yt_dlp/extractor/disney.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     determine_ext,
   6     int_or_none,
   7     join_nonempty,
   8     unified_strdate,
   9     update_url_query,
  10 )
  11
  12
  13 class DisneyIE(InfoExtractor):
  14     _VALID_URL = r'''(?x)
  15         https?://(?P<domain>(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr|channel\.de)|(?:starwars|marvelkids)\.com))/(?:(?:embed/|(?:[^/]+/)+[\w-]+-)(?P<id>[a-z0-9]{24})|(?:[^/]+/)?(?P<display_id>[^/?#]+))'''
  16     _TESTS = [{
  17         # Disney.EmbedVideo
  18         'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977',
  19         'info_dict': {
  20             'id': '545ed1857afee5a0ec239977',
  21             'ext': 'mp4',
  22             'title': 'Moana - Trailer',
  23             'description': 'A fun adventure for the entire Family!  Bring home Moana on Digital HD Feb 21 & Blu-ray March 7',
  24             'upload_date': '20170112',
  25         },
  26         'params': {
  27             # m3u8 download
  28             'skip_download': True,
  29         }
  30     }, {
  31         # Grill.burger
  32         'url': 'http://www.starwars.com/video/rogue-one-a-star-wars-story-intro-featurette',
  33         'info_dict': {
  34             'id': '5454e9f4e9804a552e3524c8',
  35             'ext': 'mp4',
  36             'title': '"Intro" Featurette: Rogue One: A Star Wars Story',
  37             'upload_date': '20170104',
  38             'description': 'Go behind-the-scenes of Rogue One: A Star Wars Story in this featurette with Director Gareth Edwards and the cast of the film.',
  39         },
  40         'params': {
  41             # m3u8 download
  42             'skip_download': True,
  43         }
  44     }, {
  45         'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2',
  46         'only_matching': True,
  47     }, {
  48         'url': 'http://video.en.disneyme.com/watch/future-worm/robo-carp-2001-544b66002aa7353cdd3f5114',
  49         'only_matching': True,
  50     }, {
  51         'url': 'http://video.disneyturkiye.com.tr/izle/7c-7-cuceler/kimin-sesi-zaten-5456f3d015f6b36c8afdd0e2',
  52         'only_matching': True,
  53     }, {
  54         'url': 'http://disneyjunior.disney.com/embed/546a4798ddba3d1612e4005d',
  55         'only_matching': True,
  56     }, {
  57         'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097',
  58         'only_matching': True,
  59     }, {
  60         'url': 'http://spiderman.marvelkids.com/embed/522900d2ced3c565e4cc0677',
  61         'only_matching': True,
  62     }, {
  63         'url': 'http://spiderman.marvelkids.com/videos/contest-of-champions-part-four-clip-1',
  64         'only_matching': True,
  65     }, {
  66         'url': 'http://disneyjunior.en.disneyme.com/dj/watch-my-friends-tigger-and-pooh-promo',
  67         'only_matching': True,
  68     }, {
  69         'url': 'http://disneychannel.de/sehen/soy-luna-folge-118-5518518987ba27f3cc729268',
  70         'only_matching': True,
  71     }, {
  72         'url': 'http://disneyjunior.disney.com/galactech-the-galactech-grab-galactech-an-admiral-rescue',
  73         'only_matching': True,
  74     }]
  75
  76     def _real_extract(self, url):
  77         domain, video_id, display_id = self._match_valid_url(url).groups()
  78         if not video_id:
  79             webpage = self._download_webpage(url, display_id)
  80             grill = re.sub(r'"\s*\+\s*"', '', self._search_regex(
  81                 r'Grill\.burger\s*=\s*({.+})\s*:',
  82                 webpage, 'grill data'))
  83             page_data = next(s for s in self._parse_json(grill, display_id)['stack'] if s.get('type') == 'video')
  84             video_data = page_data['data'][0]
  85         else:
  86             webpage = self._download_webpage(
  87                 'http://%s/embed/%s' % (domain, video_id), video_id)
  88             page_data = self._parse_json(self._search_regex(
  89                 r'Disney\.EmbedVideo\s*=\s*({.+});',
  90                 webpage, 'embed data'), video_id)
  91             video_data = page_data['video']
  92
  93         for external in video_data.get('externals', []):
  94             if external.get('source') == 'vevo':
  95                 return self.url_result('vevo:' + external['data_id'], 'Vevo')
  96
  97         video_id = video_data['id']
  98         title = video_data['title']
  99
 100         formats = []
 101         for flavor in video_data.get('flavors', []):
 102             flavor_format = flavor.get('format')
 103             flavor_url = flavor.get('url')
 104             if not flavor_url or not re.match(r'https?://', flavor_url) or flavor_format == 'mp4_access':
 105                 continue
 106             tbr = int_or_none(flavor.get('bitrate'))
 107             if tbr == 99999:
 108                 # wrong ks(Kaltura Signature) causes 404 Error
 109                 flavor_url = update_url_query(flavor_url, {'ks': ''})
 110                 m3u8_formats = self._extract_m3u8_formats(
 111                     flavor_url, video_id, 'mp4',
 112                     m3u8_id=flavor_format, fatal=False)
 113                 for f in m3u8_formats:
 114                     # Apple FairPlay
 115                     if '/fpshls/' in f['url']:
 116                         continue
 117                     formats.append(f)
 118                 continue
 119             ext = determine_ext(flavor_url)
 120             if flavor_format == 'applehttp' or ext == 'm3u8':
 121                 ext = 'mp4'
 122             width = int_or_none(flavor.get('width'))
 123             height = int_or_none(flavor.get('height'))
 124             formats.append({
 125                 'format_id': join_nonempty(flavor_format, tbr),
 126                 'url': flavor_url,
 127                 'width': width,
 128                 'height': height,
 129                 'tbr': tbr,
 130                 'ext': ext,
 131                 'vcodec': 'none' if (width == 0 and height == 0) else None,
 132             })
 133         if not formats and video_data.get('expired'):
 134             self.raise_no_formats(
 135                 '%s said: %s' % (self.IE_NAME, page_data['translations']['video_expired']),
 136                 expected=True)
 137
 138         subtitles = {}
 139         for caption in video_data.get('captions', []):
 140             caption_url = caption.get('url')
 141             caption_format = caption.get('format')
 142             if not caption_url or caption_format.startswith('unknown'):
 143                 continue
 144             subtitles.setdefault(caption.get('language', 'en'), []).append({
 145                 'url': caption_url,
 146                 'ext': {
 147                     'webvtt': 'vtt',
 148                 }.get(caption_format, caption_format),
 149             })
 150
 151         return {
 152             'id': video_id,
 153             'title': title,
 154             'description': video_data.get('description') or video_data.get('short_desc'),
 155             'thumbnail': video_data.get('thumb') or video_data.get('thumb_secure'),
 156             'duration': int_or_none(video_data.get('duration_sec')),
 157             'upload_date': unified_strdate(video_data.get('publish_date')),
 158             'formats': formats,
 159             'subtitles': subtitles,
 160         }