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 )
  14
  15
  16 class DisneyIE(InfoExtractor):
  17     _VALID_URL = r'''(?x)
  18         https?://(?P<domain>(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr)|(?:starwars|marvelkids)\.com))/(?:(?:embed/|(?:[^/]+/)+[\w-]+-)(?P<id>[a-z0-9]{24})|(?:[^/]+/)?(?P<display_id>[^/?#]+))'''
  19     _TESTS = [{
  20         # Disney.EmbedVideo
  21         'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977',
  22         'info_dict': {
  23             'id': '545ed1857afee5a0ec239977',
  24             'ext': 'mp4',
  25             'title': 'Moana - Trailer',
  26             'description': 'A fun adventure for the entire Family!  Bring home Moana on Digital HD Feb 21 & Blu-ray March 7',
  27             'upload_date': '20170112',
  28         },
  29         'params': {
  30             # m3u8 download
  31             'skip_download': True,
  32         }
  33     }, {
  34         # Grill.burger
  35         'url': 'http://www.starwars.com/video/rogue-one-a-star-wars-story-intro-featurette',
  36         'info_dict': {
  37             'id': '5454e9f4e9804a552e3524c8',
  38             'ext': 'mp4',
  39             'title': '"Intro" Featurette: Rogue One: A Star Wars Story',
  40             'upload_date': '20170104',
  41             '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.',
  42         },
  43         'params': {
  44             # m3u8 download
  45             'skip_download': True,
  46         }
  47     }, {
  48         'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2',
  49         'only_matching': True,
  50     }, {
  51         'url': 'http://video.en.disneyme.com/watch/future-worm/robo-carp-2001-544b66002aa7353cdd3f5114',
  52         'only_matching': True,
  53     }, {
  54         'url': 'http://video.disneyturkiye.com.tr/izle/7c-7-cuceler/kimin-sesi-zaten-5456f3d015f6b36c8afdd0e2',
  55         'only_matching': True,
  56     }, {
  57         'url': 'http://disneyjunior.disney.com/embed/546a4798ddba3d1612e4005d',
  58         'only_matching': True,
  59     }, {
  60         'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097',
  61         'only_matching': True,
  62     }, {
  63         'url': 'http://spiderman.marvelkids.com/embed/522900d2ced3c565e4cc0677',
  64         'only_matching': True,
  65     }, {
  66         'url': 'http://spiderman.marvelkids.com/videos/contest-of-champions-part-four-clip-1',
  67         'only_matching': True,
  68     }, {
  69         'url': 'http://disneyjunior.en.disneyme.com/dj/watch-my-friends-tigger-and-pooh-promo',
  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 = re.match(self._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                 formats.extend(self._extract_m3u8_formats(
 109                     flavor_url, video_id, 'mp4',
 110                     m3u8_id=flavor_format, fatal=False))
 111                 continue
 112             format_id = []
 113             if flavor_format:
 114                 format_id.append(flavor_format)
 115             if tbr:
 116                 format_id.append(compat_str(tbr))
 117             ext = determine_ext(flavor_url)
 118             if flavor_format == 'applehttp' or ext == 'm3u8':
 119                 ext = 'mp4'
 120             width = int_or_none(flavor.get('width'))
 121             height = int_or_none(flavor.get('height'))
 122             formats.append({
 123                 'format_id': '-'.join(format_id),
 124                 'url': flavor_url,
 125                 'width': width,
 126                 'height': height,
 127                 'tbr': tbr,
 128                 'ext': ext,
 129                 'vcodec': 'none' if (width == 0 and height == 0) else None,
 130             })
 131         if not formats and video_data.get('expired'):
 132             raise ExtractorError(
 133                 '%s said: %s' % (self.IE_NAME, page_data['translations']['video_expired']),
 134                 expected=True)
 135         self._sort_formats(formats)
 136
 137         subtitles = {}
 138         for caption in video_data.get('captions', []):
 139             caption_url = caption.get('url')
 140             caption_format = caption.get('format')
 141             if not caption_url or caption_format.startswith('unknown'):
 142                 continue
 143             subtitles.setdefault(caption.get('language', 'en'), []).append({
 144                 'url': caption_url,
 145                 'ext': {
 146                     'webvtt': 'vtt',
 147                 }.get(caption_format, caption_format),
 148             })
 149
 150         return {
 151             'id': video_id,
 152             'title': title,
 153             'description': video_data.get('description') or video_data.get('short_desc'),
 154             'thumbnail': video_data.get('thumb') or video_data.get('thumb_secure'),
 155             'duration': int_or_none(video_data.get('duration_sec')),
 156             'upload_date': unified_strdate(video_data.get('publish_date')),
 157             'formats': formats,
 158             'subtitles': subtitles,
 159         }