Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tv4.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     parse_iso8601,
   8 )
   9
  10
  11 class TV4IE(InfoExtractor):
  12     IE_DESC = 'tv4.se and tv4play.se'
  13     _VALID_URL = r'''(?x)https?://(?:www\.)?
  14         (?:
  15             tv4\.se/(?:[^/]+)/klipp/(?:.*)-|
  16             tv4play\.se/
  17             (?:
  18                 (?:program|barn)/(?:[^\?]+)\?video_id=|
  19                 iframe/video/|
  20                 film/|
  21                 sport/|
  22             )
  23         )(?P<id>[0-9]+)'''
  24     _TESTS = [
  25         {
  26             'url': 'http://www.tv4.se/kalla-fakta/klipp/kalla-fakta-5-english-subtitles-2491650',
  27             'md5': '909d6454b87b10a25aa04c4bdd416a9b',
  28             'info_dict': {
  29                 'id': '2491650',
  30                 'ext': 'mp4',
  31                 'title': 'Kalla Fakta 5 (english subtitles)',
  32                 'thumbnail': 're:^https?://.*\.jpg$',
  33                 'timestamp': int,
  34                 'upload_date': '20131125',
  35             },
  36         },
  37         {
  38             'url': 'http://www.tv4play.se/iframe/video/3054113',
  39             'md5': '77f851c55139ffe0ebd41b6a5552489b',
  40             'info_dict': {
  41                 'id': '3054113',
  42                 'ext': 'mp4',
  43                 'title': 'Så här jobbar ficktjuvarna - se avslöjande bilder',
  44                 'thumbnail': 're:^https?://.*\.jpg$',
  45                 'description': 'Unika bilder avslöjar hur turisternas fickor vittjas mitt på Stockholms central. Två experter på ficktjuvarna avslöjar knepen du ska se upp för.',
  46                 'timestamp': int,
  47                 'upload_date': '20150130',
  48             },
  49         },
  50         {
  51             'url': 'http://www.tv4play.se/sport/3060959',
  52             'only_matching': True,
  53         },
  54         {
  55             'url': 'http://www.tv4play.se/film/2378136',
  56             'only_matching': True,
  57         },
  58         {
  59             'url': 'http://www.tv4play.se/barn/looney-tunes?video_id=3062412',
  60             'only_matching': True,
  61         },
  62     ]
  63
  64     def _real_extract(self, url):
  65         video_id = self._match_id(url)
  66
  67         info = self._download_json(
  68             'http://www.tv4play.se/player/assets/%s.json' % video_id, video_id, 'Downloading video info JSON')
  69
  70         # If is_geo_restricted is true, it doesn't necessarily mean we can't download it
  71         if info['is_geo_restricted']:
  72             self.report_warning('This content might not be available in your country due to licensing restrictions.')
  73         if info['requires_subscription']:
  74             raise ExtractorError('This content requires subscription.', expected=True)
  75
  76         sources_data = self._download_json(
  77             'https://prima.tv4play.se/api/web/asset/%s/play.json?protocol=http&videoFormat=MP4' % video_id, video_id, 'Downloading sources JSON')
  78         sources = sources_data['playback']
  79
  80         formats = []
  81         for item in sources.get('items', {}).get('item', []):
  82             ext, bitrate = item['mediaFormat'], item['bitrate']
  83             formats.append({
  84                 'format_id': '%s_%s' % (ext, bitrate),
  85                 'tbr': bitrate,
  86                 'ext': ext,
  87                 'url': item['url'],
  88             })
  89         self._sort_formats(formats)
  90
  91         return {
  92             'id': video_id,
  93             'title': info['title'],
  94             'formats': formats,
  95             'description': info.get('description'),
  96             'timestamp': parse_iso8601(info.get('broadcast_date_time')),
  97             'duration': info.get('duration'),
  98             'thumbnail': info.get('image'),
  99             'is_live': sources.get('live'),
 100         }