logo

youtube-dl

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

vbox7.py (8014B)

    

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  4. import re
  5. import time
  7. from .common import InfoExtractor
  8. from ..compat import compat_kwargs
  9. from ..utils import (
  10.     base_url,
  11.     determine_ext,
  12.     ExtractorError,
  13.     float_or_none,
  14.     merge_dicts,
  15.     T,
  16.     traverse_obj,
  17.     txt_or_none,
  18.     url_basename,
  19.     url_or_none,
  20. )
  23. class Vbox7IE(InfoExtractor):
  24.     _VALID_URL = r'''(?x)
  25.                     https?://
  26.                         (?:[^/]+\.)?vbox7\.com/
  27.                         (?:
  28.                             play:|
  29.                             (?:
  30.                                 emb/external\.php|
  31.                                 player/ext\.swf
  32.                             )\?.*?\bvid=
  33.                         )
  34.                         (?P<id>[\da-fA-F]+)
  35.                     '''
  36.     _EMBED_REGEX = [r'<iframe[^>]+src=(?P<q>["\'])(?P<url>(?:https?:)?//vbox7\.com/emb/external\.php.+?)(?P=q)']
  37.     _GEO_COUNTRIES = ['BG']
  38.     _TESTS = [{
  39.         # the http: URL just redirects here
  40.         'url': 'https://vbox7.com/play:0946fff23c',
  41.         'md5': '50ca1f78345a9c15391af47d8062d074',
  42.         'info_dict': {
  43.             'id': '0946fff23c',
  44.             'ext': 'mp4',
  45.             'title': 'Борисов: Притеснен съм за бъдещето на България',
  46.             'description': 'По думите му е опасно страната ни да бъде обявена за "сигурна"',
  47.             'timestamp': 1470982814,
  48.             'upload_date': '20160812',
  49.             'uploader': 'zdraveibulgaria',
  50.             'thumbnail': r're:^https?://.*\.jpg$',
  51.             'view_count': int,
  52.             'duration': 2640,
  53.         },
  54.         'expected_warnings': [
  55.             'Unable to download webpage',
  56.         ],
  57.     }, {
  58.         'url': 'http://vbox7.com/play:249bb972c2',
  59.         'md5': '99f65c0c9ef9b682b97313e052734c3f',
  60.         'info_dict': {
  61.             'id': '249bb972c2',
  62.             'ext': 'mp4',
  63.             'title': 'Смях! Чудо - чист за секунди - Скрита камера',
  64.             'description': 'Смях! Чудо - чист за секунди - Скрита камера',
  65.             'timestamp': 1360215023,
  66.             'upload_date': '20130207',
  67.             'uploader': 'svideteliat_ot_varshava',
  68.             'thumbnail': 'https://i49.vbox7.com/o/249/249bb972c20.jpg',
  69.             'view_count': int,
  70.             'duration': 83,
  71.         },
  72.         'expected_warnings': ['Failed to download m3u8 information'],
  73.     }, {
  74.         'url': 'http://vbox7.com/emb/external.php?vid=a240d20f9c&autoplay=1',
  75.         'only_matching': True,
  76.     }, {
  77.         'url': 'http://i49.vbox7.com/player/ext.swf?vid=0946fff23c&autoplay=1',
  78.         'only_matching': True,
  79.     }]
  81.     @classmethod
  82.     def _extract_url(cls, webpage):
  83.         mobj = re.search(cls._EMBED_REGEX[0], webpage)
  84.         if mobj:
  85.             return mobj.group('url')
  87.     # specialisation to transform what looks like ld+json that
  88.     # may contain invalid character combinations
  90.     # transform_source=None, fatal=True
  91.     def _parse_json(self, json_string, video_id, *args, **kwargs):
  92.         if '"@context"' in json_string[:30]:
  93.             # this is ld+json, or that's the way to bet
  94.             transform_source = args[0] if len(args) > 0 else kwargs.get('transform_source')
  95.             if not transform_source:
  97.                 def fix_chars(src):
  98.                     # fix malformed ld+json: replace raw CRLFs with escaped LFs
  99.                     return re.sub(
  100.                         r'"[^"]+"', lambda m: re.sub(r'\r?\n', r'\\n', m.group(0)), src)
  102.                 if len(args) > 0:
  103.                     args = (fix_chars,) + args[1:]
  104.                 else:
  105.                     kwargs['transform_source'] = fix_chars
  106.                     kwargs = compat_kwargs(kwargs)
  108.         return super(Vbox7IE, self)._parse_json(
  109.             json_string, video_id, *args, **kwargs)
  111.     def _real_extract(self, url):
  112.         video_id = self._match_id(url)
