Raphaël G. Git Repositories - youtubedl/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         for display_id_key in ('display_id', 'display_id_2'):
  78             if display_id_key in mobj.groupdict():
  79                 display_id = mobj.group(display_id_key)
  80                 if display_id:
  81                     break
  82         else:
  83             display_id = video_id
  84
  85         webpage = self._download_webpage(url, display_id)
  86
  87         cfg_url = self._proto_relative_url(self._html_search_regex(
  88             self._CONFIG_REGEX, webpage, 'flashvars.config', default=None), 'http:')
  89
  90         if not cfg_url:
  91             inputs = self._hidden_inputs(webpage)
  92             cfg_url = ('https://cdn-fck.%sflix.com/%sflix/%s%s.fid?key=%s&VID=%s&premium=1&vip=1&alpha'
  93                        % (self._HOST, self._HOST, inputs['vkey'], self._VKEY_SUFFIX, inputs['nkey'], video_id))
  94
  95         cfg_xml = self._download_xml(
  96             cfg_url, display_id, 'Downloading metadata',
  97             transform_source=fix_xml_ampersands)
  98
  99         formats = []
 100
 101         def extract_video_url(vl):
 102             # Any URL modification now results in HTTP Error 403: Forbidden
 103             return unescapeHTML(vl.text)
 104
 105         video_link = cfg_xml.find('./videoLink')
 106         if video_link is not None:
 107             formats.append({
 108                 'url': extract_video_url(video_link),
 109                 'ext': xpath_text(cfg_xml, './videoConfig/type', 'type', default='flv'),
 110             })
 111
 112         for item in cfg_xml.findall('./quality/item'):
 113             video_link = item.find('./videoLink')
 114             if video_link is None:
 115                 continue
 116             res = item.find('res')
 117             format_id = None if res is None else res.text
 118             height = int_or_none(self._search_regex(
 119                 r'^(\d+)[pP]', format_id, 'height', default=None))
 120             formats.append({
 121                 'url': self._proto_relative_url(extract_video_url(video_link), 'http:'),
 122                 'format_id': format_id,
 123                 'height': height,
 124             })
 125
 126         self._sort_formats(formats)
 127
 128         thumbnail = self._proto_relative_url(
 129             xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:')
 130         thumbnails = self._extract_thumbnails(cfg_xml)
 131
 132         title = None
 133         if self._TITLE_REGEX:
 134             title = self._html_search_regex(
 135                 self._TITLE_REGEX, webpage, 'title', default=None)
 136         if not title:
 137             title = self._og_search_title(webpage)
 138
 139         age_limit = self._rta_search(webpage) or 18
 140
 141         duration = parse_duration(self._html_search_meta(
 142             'duration', webpage, 'duration', default=None))
 143
 144         def extract_field(pattern, name):
 145             return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None
 146
 147         description = extract_field(self._DESCRIPTION_REGEX, 'description')
 148         uploader = extract_field(self._UPLOADER_REGEX, 'uploader')
 149         view_count = str_to_int(extract_field(self._VIEW_COUNT_REGEX, 'view count'))
 150         comment_count = str_to_int(extract_field(self._COMMENT_COUNT_REGEX, 'comment count'))
 151         average_rating = float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating'))
 152
 153         categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
 154         categories = [c.strip() for c in categories_str.split(',')] if categories_str is not None else []
 155
 156         return {
 157             'id': video_id,
 158             'display_id': display_id,
 159             'title': title,
 160             'description': description,
 161             'thumbnail': thumbnail,
 162             'thumbnails': thumbnails,
 163             'duration': duration,
 164             'age_limit': age_limit,
 165             'uploader': uploader,
 166             'view_count': view_count,
 167             'comment_count': comment_count,
 168             'average_rating': average_rating,
 169             'categories': categories,
 170             'formats': formats,
 171         }
 172
 173
 174 class TNAFlixNetworkEmbedIE(TNAFlixNetworkBaseIE):
 175     _VALID_URL = r'https?://player\.(?:tna|emp)flix\.com/video/(?P<id>\d+)'
 176
 177     _TITLE_REGEX = r'<title>([^<]+)</title>'
 178
 179     _TESTS = [{
 180         'url': 'https://player.tnaflix.com/video/6538',
 181         'info_dict': {
 182             'id': '6538',
 183             'display_id': '6538',
 184             'ext': 'mp4',
 185             'title': 'Educational xxx video',
 186             'thumbnail': r're:https?://.*\.jpg$',
 187             'age_limit': 18,
 188         },
 189         'params': {
 190             'skip_download': True,
 191         },
 192     }, {
 193         'url': 'https://player.empflix.com/video/33051',
 194         'only_matching': True,
 195     }]
 196
 197     @staticmethod
 198     def _extract_urls(webpage):
 199         return [url for _, url in re.findall(
