youtube-dl

Another place where youtube-dl lives on
git clone git://git.oshgnacknak.de/youtube-dl.git
Log | Files | Refs | README | LICENSE

youporn.py (7294B)


      1 from __future__ import unicode_literals
      2 
      3 import re
      4 
      5 from .common import InfoExtractor
      6 from ..utils import (
      7     extract_attributes,
      8     int_or_none,
      9     str_to_int,
     10     unified_strdate,
     11     url_or_none,
     12 )
     13 
     14 
     15 class YouPornIE(InfoExtractor):
     16     _VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
     17     _TESTS = [{
     18         'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
     19         'md5': '3744d24c50438cf5b6f6d59feb5055c2',
     20         'info_dict': {
     21             'id': '505835',
     22             'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
     23             'ext': 'mp4',
     24             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
     25             'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
     26             'thumbnail': r're:^https?://.*\.jpg$',
     27             'duration': 210,
     28             'uploader': 'Ask Dan And Jennifer',
     29             'upload_date': '20101217',
     30             'average_rating': int,
     31             'view_count': int,
     32             'categories': list,
     33             'tags': list,
     34             'age_limit': 18,
     35         },
     36         'skip': 'This video has been disabled',
     37     }, {
     38         # Unknown uploader
     39         'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
     40         'info_dict': {
     41             'id': '561726',
     42             'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
     43             'ext': 'mp4',
     44             'title': 'Big Tits Awesome Brunette On amazing webcam show',
     45             'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
     46             'thumbnail': r're:^https?://.*\.jpg$',
     47             'uploader': 'Unknown',
     48             'upload_date': '20110418',
     49             'average_rating': int,
     50             'view_count': int,
     51             'categories': list,
     52             'tags': list,
     53             'age_limit': 18,
     54         },
     55         'params': {
     56             'skip_download': True,
     57         },
     58         'skip': '404',
     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         'url': 'https://www.youporn.com/watch/13922959/femdom-principal/',
     67         'only_matching': True,
     68     }]
     69 
     70     @staticmethod
     71     def _extract_urls(webpage):
     72         return re.findall(
     73             r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)',
     74             webpage)
     75 
     76     def _real_extract(self, url):
     77         mobj = re.match(self._VALID_URL, url)
     78         video_id = mobj.group('id')
     79         display_id = mobj.group('display_id') or video_id
     80 
     81         definitions = self._download_json(
     82             'https://www.youporn.com/api/video/media_definitions/%s/' % video_id,
     83             display_id)
     84 
     85         formats = []
     86         for definition in definitions:
     87             if not isinstance(definition, dict):
     88                 continue
     89             video_url = url_or_none(definition.get('videoUrl'))
     90             if not video_url:
     91                 continue
     92             f = {
     93                 'url': video_url,
     94                 'filesize': int_or_none(definition.get('videoSize')),
     95             }
     96             height = int_or_none(definition.get('quality'))
     97             # Video URL's path looks like this:
     98             #  /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
     99             #  /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
    100             #  /videos/201703/11/109285532/1080P_4000K_109285532.mp4
    101             # We will benefit from it by extracting some metadata
    102             mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
    103             if mobj:
    104                 if not height:
    105                     height = int(mobj.group('height'))
    106                 bitrate = int(mobj.group('bitrate'))
    107                 f.update({
    108                     'format_id': '%dp-%dk' % (height, bitrate),
    109                     'tbr': bitrate,
    110                 })
    111             f['height'] = height
    112             formats.append(f)
    113         self._sort_formats(formats)
    114 
    115         webpage = self._download_webpage(
    116             'http://www.youporn.com/watch/%s' % video_id, display_id,
    117             headers={'Cookie': 'age_verified=1'})
    118 
    119         title = self._html_search_regex(
    120             r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
    121             webpage, 'title', default=None) or self._og_search_title(
    122             webpage, default=None) or self._html_search_meta(
    123             'title', webpage, fatal=True)
    124 
    125         description = self._html_search_regex(
    126             r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>',
    127             webpage, 'description',
    128             default=None) or self._og_search_description(
    129             webpage, default=None)
    130         thumbnail = self._search_regex(
    131             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
    132             webpage, 'thumbnail', fatal=False, group='thumbnail')
    133         duration = int_or_none(self._html_search_meta(
    134             'video:duration', webpage, 'duration', fatal=False))
    135 
    136         uploader = self._html_search_regex(
    137             r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
    138             webpage, 'uploader', fatal=False)
    139         upload_date = unified_strdate(self._html_search_regex(
    140             [r'UPLOADED:\s*<span>([^<]+)',
    141              r'Date\s+[Aa]dded:\s*<span>([^<]+)',
    142              r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>'],
    143             webpage, 'upload date', fatal=False))
    144 
    145         age_limit = self._rta_search(webpage)
    146 
    147         view_count = None
    148         views = self._search_regex(
    149             r'(<div[^>]+\bclass=["\']js_videoInfoViews["\']>)', webpage,
    150             'views', default=None)
    151         if views:
    152             view_count = str_to_int(extract_attributes(views).get('data-value'))
    153         comment_count = str_to_int(self._search_regex(
    154             r'>All [Cc]omments? \(([\d,.]+)\)',
    155             webpage, 'comment count', default=None))
    156 
    157         def extract_tag_box(regex, title):
    158             tag_box = self._search_regex(regex, webpage, title, default=None)
    159             if not tag_box:
    160                 return []
    161             return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
    162 
    163         categories = extract_tag_box(
    164             r'(?s)Categories:.*?</[^>]+>(.+?)</div>', 'categories')
    165         tags = extract_tag_box(
    166             r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>',
    167             'tags')
    168 
    169         return {
    170             'id': video_id,
    171             'display_id': display_id,
    172             'title': title,
    173             'description': description,
    174             'thumbnail': thumbnail,
    175             'duration': duration,
    176             'uploader': uploader,
    177             'upload_date': upload_date,
    178             'view_count': view_count,
    179             'comment_count': comment_count,
    180             'categories': categories,
    181             'tags': tags,
    182             'age_limit': age_limit,
    183             'formats': formats,
    184         }