logo

youtube-dl

[mirror] Download/Watch videos from video hostersgit clone https://hacktivis.me/git/mirror/youtube-dl.git

nuvid.py (3917B)

    

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  4. from .common import InfoExtractor
  5. from ..compat import compat_str
  6. from ..utils import (
  7.     parse_duration,
  8.     int_or_none,
  9.     try_get,
  10.     url_or_none,
  11. )
  13. import re
  16. class NuvidIE(InfoExtractor):
  17.     _VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
  18.     _TESTS = [{
  19.         'url': 'https://www.nuvid.com/video/6513023/italian-babe',
  20.         'md5': '772d2f8288f3d3c5c45f7a41761c7844',
  21.         'info_dict': {
  22.             'id': '6513023',
  23.             'ext': 'mp4',
  24.             'title': 'italian babe',
  25.             'format_id': '360p',
  26.             'duration': 321.0,
  27.             'age_limit': 18,
  28.             'thumbnail': r're:https?://.+\.jpg',
  29.             'thumbnails': list,
  30.         }
  31.     }, {
  32.         'url': 'https://m.nuvid.com/video/6523263',
  33.         'md5': 'ebd22ce8e47e1d9a4d0756a15c67da52',
  34.         'info_dict': {
  35.             'id': '6523263',
  36.             'ext': 'mp4',
  37.             'title': 'Slut brunette college student anal dorm',
  38.             'format_id': '720p',
  39.             'duration': 421.0,
  40.             'age_limit': 18,
  41.             'thumbnail': r're:https?://.+\.jpg',
  42.             'thumbnails': list,
  43.         }
  44.     }, {
  45.         'url': 'http://m.nuvid.com/video/6415801/',
  46.         'md5': '638d5ececb138d5753593f751ae3f697',
  47.         'info_dict': {
  48.             'id': '6415801',
  49.             'ext': 'mp4',
  50.             'title': 'My best friend wanted to fuck my wife for a long time',
  51.             'format_id': '720p',
  52.             'duration': 1882,
  53.             'age_limit': 18,
  54.             'thumbnail': r're:https?://.+\.jpg',
  55.             'thumbnails': list,
  56.         }
  57.     }]
  59.     def _real_extract(self, url):
  60.         video_id = self._match_id(url)
  62.         qualities = {
  63.             'lq': '360p',
  64.             'hq': '720p',
  65.         }
  67.         json_url = 'https://www.nuvid.com/player_config_json/?vid={video_id}&aid=0&domain_id=0&embed=0&check_speed=0'.format(**locals())
  68.         video_data = self._download_json(
  69.             json_url, video_id, headers={
  70.                 'Accept': 'application/json, text/javascript, */*; q = 0.01',
  71.                 'Content-Type': 'application/x-www-form-urlencoded; charset=utf-8',
  72.             }) or {}
  74.         # nice to have, not required
  75.         webpage = self._download_webpage(
  76.             'http://m.nuvid.com/video/%s' % (video_id, ),
  77.             video_id, 'Downloading video page', fatal=False) or ''
  79.         title = (
  80.             try_get(video_data, lambda x: x['title'], compat_str)
  81.             or self._html_search_regex(
  82.                 (r'''<span\s[^>]*?\btitle\s*=\s*(?P<q>"|'|\b)(?P<title>[^"]+)(?P=q)\s*>''',
  83.                  r'''<div\s[^>]*?\bclass\s*=\s*(?P<q>"|'|\b)thumb-holder video(?P=q)>\s*<h5\b[^>]*>(?P<title>[^<]+)</h5''',
  84.                  r'''<span\s[^>]*?\bclass\s*=\s*(?P<q>"|'|\b)title_thumb(?P=q)>(?P<title>[^<]+)</span'''),
  85.                 webpage, 'title', group='title')).strip()
  87.         formats = [{
  88.             'url': source,
  89.             'format_id': qualities.get(quality),
  90.             'height': int_or_none(qualities.get(quality)[:-1]),
  91.         } for quality, source in video_data.get('files').items() if source]
  93.         self._check_formats(formats, video_id)
  94.         self._sort_formats(formats)
  96.         duration = parse_duration(video_data.get('duration') or video_data.get('duration_format'))
  97.         thumbnails = [
  98.             {'url': thumb_url, }
  99.             for thumb_url in (
  100.                 url_or_none(src) for src in re.findall(
  101.                     r'<div\s+class\s*=\s*"video-tmb-wrap"\s*>\s*<img\s+src\s*=\s*"([^"]+)"\s*/>',
  102.                     webpage))
  103.         ]
  105.         return {
  106.             'id': video_id,
  107.             'formats': formats,
  108.             'title': title,
  109.             'thumbnail': url_or_none(video_data.get('poster')),
  110.             'thumbnails': thumbnails,
  111.             'duration': duration,
  112.             'age_limit': 18,
  113.         }