youtube_dlc/extractor/youporn.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     int_or_none,
   8     str_to_int,
   9     unescapeHTML,
  10     unified_strdate,
  11     url_or_none,
  12 )
  13 from ..aes import aes_decrypt_text
  14
  15
  16 class YouPornIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
  18     _TESTS = [{
  19         'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  20         'md5': '3744d24c50438cf5b6f6d59feb5055c2',
  21         'info_dict': {
  22             'id': '505835',
  23             'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
  24             'ext': 'mp4',
  25             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
  26             'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
  27             'thumbnail': r're:^https?://.*\.jpg$',
  28             'uploader': 'Ask Dan And Jennifer',
  29             'upload_date': '20101217',
  30             'average_rating': int,
  31             'view_count': int,
  32             'categories': list,
  33             'tags': list,
  34             'age_limit': 18,
  35         },
  36     }, {
  37         # Unknown uploader
  38         'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
  39         'info_dict': {
  40             'id': '561726',
  41             'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
  42             'ext': 'mp4',
  43             'title': 'Big Tits Awesome Brunette On amazing webcam show',
  44             'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
  45             'thumbnail': r're:^https?://.*\.jpg$',
  46             'uploader': 'Unknown',
  47             'upload_date': '20110418',
  48             'average_rating': int,
  49             'view_count': int,
  50             'categories': list,
  51             'tags': list,
  52             'age_limit': 18,
  53         },
  54         'params': {
  55             'skip_download': True,
  56         },
  57     }, {
  58         'url': 'https://www.youporn.com/embed/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  59         'only_matching': True,
  60     }, {
  61         'url': 'http://www.youporn.com/watch/505835',
  62         'only_matching': True,
  63     }, {
  64         'url': 'https://www.youporn.com/watch/13922959/femdom-principal/',
  65         'only_matching': True,
  66     }]
  67
  68     @staticmethod
  69     def _extract_urls(webpage):
  70         return re.findall(
  71             r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)',
  72             webpage)
  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') or video_id
  78
  79         webpage = self._download_webpage(
  80             'http://www.youporn.com/watch/%s' % video_id, display_id,
  81             headers={'Cookie': 'age_verified=1'})
  82
  83         title = self._html_search_regex(
  84             r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
  85             webpage, 'title', default=None) or self._og_search_title(
  86             webpage, default=None) or self._html_search_meta(
  87             'title', webpage, fatal=True)
  88
  89         links = []
  90
  91         # Main source
  92         definitions = self._parse_json(
  93             self._search_regex(
  94                 r'mediaDefinition\s*[=:]\s*(\[.+?\])\s*[;,]', webpage,
  95                 'media definitions', default='[]'),
  96             video_id, fatal=False)
  97         if definitions:
  98             for definition in definitions:
  99                 if not isinstance(definition, dict):
 100                     continue
 101                 video_url = url_or_none(definition.get('videoUrl'))
 102                 if video_url:
 103                     links.append(video_url)
 104
 105         # Fallback #1, this also contains extra low quality 180p format
 106         for _, link in re.findall(r'<a[^>]+href=(["\'])(http(?:(?!\1).)+\.mp4(?:(?!\1).)*)\1[^>]+title=["\']Download [Vv]ideo', webpage):
 107             links.append(link)
 108
 109         # Fallback #2 (unavailable as at 22.06.2017)
 110         sources = self._search_regex(
 111             r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None)
 112         if sources:
 113             for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
 114                 links.append(link)
 115
 116         # Fallback #3 (unavailable as at 22.06.2017)
 117         for _, link in re.findall(
 118                 r'(?:videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
 119             links.append(link)
 120
 121         # Fallback #4, encrypted links (unavailable as at 22.06.2017)
 122         for _, encrypted_link in re.findall(
 123                 r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage):
 124             links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8'))
 125
 126         formats = []
 127         for video_url in set(unescapeHTML(link) for link in links):
 128             f = {
 129                 'url': video_url,
 130             }
 131             # Video URL's path looks like this:
 132             #  /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 133             #  /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 134             #  /videos/201703/11/109285532/1080P_4000K_109285532.mp4
 135             # We will benefit from it by extracting some metadata
 136             mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
 137             if mobj:
 138                 height = int(mobj.group('height'))
 139                 bitrate = int(mobj.group('bitrate'))
 140                 f.update({
 141                     'format_id': '%dp-%dk' % (height, bitrate),
 142                     'height': height,
 143                     'tbr': bitrate,
 144                 })
 145             formats.append(f)
 146         self._sort_formats(formats)
 147
 148         description = self._html_search_regex(
 149             r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>',
 150             webpage, 'description',
 151             default=None) or self._og_search_description(
 152             webpage, default=None)
 153         thumbnail = self._search_regex(
 154             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
 155             webpage, 'thumbnail', fatal=False, group='thumbnail')
 156
 157         uploader = self._html_search_regex(
 158             r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
 159             webpage, 'uploader', fatal=False)
 160         upload_date = unified_strdate(self._html_search_regex(
 161             [r'UPLOADED:\s*<span>([^<]+)',
 162              r'Date\s+[Aa]dded:\s*<span>([^<]+)',
 163              r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>'],
 164             webpage, 'upload date', fatal=False))
 165
 166         age_limit = self._rta_search(webpage)
 167
 168         average_rating = int_or_none(self._search_regex(
 169             r'<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
 170             webpage, 'average rating', fatal=False))
 171
 172         view_count = str_to_int(self._search_regex(
 173             r'(?s)<div[^>]+class=(["\']).*?\bvideoInfoViews\b.*?\1[^>]*>.*?(?P<count>[\d,.]+)<',
 174             webpage, 'view count', fatal=False, group='count'))
 175         comment_count = str_to_int(self._search_regex(
 176             r'>All [Cc]omments? \(([\d,.]+)\)',
 177             webpage, 'comment count', default=None))
 178
 179         def extract_tag_box(regex, title):
 180             tag_box = self._search_regex(regex, webpage, title, default=None)
 181             if not tag_box:
 182                 return []
 183             return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
 184
 185         categories = extract_tag_box(
 186             r'(?s)Categories:.*?</[^>]+>(.+?)</div>', 'categories')
 187         tags = extract_tag_box(
 188             r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>',
 189             'tags')
 190
 191         return {
 192             'id': video_id,
 193             'display_id': display_id,
 194             'title': title,
 195             'description': description,
 196             'thumbnail': thumbnail,
 197             'uploader': uploader,
 198             'upload_date': upload_date,
 199             'average_rating': average_rating,
 200             'view_count': view_count,
 201             'comment_count': comment_count,
 202             'categories': categories,
 203             'tags': tags,
 204             'age_limit': age_limit,
 205             'formats': formats,
 206         }