 200             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.(?:tna|emp)flix\.com/video/\d+)\1',
 201             webpage)]
 202
 203
 204 class TNAEMPFlixBaseIE(TNAFlixNetworkBaseIE):
 205     _DESCRIPTION_REGEX = r'(?s)>Description:</[^>]+>(.+?)<'
 206     _UPLOADER_REGEX = r'<span>by\s*<a[^>]+\bhref=["\']/profile/[^>]+>([^<]+)<'
 207     _CATEGORIES_REGEX = r'(?s)<span[^>]*>Categories:</span>(.+?)</div>'
 208
 209
 210 class TNAFlixIE(TNAEMPFlixBaseIE):
 211     _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
 212
 213     _TITLE_REGEX = r'<title>(.+?) - (?:TNAFlix Porn Videos|TNAFlix\.com)</title>'
 214
 215     _TESTS = [{
 216         # anonymous uploader, no categories
 217         'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
 218         'md5': '7e569419fe6d69543d01e6be22f5f7c4',
 219         'info_dict': {
 220             'id': '553878',
 221             'display_id': 'Carmella-Decesare-striptease',
 222             'ext': 'mp4',
 223             'title': 'Carmella Decesare - striptease',
 224             'thumbnail': r're:https?://.*\.jpg$',
 225             'duration': 91,
 226             'age_limit': 18,
 227             'categories': ['Porn Stars'],
 228         }
 229     }, {
 230         # non-anonymous uploader, categories
 231         'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
 232         'md5': '0f5d4d490dbfd117b8607054248a07c0',
 233         'info_dict': {
 234             'id': '6538',
 235             'display_id': 'Educational-xxx-video',
 236             'ext': 'mp4',
 237             'title': 'Educational xxx video',
 238             'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
 239             'thumbnail': r're:https?://.*\.jpg$',
 240             'duration': 164,
 241             'age_limit': 18,
 242             'uploader': 'bobwhite39',
 243             'categories': list,
 244         }
 245     }, {
 246         'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
 247         'only_matching': True,
 248     }]
 249
 250
 251 class EMPFlixIE(TNAEMPFlixBaseIE):
 252     _VALID_URL = r'https?://(?:www\.)?empflix\.com/(?:videos/(?P<display_id>.+?)-|[^/]+/(?P<display_id_2>[^/]+)/video)(?P<id>[0-9]+)'
 253
 254     _HOST = 'emp'
 255     _VKEY_SUFFIX = '-1'
 256
 257     _TESTS = [{
 258         'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
 259         'md5': 'bc30d48b91a7179448a0bda465114676',
 260         'info_dict': {
 261             'id': '33051',
 262             'display_id': 'Amateur-Finger-Fuck',
 263             'ext': 'mp4',
 264             'title': 'Amateur Finger Fuck',
 265             'description': 'Amateur solo finger fucking.',
 266             'thumbnail': r're:https?://.*\.jpg$',
 267             'duration': 83,
 268             'age_limit': 18,
 269             'uploader': 'cwbike',
 270             'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'],
 271         }
 272     }, {
 273         'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
 274         'only_matching': True,
 275     }, {
 276         'url': 'https://www.empflix.com/amateur-porn/Amateur-Finger-Fuck/video33051',
 277         'only_matching': True,
 278     }]
 279
 280
 281 class MovieFapIE(TNAFlixNetworkBaseIE):
 282     _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html'
 283
 284     _VIEW_COUNT_REGEX = r'<br>Views\s*<strong>([\d,.]+)</strong>'
 285     _COMMENT_COUNT_REGEX = r'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>'
 286     _AVERAGE_RATING_REGEX = r'Current Rating\s*<br>\s*<strong>([\d.]+)</strong>'
 287     _CATEGORIES_REGEX = r'(?s)<div[^>]+id="vid_info"[^>]*>\s*<div[^>]*>.+?</div>(.*?)<br>'
 288
 289     _TESTS = [{
 290         # normal, multi-format video
 291         'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
 292         'md5': '26624b4e2523051b550067d547615906',
 293         'info_dict': {
 294             'id': 'be9867c9416c19f54a4a',
 295             'display_id': 'experienced-milf-amazing-handjob',
 296             'ext': 'mp4',
 297             'title': 'Experienced MILF Amazing Handjob',
 298             'description': 'Experienced MILF giving an Amazing Handjob',
 299             'thumbnail': r're:https?://.*\.jpg$',
 300             'age_limit': 18,
 301             'uploader': 'darvinfred06',
 302             'view_count': int,
 303             'comment_count': int,
 304             'average_rating': float,
 305             'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'],
 306         }
 307     }, {
 308         # quirky single-format case where the extension is given as fid, but the video is really an flv
 309         'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
 310         'md5': 'fa56683e291fc80635907168a743c9ad',
 311         'info_dict': {
 312             'id': 'e5da0d3edce5404418f5',
 313             'display_id': 'jeune-couple-russe',
 314             'ext': 'flv',
 315             'title': 'Jeune Couple Russe',
 316             'description': 'Amateur',
 317             'thumbnail': r're:https?://.*\.jpg$',
 318             'age_limit': 18,
 319             'uploader': 'whiskeyjar',
 320             'view_count': int,
 321             'comment_count': int,
 322             'average_rating': float,
 323             'categories': ['Amateur', 'Teen'],
 324         }
 325     }]