yt_dlp/extractor/nuvid.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     parse_duration,
   7     strip_or_none,
   8     traverse_obj,
   9     url_or_none,
  10 )
  11
  12
  13 class NuvidIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
  15     _TESTS = [{
  16         'url': 'https://www.nuvid.com/video/6513023/italian-babe',
  17         'md5': '772d2f8288f3d3c5c45f7a41761c7844',
  18         'info_dict': {
  19             'id': '6513023',
  20             'ext': 'mp4',
  21             'title': 'italian babe',
  22             'duration': 321.0,
  23             'age_limit': 18,
  24             'thumbnail': r're:https?://.+\.jpg',
  25         },
  26     }, {
  27         'url': 'https://m.nuvid.com/video/6523263',
  28         'md5': 'ebd22ce8e47e1d9a4d0756a15c67da52',
  29         'info_dict': {
  30             'id': '6523263',
  31             'ext': 'mp4',
  32             'title': 'Slut brunette college student anal dorm',
  33             'duration': 421.0,
  34             'age_limit': 18,
  35             'thumbnail': r're:https?://.+\.jpg',
  36             'thumbnails': list,
  37         },
  38     }, {
  39         'url': 'http://m.nuvid.com/video/6415801/',
  40         'md5': '638d5ececb138d5753593f751ae3f697',
  41         'info_dict': {
  42             'id': '6415801',
  43             'ext': 'mp4',
  44             'title': 'My best friend wanted to fuck my wife for a long time',
  45             'duration': 1882,
  46             'age_limit': 18,
  47             'thumbnail': r're:https?://.+\.jpg',
  48         },
  49     }]
  50
  51     def _real_extract(self, url):
  52         video_id = self._match_id(url)
  53
  54         qualities = {
  55             'lq': '360p',
  56             'hq': '720p',
  57         }
  58
  59         json_url = f'https://www.nuvid.com/player_config_json/?vid={video_id}&aid=0&domain_id=0&embed=0&check_speed=0'
  60         video_data = self._download_json(
  61             json_url, video_id, headers={
  62                 'Accept': 'application/json, text/javascript, */*; q = 0.01',
  63                 'Content-Type': 'application/x-www-form-urlencoded; charset=utf-8',
  64             })
  65
  66         webpage = self._download_webpage(
  67             f'http://m.nuvid.com/video/{video_id}',
  68             video_id, 'Downloading video page', fatal=False) or ''
  69
  70         title = strip_or_none(video_data.get('title') or self._html_search_regex(
  71             (r'''<span\s[^>]*?\btitle\s*=\s*(?P<q>"|'|\b)(?P<title>[^"]+)(?P=q)\s*>''',
  72                 r'''<div\s[^>]*?\bclass\s*=\s*(?P<q>"|'|\b)thumb-holder video(?P=q)>\s*<h5\b[^>]*>(?P<title>[^<]+)</h5''',
  73                 r'''<span\s[^>]*?\bclass\s*=\s*(?P<q>"|'|\b)title_thumb(?P=q)>(?P<title>[^<]+)</span'''),
  74             webpage, 'title', group='title'))
  75
  76         formats = [{
  77             'url': source,
  78             'format_id': qualities.get(quality),
  79             'height': int_or_none(qualities.get(quality)[:-1]),
  80         } for quality, source in video_data.get('files').items() if source]
  81
  82         self._check_formats(formats, video_id)
  83
  84         duration = parse_duration(traverse_obj(video_data, 'duration', 'duration_format'))
  85         thumbnails = [
  86             {'url': thumb_url} for thumb_url in re.findall(
  87                 r'<div\s+class\s*=\s*"video-tmb-wrap"\s*>\s*<img\s+src\s*=\s*"([^"]+)"\s*/>', webpage)
  88             if url_or_none(thumb_url)]
  89         if url_or_none(video_data.get('poster')):
  90             thumbnails.append({'url': video_data['poster'], 'preference': 1})
  91
  92         return {
  93             'id': video_id,
  94             'formats': formats,
  95             'title': title,
  96             'thumbnails': thumbnails,
  97             'duration': duration,
  98             'age_limit': 18,
  99         }