You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

170 lines
6.9 KiB

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. import re
  4. from .common import InfoExtractor
  5. from ..utils import (
  6. int_or_none,
  7. unified_strdate,
  8. compat_str,
  9. determine_ext,
  10. ExtractorError,
  11. update_url_query,
  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. def _real_extract(self, url):
  76. domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
  77. if not video_id:
  78. webpage = self._download_webpage(url, display_id)
  79. grill = re.sub(r'"\s*\+\s*"', '', self._search_regex(
  80. r'Grill\.burger\s*=\s*({.+})\s*:',
  81. webpage, 'grill data'))
  82. page_data = next(s for s in self._parse_json(grill, display_id)['stack'] if s.get('type') == 'video')
  83. video_data = page_data['data'][0]
  84. else:
  85. webpage = self._download_webpage(
  86. 'http://%s/embed/%s' % (domain, video_id), video_id)
  87. page_data = self._parse_json(self._search_regex(
  88. r'Disney\.EmbedVideo\s*=\s*({.+});',
  89. webpage, 'embed data'), video_id)
  90. video_data = page_data['video']
  91. for external in video_data.get('externals', []):
  92. if external.get('source') == 'vevo':
  93. return self.url_result('vevo:' + external['data_id'], 'Vevo')
  94. video_id = video_data['id']
  95. title = video_data['title']
  96. formats = []
  97. for flavor in video_data.get('flavors', []):
  98. flavor_format = flavor.get('format')
  99. flavor_url = flavor.get('url')
  100. if not flavor_url or not re.match(r'https?://', flavor_url) or flavor_format == 'mp4_access':
  101. continue
  102. tbr = int_or_none(flavor.get('bitrate'))
  103. if tbr == 99999:
  104. # wrong ks(Kaltura Signature) causes 404 Error
  105. flavor_url = update_url_query(flavor_url, {'ks': ''})
  106. m3u8_formats = self._extract_m3u8_formats(
  107. flavor_url, video_id, 'mp4',
  108. m3u8_id=flavor_format, fatal=False)
  109. for f in m3u8_formats:
  110. # Apple FairPlay
  111. if '/fpshls/' in f['url']:
  112. continue
  113. formats.append(f)
  114. continue
  115. format_id = []
  116. if flavor_format:
  117. format_id.append(flavor_format)
  118. if tbr:
  119. format_id.append(compat_str(tbr))
  120. ext = determine_ext(flavor_url)
  121. if flavor_format == 'applehttp' or ext == 'm3u8':
  122. ext = 'mp4'
  123. width = int_or_none(flavor.get('width'))
  124. height = int_or_none(flavor.get('height'))
  125. formats.append({
  126. 'format_id': '-'.join(format_id),
  127. 'url': flavor_url,
  128. 'width': width,
  129. 'height': height,
  130. 'tbr': tbr,
  131. 'ext': ext,
  132. 'vcodec': 'none' if (width == 0 and height == 0) else None,
  133. })
  134. if not formats and video_data.get('expired'):
  135. raise ExtractorError(
  136. '%s said: %s' % (self.IE_NAME, page_data['translations']['video_expired']),
  137. expected=True)
  138. self._sort_formats(formats)
  139. subtitles = {}
  140. for caption in video_data.get('captions', []):
  141. caption_url = caption.get('url')
  142. caption_format = caption.get('format')
  143. if not caption_url or caption_format.startswith('unknown'):
  144. continue
  145. subtitles.setdefault(caption.get('language', 'en'), []).append({
  146. 'url': caption_url,
  147. 'ext': {
  148. 'webvtt': 'vtt',
  149. }.get(caption_format, caption_format),
  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. }