Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/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$',
  28             'uploader': 'Ask Dan And Jennifer',
  29             'upload_date': '20101217',
  30             'average_rating': int,
  31             'view_count': int,
  32             'comment_count': int,
  33             'categories': list,
  34             'tags': list,
  35             'age_limit': 18,
  36         },
  37     }, {
  38         # Unknown uploader
  39         'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
  40         'info_dict': {
  41             'id': '561726',
  42             'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
  43             'ext': 'mp4',
  44             'title': 'Big Tits Awesome Brunette On amazing webcam show',
  45             'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
  46             'thumbnail': r're:^https?://.*\.jpg$',
  47             'uploader': 'Unknown',
  48             'upload_date': '20110418',
  49             'average_rating': int,
  50             'view_count': int,
  51             'comment_count': int,
  52             'categories': list,
  53             'tags': list,
  54             'age_limit': 18,
  55         },
  56         'params': {
  57             'skip_download': True,
  58         },
  59     }, {
  60         'url': 'https://www.youporn.com/embed/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  61         'only_matching': True,
  62     }, {
  63         'url': 'http://www.youporn.com/watch/505835',
  64         'only_matching': True,
  65     }]
  66
  67     @staticmethod
  68     def _extract_urls(webpage):
  69         return re.findall(
  70             r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)',
  71             webpage)
  72
  73     def _real_extract(self, url):
  74         mobj = re.match(self._VALID_URL, url)
  75         video_id = mobj.group('id')
  76         display_id = mobj.group('display_id') or video_id
  77
  78         webpage = self._download_webpage(
  79             'http://www.youporn.com/watch/%s' % video_id, display_id,
  80             headers={'Cookie': 'age_verified=1'})
  81
  82         title = self._html_search_regex(
  83             r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
  84             webpage, 'title', default=None) or self._og_search_title(
  85             webpage, default=None) or self._html_search_meta(
  86             'title', webpage, fatal=True)
  87
  88         links = []
  89
  90         # Main source
  91         definitions = self._parse_json(
  92             self._search_regex(
  93                 r'mediaDefinition\s*=\s*(\[.+?\]);', webpage,
  94                 'media definitions', default='[]'),
  95             video_id, fatal=False)
  96         if definitions:
  97             for definition in definitions:
  98                 if not isinstance(definition, dict):
  99                     continue
 100                 video_url = url_or_none(definition.get('videoUrl'))
 101                 if video_url:
 102                     links.append(video_url)
 103
 104         # Fallback #1, this also contains extra low quality 180p format
 105         for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage):
 106             links.append(link)
 107
 108         # Fallback #2 (unavailable as at 22.06.2017)
 109         sources = self._search_regex(
 110             r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None)
 111         if sources:
 112             for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
 113                 links.append(link)
 114
 115         # Fallback #3 (unavailable as at 22.06.2017)
 116         for _, link in re.findall(
 117                 r'(?:videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
 118             links.append(link)
 119
 120         # Fallback #4, encrypted links (unavailable as at 22.06.2017)
 121         for _, encrypted_link in re.findall(
 122                 r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage):
 123             links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8'))
 124
 125         formats = []
 126         for video_url in set(unescapeHTML(link) for link in links):
 127             f = {
 128                 'url': video_url,
 129             }
 130             # Video URL's path looks like this:
 131             #  /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 132             #  /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 133             # We will benefit from it by extracting some metadata
 134             mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url)
 135             if mobj:
 136                 height = int(mobj.group('height'))
 137                 bitrate = int(mobj.group('bitrate'))
 138                 f.update({
 139                     'format_id': '%dp-%dk' % (height, bitrate),
 140                     'height': height,
 141                     'tbr': bitrate,
 142                 })
 143             formats.append(f)
 144         self._sort_formats(formats)
 145
 146         description = self._html_search_regex(
 147             r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>',
 148             webpage, 'description',
 149             default=None) or self._og_search_description(
 150             webpage, default=None)
 151         thumbnail = self._search_regex(
 152             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
 153             webpage, 'thumbnail', fatal=False, group='thumbnail')
 154
 155         uploader = self._html_search_regex(
 156             r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
 157             webpage, 'uploader', fatal=False)
 158         upload_date = unified_strdate(self._html_search_regex(
 159             [r'Date\s+[Aa]dded:\s*<span>([^<]+)',
 160              r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>'],
 161             webpage, 'upload date', fatal=False))
 162
 163         age_limit = self._rta_search(webpage)
 164
 165         average_rating = int_or_none(self._search_regex(
 166             r'<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
 167             webpage, 'average rating', fatal=False))
 168
 169         view_count = str_to_int(self._search_regex(
 170             r'(?s)<div[^>]+class=(["\']).*?\bvideoInfoViews\b.*?\1[^>]*>.*?(?P<count>[\d,.]+)<',
 171             webpage, 'view count', fatal=False, group='count'))
 172         comment_count = str_to_int(self._search_regex(
 173             r'>All [Cc]omments? \(([\d,.]+)\)',
 174             webpage, 'comment count', fatal=False))
 175
 176         def extract_tag_box(regex, title):
 177             tag_box = self._search_regex(regex, webpage, title, default=None)
 178             if not tag_box:
 179                 return []
 180             return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
 181
 182         categories = extract_tag_box(
 183             r'(?s)Categories:.*?</[^>]+>(.+?)</div>', 'categories')
 184         tags = extract_tag_box(
 185             r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>',
 186             'tags')
 187
 188         return {
 189             'id': video_id,
 190             'display_id': display_id,
 191             'title': title,
 192             'description': description,
 193             'thumbnail': thumbnail,
 194             'uploader': uploader,
 195             'upload_date': upload_date,
 196             'average_rating': average_rating,
 197             'view_count': view_count,
 198             'comment_count': comment_count,
 199             'categories': categories,
 200             'tags': tags,
 201             'age_limit': age_limit,
 202             'formats': formats,
 203         }