Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/disney.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     int_or_none,
   9     unified_strdate,
  10     compat_str,
  11     determine_ext,
  12     ExtractorError,
  13     update_url_query,
  14 )
  15
  16
  17 class DisneyIE(InfoExtractor):
  18     _VALID_URL = r'''(?x)
  19         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>[^/?#]+))'''
  20     _TESTS = [{
  21         # Disney.EmbedVideo
  22         'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977',
  23         'info_dict': {
  24             'id': '545ed1857afee5a0ec239977',
  25             'ext': 'mp4',
  26             'title': 'Moana - Trailer',
  27             'description': 'A fun adventure for the entire Family!  Bring home Moana on Digital HD Feb 21 & Blu-ray March 7',
  28             'upload_date': '20170112',
  29         },
  30         'params': {
  31             # m3u8 download
  32             'skip_download': True,
  33         }
  34     }, {
  35         # Grill.burger
  36         'url': 'http://www.starwars.com/video/rogue-one-a-star-wars-story-intro-featurette',
  37         'info_dict': {
  38             'id': '5454e9f4e9804a552e3524c8',
  39             'ext': 'mp4',
  40             'title': '"Intro" Featurette: Rogue One: A Star Wars Story',
  41             'upload_date': '20170104',
  42             '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.',
  43         },
  44         'params': {
  45             # m3u8 download
  46             'skip_download': True,
  47         }
  48     }, {
  49         'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2',
  50         'only_matching': True,
  51     }, {
  52         'url': 'http://video.en.disneyme.com/watch/future-worm/robo-carp-2001-544b66002aa7353cdd3f5114',
  53         'only_matching': True,
  54     }, {
  55         'url': 'http://video.disneyturkiye.com.tr/izle/7c-7-cuceler/kimin-sesi-zaten-5456f3d015f6b36c8afdd0e2',
  56         'only_matching': True,
  57     }, {
  58         'url': 'http://disneyjunior.disney.com/embed/546a4798ddba3d1612e4005d',
  59         'only_matching': True,
  60     }, {
  61         'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097',
  62         'only_matching': True,
  63     }, {
  64         'url': 'http://spiderman.marvelkids.com/embed/522900d2ced3c565e4cc0677',
  65         'only_matching': True,
  66     }, {
  67         'url': 'http://spiderman.marvelkids.com/videos/contest-of-champions-part-four-clip-1',
  68         'only_matching': True,
  69     }, {
  70         'url': 'http://disneyjunior.en.disneyme.com/dj/watch-my-friends-tigger-and-pooh-promo',
  71         'only_matching': True,
  72     }, {
  73         'url': 'http://disneychannel.de/sehen/soy-luna-folge-118-5518518987ba27f3cc729268',
  74         'only_matching': True,
  75     }, {
  76         'url': 'http://disneyjunior.disney.com/galactech-the-galactech-grab-galactech-an-admiral-rescue',
  77         'only_matching': True,
  78     }]
  79
  80     def _real_extract(self, url):
  81         domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
  82         if not video_id:
  83             webpage = self._download_webpage(url, display_id)
  84             grill = re.sub(r'"\s*\+\s*"', '', self._search_regex(
  85                 r'Grill\.burger\s*=\s*({.+})\s*:',
  86                 webpage, 'grill data'))
  87             page_data = next(s for s in self._parse_json(grill, display_id)['stack'] if s.get('type') == 'video')
  88             video_data = page_data['data'][0]
  89         else:
  90             webpage = self._download_webpage(
  91                 'http://%s/embed/%s' % (domain, video_id), video_id)
  92             page_data = self._parse_json(self._search_regex(
  93                 r'Disney\.EmbedVideo\s*=\s*({.+});',
  94                 webpage, 'embed data'), video_id)
  95             video_data = page_data['video']
  96
  97         for external in video_data.get('externals', []):
  98             if external.get('source') == 'vevo':
  99                 return self.url_result('vevo:' + external['data_id'], 'Vevo')
 100
 101         video_id = video_data['id']
 102         title = video_data['title']
 103
 104         formats = []
 105         for flavor in video_data.get('flavors', []):
 106             flavor_format = flavor.get('format')
 107             flavor_url = flavor.get('url')
 108             if not flavor_url or not re.match(r'https?://', flavor_url) or flavor_format == 'mp4_access':
 109                 continue
 110             tbr = int_or_none(flavor.get('bitrate'))
 111             if tbr == 99999:
 112                 # wrong ks(Kaltura Signature) causes 404 Error
 113                 flavor_url = update_url_query(flavor_url, {'ks': ''})
 114                 m3u8_formats = self._extract_m3u8_formats(
 115                     flavor_url, video_id, 'mp4',
 116                     m3u8_id=flavor_format, fatal=False)
 117                 for f in m3u8_formats:
 118                     # Apple FairPlay
 119                     if '/fpshls/' in f['url']:
 120                         continue
 121                     formats.append(f)
 122                 continue
 123             format_id = []
 124             if flavor_format:
 125                 format_id.append(flavor_format)
 126             if tbr:
 127                 format_id.append(compat_str(tbr))
 128             ext = determine_ext(flavor_url)
 129             if flavor_format == 'applehttp' or ext == 'm3u8':
 130                 ext = 'mp4'
 131             width = int_or_none(flavor.get('width'))
 132             height = int_or_none(flavor.get('height'))
 133             formats.append({
 134                 'format_id': '-'.join(format_id),
 135                 'url': flavor_url,
 136                 'width': width,
 137                 'height': height,
 138                 'tbr': tbr,
 139                 'ext': ext,
 140                 'vcodec': 'none' if (width == 0 and height == 0) else None,
 141             })
 142         if not formats and video_data.get('expired'):
 143             raise ExtractorError(
 144                 '%s said: %s' % (self.IE_NAME, page_data['translations']['video_expired']),
 145                 expected=True)
 146         self._sort_formats(formats)
 147
 148         subtitles = {}
 149         for caption in video_data.get('captions', []):
 150             caption_url = caption.get('url')
 151             caption_format = caption.get('format')
 152             if not caption_url or caption_format.startswith('unknown'):
 153                 continue
 154             subtitles.setdefault(caption.get('language', 'en'), []).append({
 155                 'url': caption_url,
 156                 'ext': {
 157                     'webvtt': 'vtt',
 158                 }.get(caption_format, caption_format),
 159             })
 160
 161         return {
 162             'id': video_id,
 163             'title': title,
 164             'description': video_data.get('description') or video_data.get('short_desc'),
 165             'thumbnail': video_data.get('thumb') or video_data.get('thumb_secure'),
 166             'duration': int_or_none(video_data.get('duration_sec')),
 167             'upload_date': unified_strdate(video_data.get('publish_date')),
 168             'formats': formats,
 169             'subtitles': subtitles,
 170         }