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 )
  13
  14
  15 class DisneyIE(InfoExtractor):
  16     _VALID_URL = r'''(?x)
  17         https?://(?P<domain>(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr)|starwars\.com))/(?:embed/|(?:[^/]+/)+[\w-]+-)(?P<id>[a-z0-9]{24})'''
  18     _TESTS = [{
  19         'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977',
  20         'info_dict': {
  21             'id': '545ed1857afee5a0ec239977',
  22             'ext': 'mp4',
  23             'title': 'Moana - Trailer',
  24             'description': 'A fun adventure for the entire Family!  Bring home Moana on Digital HD Feb 21 & Blu-ray March 7',
  25             'upload_date': '20170112',
  26         },
  27         'params': {
  28             # m3u8 download
  29             'skip_download': True,
  30         }
  31     }, {
  32         'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2',
  33         'only_matching': True,
  34     }, {
  35         'url': 'http://video.en.disneyme.com/watch/future-worm/robo-carp-2001-544b66002aa7353cdd3f5114',
  36         'only_matching': True,
  37     }, {
  38         'url': 'http://video.disneyturkiye.com.tr/izle/7c-7-cuceler/kimin-sesi-zaten-5456f3d015f6b36c8afdd0e2',
  39         'only_matching': True,
  40     }, {
  41         'url': 'http://disneyjunior.disney.com/embed/546a4798ddba3d1612e4005d',
  42         'only_matching': True,
  43     }, {
  44         'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097',
  45         'only_matching': True,
  46     }]
  47
  48     def _real_extract(self, url):
  49         domain, video_id = re.match(self._VALID_URL, url).groups()
  50         webpage = self._download_webpage(
  51             'http://%s/embed/%s' % (domain, video_id), video_id)
  52         video_data = self._parse_json(self._search_regex(
  53             r'Disney\.EmbedVideo=({.+});', webpage, 'embed data'), video_id)['video']
  54
  55         for external in video_data.get('externals', []):
  56             if external.get('source') == 'vevo':
  57                 return self.url_result('vevo:' + external['data_id'], 'Vevo')
  58
  59         title = video_data['title']
  60
  61         formats = []
  62         for flavor in video_data.get('flavors', []):
  63             flavor_format = flavor.get('format')
  64             flavor_url = flavor.get('url')
  65             if not flavor_url or not re.match(r'https?://', flavor_url):
  66                 continue
  67             tbr = int_or_none(flavor.get('bitrate'))
  68             if tbr == 99999:
  69                 formats.extend(self._extract_m3u8_formats(
  70                     flavor_url, video_id, 'mp4', m3u8_id=flavor_format, fatal=False))
  71                 continue
  72             format_id = []
  73             if flavor_format:
  74                 format_id.append(flavor_format)
  75             if tbr:
  76                 format_id.append(compat_str(tbr))
  77             ext = determine_ext(flavor_url)
  78             if flavor_format == 'applehttp' or ext == 'm3u8':
  79                 ext = 'mp4'
  80             width = int_or_none(flavor.get('width'))
  81             height = int_or_none(flavor.get('height'))
  82             formats.append({
  83                 'format_id': '-'.join(format_id),
  84                 'url': flavor_url,
  85                 'width': width,
  86                 'height': height,
  87                 'tbr': tbr,
  88                 'ext': ext,
  89                 'vcodec': 'none' if (width == 0 and height == 0) else None,
  90             })
  91         self._sort_formats(formats)
  92
  93         subtitles = {}
  94         for caption in video_data.get('captions', []):
  95             caption_url = caption.get('url')
  96             caption_format = caption.get('format')
  97             if not caption_url or caption_format.startswith('unknown'):
  98                 continue
  99             subtitles.setdefault(caption.get('language', 'en'), []).append({
 100                 'url': caption_url,
 101                 'ext': {
 102                     'webvtt': 'vtt',
 103                 }.get(caption_format, caption_format),
 104             })
 105
 106         return {
 107             'id': video_id,
 108             'title': title,
 109             'description': video_data.get('description') or video_data.get('short_desc'),
 110             'thumbnail': video_data.get('thumb') or video_data.get('thumb_secure'),
 111             'duration': int_or_none(video_data.get('duration_sec')),
 112             'upload_date': unified_strdate(video_data.get('publish_date')),
 113             'formats': formats,
 114             'subtitles': subtitles,
 115         }