[disney] improve extraction

- add support for more urls
- detect expired videos
- skip Adobe Flash Access protected videos

closes #4975
closes #11000
closes #11882
closes #11936
This commit is contained in:
Remita Amine 2017-02-13 11:43:20 +01:00
parent 0dac7cbb09
commit 9dad941853
2 changed files with 52 additions and 21 deletions

View File

@ -9,13 +9,15 @@ from ..utils import (
unified_strdate, unified_strdate,
compat_str, compat_str,
determine_ext, determine_ext,
ExtractorError,
) )
class DisneyIE(InfoExtractor): class DisneyIE(InfoExtractor):
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
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})''' 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>[^/?#]+))'''
_TESTS = [{ _TESTS = [{
# Disney.EmbedVideo
'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977', 'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977',
'info_dict': { 'info_dict': {
'id': '545ed1857afee5a0ec239977', 'id': '545ed1857afee5a0ec239977',
@ -28,6 +30,20 @@ class DisneyIE(InfoExtractor):
# m3u8 download # m3u8 download
'skip_download': True, 'skip_download': True,
} }
}, {
# Grill.burger
'url': 'http://www.starwars.com/video/rogue-one-a-star-wars-story-intro-featurette',
'info_dict': {
'id': '5454e9f4e9804a552e3524c8',
'ext': 'mp4',
'title': '"Intro" Featurette: Rogue One: A Star Wars Story',
'upload_date': '20170104',
'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.',
},
'params': {
# m3u8 download
'skip_download': True,
}
}, { }, {
'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2', 'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2',
'only_matching': True, 'only_matching': True,
@ -43,31 +59,55 @@ class DisneyIE(InfoExtractor):
}, { }, {
'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097', 'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097',
'only_matching': True, 'only_matching': True,
}, {
'url': 'http://spiderman.marvelkids.com/embed/522900d2ced3c565e4cc0677',
'only_matching': True,
}, {
'url': 'http://spiderman.marvelkids.com/videos/contest-of-champions-part-four-clip-1',
'only_matching': True,
}, {
'url': 'http://disneyjunior.en.disneyme.com/dj/watch-my-friends-tigger-and-pooh-promo',
'only_matching': True,
}, {
'url': 'http://disneyjunior.disney.com/galactech-the-galactech-grab-galactech-an-admiral-rescue',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
domain, video_id = re.match(self._VALID_URL, url).groups() domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
if not video_id:
webpage = self._download_webpage(url, display_id)
grill = re.sub(r'"\s*\+\s*"', '', self._search_regex(
r'Grill\.burger\s*=\s*({.+})\s*:',
webpage, 'grill data'))
page_data = next(s for s in self._parse_json(grill, display_id)['stack'] if s.get('type') == 'video')
video_data = page_data['data'][0]
else:
webpage = self._download_webpage( webpage = self._download_webpage(
'http://%s/embed/%s' % (domain, video_id), video_id) 'http://%s/embed/%s' % (domain, video_id), video_id)
video_data = self._parse_json(self._search_regex( page_data = self._parse_json(self._search_regex(
r'Disney\.EmbedVideo=({.+});', webpage, 'embed data'), video_id)['video'] r'Disney\.EmbedVideo\s*=\s*({.+});',
webpage, 'embed data'), video_id)
video_data = page_data['video']
for external in video_data.get('externals', []): for external in video_data.get('externals', []):
if external.get('source') == 'vevo': if external.get('source') == 'vevo':
return self.url_result('vevo:' + external['data_id'], 'Vevo') return self.url_result('vevo:' + external['data_id'], 'Vevo')
video_id = video_data['id']
title = video_data['title'] title = video_data['title']
formats = [] formats = []
for flavor in video_data.get('flavors', []): for flavor in video_data.get('flavors', []):
flavor_format = flavor.get('format') flavor_format = flavor.get('format')
flavor_url = flavor.get('url') flavor_url = flavor.get('url')
if not flavor_url or not re.match(r'https?://', flavor_url): if not flavor_url or not re.match(r'https?://', flavor_url) or flavor_format == 'mp4_access':
continue continue
tbr = int_or_none(flavor.get('bitrate')) tbr = int_or_none(flavor.get('bitrate'))
if tbr == 99999: if tbr == 99999:
formats.extend(self._extract_m3u8_formats( formats.extend(self._extract_m3u8_formats(
flavor_url, video_id, 'mp4', m3u8_id=flavor_format, fatal=False)) flavor_url, video_id, 'mp4',
m3u8_id=flavor_format, fatal=False))
continue continue
format_id = [] format_id = []
if flavor_format: if flavor_format:
@ -88,6 +128,10 @@ class DisneyIE(InfoExtractor):
'ext': ext, 'ext': ext,
'vcodec': 'none' if (width == 0 and height == 0) else None, 'vcodec': 'none' if (width == 0 and height == 0) else None,
}) })
if not formats and video_data.get('expired'):
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, page_data['translations']['video_expired']),
expected=True)
self._sort_formats(formats) self._sort_formats(formats)
subtitles = {} subtitles = {}

View File

@ -991,19 +991,6 @@ class GenericIE(InfoExtractor):
'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014', 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
}, },
}, },
# Kaltura embed protected with referrer
{
'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
'info_dict': {
'id': '1_g4fbemnq',
'ext': 'mp4',
'title': 'Violetta - Achter De Schermen - Ruggero',
'description': 'Achter de schermen met Ruggero',
'timestamp': 1435133761,
'upload_date': '20150624',
'uploader_id': 'echojecka',
},
},
# Kaltura embed with single quotes # Kaltura embed with single quotes
{ {
'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY', 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',