self._VIEW_COUNT_REGEX, 'view count'))
 139         comment_count = str_to_int(extract_field(self._COMMENT_COUNT_REGEX, 'comment count'))
 140         average_rating = float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating'))
 141
 142         categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
 143         categories = [c.strip() for c in categories_str.split(',')] if categories_str is not None else []
 144
 145         return {
 146             'id': video_id,
 147             'display_id': display_id,
 148             'title': title,
 149             'description': description,
 150             'thumbnail': thumbnail,
 151             'thumbnails': thumbnails,
 152             'duration': duration,
 153             'age_limit': age_limit,
 154             'uploader': uploader,
 155             'view_count': view_count,
 156             'comment_count': comment_count,
 157             'average_rating': average_rating,
 158             'categories': categories,
 159             'formats': formats,
 160         }
 161
 162
 163 class TNAFlixNetworkEmbedIE(TNAFlixNetworkBaseIE):
 164     _VALID_URL = r'https?://player\.(?:tna|emp)flix\.com/video/(?P<id>\d+)'
 165
 166     _TITLE_REGEX = r'<title>([^<]+)</title>'
 167
 168     _TESTS = [{
 169         'url': 'https://player.tnaflix.com/video/6538',
 170         'info_dict': {
 171             'id': '6538',
 172             'display_id': '6538',
 173             'ext': 'mp4',
 174             'title': 'Educational xxx video',
 175             'thumbnail': 're:https?://.*\.jpg$',
 176             'age_limit': 18,
 177         },
 178         'params': {
 179             'skip_download': True,
 180         },
 181     }, {
 182         'url': 'https://player.empflix.com/video/33051',
 183         'only_matching': True,
 184     }]
 185
 186     @staticmethod
 187     def _extract_urls(webpage):
 188         return [url for _, url in re.findall(
 189             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.(?:tna|emp)flix\.com/video/\d+)\1',
 190             webpage)]
 191
 192
 193 class TNAFlixIE(TNAFlixNetworkBaseIE):
 194     _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
 195
 196     _TITLE_REGEX = r'<title>(.+?) - (?:TNAFlix Porn Videos|TNAFlix\.com)</title>'
 197     _DESCRIPTION_REGEX = r'(?s)>Description:</[^>]+>(.+?)<'
 198     _UPLOADER_REGEX = r'<i>\s*Verified Member\s*</i>\s*<h\d+>(.+?)<'
 199     _CATEGORIES_REGEX = r'(?s)<span[^>]*>Categories:</span>(.+?)</div>'
 200
 201     _TESTS = [{
 202         # anonymous uploader, no categories
 203         'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
 204         'md5': '7e569419fe6d69543d01e6be22f5f7c4',
 205         'info_dict': {
 206             'id': '553878',
 207             'display_id': 'Carmella-Decesare-striptease',
 208             'ext': 'mp4',
 209             'title': 'Carmella Decesare - striptease',
 210             'thumbnail': 're:https?://.*\.jpg$',
 211             'duration': 91,
 212             'age_limit': 18,
 213             'categories': ['Porn Stars'],
 214         }
 215     }, {
 216         # non-anonymous uploader, categories
 217         'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
 218         'md5': 'fcba2636572895aba116171a899a5658',
 219         'info_dict': {
 220             'id': '6538',
 221             'display_id': 'Educational-xxx-video',
 222             'ext': 'flv',
 223             'title': 'Educational xxx video',
 224             'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
 225             'thumbnail': 're:https?://.*\.jpg$',
 226             'duration': 164,
 227             'age_limit': 18,
 228             'uploader': 'bobwhite39',
 229             'categories': ['Amateur Porn', 'Squirting Videos', 'Teen Girls 18+'],
 230         }
 231     }, {
 232         'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
 233         'only_matching': True,
 234     }]
 235
 236
 237 class EMPFlixIE(TNAFlixNetworkBaseIE):
 238     _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
 239
 240     _UPLOADER_REGEX = r'<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)</li>'
 241
 242     _TESTS = [{
 243         'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
 244         'md5': 'b1bc15b6412d33902d6e5952035fcabc',
 245         'info_dict': {
 246             'id': '33051',
 247             'display_id': 'Amateur-Finger-Fuck',
 248             'ext': 'mp4',
 249             'title': 'Amateur Finger Fuck',
 250             'description': 'Amateur solo finger fucking.',
 251             'thumbnail': 're:https?://.*\.jpg$',
 252             'duration': 83,
 253             'age_limit': 18,
 254             'uploader': 'cwbike',
 255             'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'],
 256         }
 257     }, {
 258         'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
 259         'only_matching': True,
 260     }]
 261
 262
 263 class MovieFapIE(TNAFlixNetworkBaseIE):
 264     _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html'
 265
 266     _VIEW_COUNT_REGEX = r'<br>Views\s*<strong>([\d,.]+)</strong>'
 267     _COMMENT_COUNT_REGEX = r'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>'
 268     _AVERAGE_RATING_REGEX = r'Current Rating\s*<br>\s*<strong>([\d.]+)</strong>'
 269     _CATEGORIES_REGEX = r'(?s)<div[^>]+id="vid_info"[^>]*>\s*<div[^>]*>.+?</div>(.*?)<br>'
 270
 271     _TESTS = [{
 272         # normal, multi-format video
 273         'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
 274         'md5': '26624b4e2523051b550067d547615906',
 275         'info_dict': {
 276             'id': 'be9867c9416c19f54a4a',
 277             'display_id': 'experienced-milf-amazing-handjob',
 278             'ext': 'mp4',
 279             'title': 'Experienced MILF Amazing Handjob',
 280             'description': 'Experienced MILF giving an Amazing Handjob',
 281             'thumbnail': 're:https?://.*\.jpg$',
 282             'age_limit': 18,
 283             'uploader': 'darvinfred06',
 284             'view_count': int,
 285             'comment_count': int,
 286             'average_rating': float,
 287             'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'],
 288         }
 289     }, {
 290         # quirky single-format case where the extension is given as fid, but the video is really an flv
 291         'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
 292         'md5': 'fa56683e291fc80635907168a743c9ad',
 293         'info_dict': {
 294             'id': 'e5da0d3edce5404418f5',
 295             'display_id': 'jeune-couple-russe',
 296             'ext': 'flv',
 297             'title': 'Jeune Couple Russe',
 298             'description': 'Amateur',
 299             'thumbnail': 're:https?://.*\.jpg$',
 300             'age_limit': 18,
 301             'uploader': 'whiskeyjar',
 302             'view_count': int,
 303             'comment_count': int,
 304             'average_rating': float,
 305             'categories': ['Amateur', 'Teen'],
 306         }
 307     }]