  113.         url = 'https://vbox7.com/play:%s' % (video_id,)
  115.         now = time.time()
  116.         response = self._download_json(
  117.             'https://www.vbox7.com/aj/player/item/options', video_id,
  118.             query={'vid': video_id}, headers={'Referer': url})
  119.         # estimate time to which possible `ago` member is relative
  120.         now = now + 0.5 * (time.time() - now)
  122.         if traverse_obj(response, 'error'):
  123.             raise ExtractorError(
  124.                 '%s said: %s' % (self.IE_NAME, response['error']), expected=True)
  126.         src_url = traverse_obj(response, ('options', 'src', T(url_or_none))) or ''
  128.         fmt_base = url_basename(src_url).rsplit('.', 1)[0].rsplit('_', 1)[0]
  129.         if fmt_base in ('na', 'vn'):
  130.             self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
  132.         ext = determine_ext(src_url)
  133.         if ext == 'mpd':
  134.             # extract MPD
  135.             try:
  136.                 formats, subtitles = self._extract_mpd_formats_and_subtitles(
  137.                     src_url, video_id, 'dash', fatal=False)
  138.             except KeyError:  # fatal doesn't catch this
  139.                 self.report_warning('Failed to parse MPD manifest')
  140.                 formats, subtitles = [], {}
  141.         elif ext != 'm3u8':
  142.             formats = [{
  143.                 'url': src_url,
  144.             }] if src_url else []
  145.             subtitles = {}
  147.         if src_url:
  148.             # possibly extract HLS, based on https://github.com/yt-dlp/yt-dlp/pull/9100
  149.             fmt_base = base_url(src_url) + fmt_base
  150.             # prepare for _extract_m3u8_formats_and_subtitles()
  151.             # hls_formats, hls_subs = self._extract_m3u8_formats_and_subtitles(
  152.             hls_formats = self._extract_m3u8_formats(
  153.                 '{0}.m3u8'.format(fmt_base), video_id, m3u8_id='hls', fatal=False)
  154.             formats.extend(hls_formats)
  155.             # self._merge_subtitles(hls_subs, target=subtitles)
  157.             # In case MPD/HLS cannot be parsed, or anyway, get mp4 combined
  158.             # formats usually provided to Safari, iOS, and old Windows
  159.             video = response['options']
  160.             resolutions = (1080, 720, 480, 240, 144)
  161.             highest_res = traverse_obj(video, (
  162.                 'highestRes', T(int))) or resolutions[0]
  163.             resolutions = traverse_obj(video, (
  164.                 'resolutions', lambda _, r: highest_res >= int(r) > 0)) or resolutions
  165.             mp4_formats = traverse_obj(resolutions, (
  166.                 Ellipsis, T(lambda res: {
  167.                     'url': '{0}_{1}.mp4'.format(fmt_base, res),
  168.                     'format_id': 'http-{0}'.format(res),
  169.                     'height': res,
  170.                 })))
  171.             # if above formats are flaky, enable the line below
  172.             # self._check_formats(mp4_formats, video_id)
  173.             formats.extend(mp4_formats)
  175.         self._sort_formats(formats)
  177.         webpage = self._download_webpage(url, video_id, fatal=False) or ''
  179.         info = self._search_json_ld(
  180.             webpage.replace('"/*@context"', '"@context"'), video_id,
  181.             fatal=False) if webpage else {}
  183.         if not info.get('title'):
  184.             info['title'] = traverse_obj(response, (
  185.                 'options', 'title', T(txt_or_none))) or self._og_search_title(webpage)
  187.         def if_missing(k):
  188.             return lambda x: None if k in info else x
  190.         info = merge_dicts(info, {
  191.             'id': video_id,
  192.             'formats': formats,
  193.             'subtitles': subtitles or None,
  194.         }, info, traverse_obj(response, ('options', {
  195.             'uploader': ('uploader', T(txt_or_none)),
  196.             'timestamp': ('ago', T(if_missing('timestamp')), T(lambda t: int(round((now - t) / 60.0)) * 60)),
  197.             'duration': ('duration', T(if_missing('duration')), T(float_or_none)),
  198.         })))
  199.         if 'thumbnail' not in info:
  200.             info['thumbnail'] = self._proto_relative_url(
  201.                 info.get('thumbnail') or self._og_search_thumbnail(webpage),
  202.                 'https:'),
  204.         return info