yt_dlp/extractor/nuvid.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     parse_duration,
   7     int_or_none,
   8     try_get,
   9 )
  10
  11
  12 class NuvidIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
  14     _TESTS = [{
  15         'url': 'https://www.nuvid.com/video/6513023/italian-babe',
  16         'md5': '772d2f8288f3d3c5c45f7a41761c7844',
  17         'info_dict': {
  18             'id': '6513023',
  19             'ext': 'mp4',
  20             'title': 'italian babe',
  21             'duration': 321.0,
  22             'age_limit': 18,
  23         }
  24     }, {
  25         'url': 'https://m.nuvid.com/video/6523263',
  26         'info_dict': {
  27             'id': '6523263',
  28             'ext': 'mp4',
  29             'age_limit': 18,
  30             'title': 'Slut brunette college student anal dorm',
  31         }
  32     }]
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36
  37         qualities = {
  38             'lq': '360p',
  39             'hq': '720p',
  40         }
  41
  42         json_url = f'https://www.nuvid.com/player_config_json/?vid={video_id}&aid=0&domain_id=0&embed=0&check_speed=0'
  43         video_data = self._download_json(
  44             json_url, video_id, headers={
  45                 'Accept': 'application/json, text/javascript, */*; q = 0.01',
  46                 'Content-Type': 'application/x-www-form-urlencoded; charset=utf-8',
  47             })
  48
  49         formats = [{
  50             'url': source,
  51             'format_id': qualities.get(quality),
  52             'height': int_or_none(qualities.get(quality)[:-1]),
  53         } for quality, source in video_data.get('files').items() if source]
  54
  55         self._check_formats(formats, video_id)
  56         self._sort_formats(formats)
  57
  58         title = video_data.get('title')
  59         thumbnail_base_url = try_get(video_data, lambda x: x['thumbs']['url'])
  60         thumbnail_extension = try_get(video_data, lambda x: x['thumbs']['extension'])
  61         thumbnail_id = self._search_regex(
  62             r'/media/videos/tmb/6523263/preview/(/d+)' + thumbnail_extension, video_data.get('poster', ''), 'thumbnail id', default=19)
  63         thumbnail = f'{thumbnail_base_url}player/{thumbnail_id}{thumbnail_extension}'
  64         duration = parse_duration(video_data.get('duration') or video_data.get('duration_format'))
  65
  66         return {
  67             'id': video_id,
  68             'formats': formats,
  69             'title': title,
  70             'thumbnail': thumbnail,
  71             'duration': duration,
  72             'age_limit': 18,
  73         }