Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tvigle.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     float_or_none,
  10     int_or_none,
  11     parse_age_limit,
  12     try_get,
  13     url_or_none,
  14 )
  15
  16
  17 class TvigleIE(InfoExtractor):
  18     IE_NAME = 'tvigle'
  19     IE_DESC = 'Интернет-телевидение Tvigle.ru'
  20     _VALID_URL = r'https?://(?:www\.)?(?:tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$|cloud\.tvigle\.ru/video/(?P<id>\d+))'
  21
  22     _GEO_BYPASS = False
  23     _GEO_COUNTRIES = ['RU']
  24
  25     _TESTS = [
  26         {
  27             'url': 'http://www.tvigle.ru/video/sokrat/',
  28             'info_dict': {
  29                 'id': '1848932',
  30                 'display_id': 'sokrat',
  31                 'ext': 'mp4',
  32                 'title': 'Сократ',
  33                 'description': 'md5:d6b92ffb7217b4b8ebad2e7665253c17',
  34                 'duration': 6586,
  35                 'age_limit': 12,
  36             },
  37             'skip': 'georestricted',
  38         },
  39         {
  40             'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/',
  41             'info_dict': {
  42                 'id': '5142516',
  43                 'ext': 'flv',
  44                 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком',
  45                 'description': 'md5:027f7dc872948f14c96d19b4178428a4',
  46                 'duration': 186.080,
  47                 'age_limit': 0,
  48             },
  49             'skip': 'georestricted',
  50         }, {
  51             'url': 'https://cloud.tvigle.ru/video/5267604/',
  52             'only_matching': True,
  53         }
  54     ]
  55
  56     def _real_extract(self, url):
  57         mobj = re.match(self._VALID_URL, url)
  58         video_id = mobj.group('id')
  59         display_id = mobj.group('display_id')
  60
  61         if not video_id:
  62             webpage = self._download_webpage(url, display_id)
  63             video_id = self._html_search_regex(
  64                 (r'<div[^>]+class=["\']player["\'][^>]+id=["\'](\d+)',
  65                  r'cloudId\s*=\s*["\'](\d+)',
  66                  r'class="video-preview current_playing" id="(\d+)"'),
  67                 webpage, 'video id')
  68
  69         video_data = self._download_json(
  70             'http://cloud.tvigle.ru/api/play/video/%s/' % video_id, display_id)
  71
  72         item = video_data['playlist']['items'][0]
  73
  74         videos = item.get('videos')
  75
  76         error_message = item.get('errorMessage')
  77         if not videos and error_message:
  78             if item.get('isGeoBlocked') is True:
  79                 self.raise_geo_restricted(
  80                     msg=error_message, countries=self._GEO_COUNTRIES)
  81             else:
  82                 raise ExtractorError(
  83                     '%s returned error: %s' % (self.IE_NAME, error_message),
  84                     expected=True)
  85
  86         title = item['title']
  87         description = item.get('description')
  88         thumbnail = item.get('thumbnail')
  89         duration = float_or_none(item.get('durationMilliseconds'), 1000)
  90         age_limit = parse_age_limit(item.get('ageRestrictions'))
  91
  92         formats = []
  93         for vcodec, url_or_fmts in item['videos'].items():
  94             if vcodec == 'hls':
  95                 m3u8_url = url_or_none(url_or_fmts)
  96                 if not m3u8_url:
  97                     continue
  98                 formats.extend(self._extract_m3u8_formats(
  99                     m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native',
 100                     m3u8_id='hls', fatal=False))
 101             elif vcodec == 'dash':
 102                 mpd_url = url_or_none(url_or_fmts)
 103                 if not mpd_url:
 104                     continue
 105                 formats.extend(self._extract_mpd_formats(
 106                     mpd_url, video_id, mpd_id='dash', fatal=False))
 107             else:
 108                 if not isinstance(url_or_fmts, dict):
 109                     continue
 110                 for format_id, video_url in url_or_fmts.items():
 111                     if format_id == 'm3u8':
 112                         continue
 113                     video_url = url_or_none(video_url)
 114                     if not video_url:
 115                         continue
 116                     height = self._search_regex(
 117                         r'^(\d+)[pP]$', format_id, 'height', default=None)
 118                     filesize = int_or_none(try_get(
 119                         item, lambda x: x['video_files_size'][vcodec][format_id]))
 120                     formats.append({
 121                         'url': video_url,
 122                         'format_id': '%s-%s' % (vcodec, format_id),
 123                         'vcodec': vcodec,
 124                         'height': int_or_none(height),
 125                         'filesize': filesize,
 126                     })
 127         self._sort_formats(formats)
 128
 129         return {
 130             'id': video_id,
 131             'display_id': display_id,
 132             'title': title,
 133             'description': description,
 134             'thumbnail': thumbnail,
 135             'duration': duration,
 136             'age_limit': age_limit,
 137             'formats': formats,
 138         }