|
|
|
@ -1,108 +1,69 @@
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
import re
|
|
|
|
import json
|
|
|
|
|
|
|
|
import base64
|
|
|
|
import base64
|
|
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
from .common import InfoExtractor
|
|
|
|
from ..utils import (
|
|
|
|
from ..utils import (
|
|
|
|
unescapeHTML,
|
|
|
|
|
|
|
|
ExtractorError,
|
|
|
|
|
|
|
|
determine_ext,
|
|
|
|
|
|
|
|
int_or_none,
|
|
|
|
int_or_none,
|
|
|
|
|
|
|
|
float_or_none,
|
|
|
|
|
|
|
|
ExtractorError,
|
|
|
|
|
|
|
|
unsmuggle_url,
|
|
|
|
)
|
|
|
|
)
|
|
|
|
|
|
|
|
from ..compat import compat_urllib_parse
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class OoyalaBaseIE(InfoExtractor):
|
|
|
|
class OoyalaBaseIE(InfoExtractor):
|
|
|
|
|
|
|
|
|
|
|
|
def _extract_result(self, info, more_info):
|
|
|
|
def _extract(self, content_tree_url, video_id, domain='example.org'):
|
|
|
|
embedCode = info['embedCode']
|
|
|
|
content_tree = self._download_json(content_tree_url, video_id)['content_tree']
|
|
|
|
video_url = info.get('ipad_url') or info['url']
|
|
|
|
metadata = content_tree[list(content_tree)[0]]
|
|
|
|
|
|
|
|
embed_code = metadata['embed_code']
|
|
|
|
if determine_ext(video_url) == 'm3u8':
|
|
|
|
pcode = metadata.get('asset_pcode') or embed_code
|
|
|
|
formats = self._extract_m3u8_formats(video_url, embedCode, ext='mp4')
|
|
|
|
video_info = {
|
|
|
|
else:
|
|
|
|
'id': embed_code,
|
|
|
|
formats = [{
|
|
|
|
'title': metadata['title'],
|
|
|
|
'url': video_url,
|
|
|
|
'description': metadata.get('description'),
|
|
|
|
'ext': 'mp4',
|
|
|
|
'thumbnail': metadata.get('thumbnail_image') or metadata.get('promo_image'),
|
|
|
|
}]
|
|
|
|
'duration': int_or_none(metadata.get('duration')),
|
|
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
|
|
|
'id': embedCode,
|
|
|
|
|
|
|
|
'title': unescapeHTML(info['title']),
|
|
|
|
|
|
|
|
'formats': formats,
|
|
|
|
|
|
|
|
'description': unescapeHTML(more_info['description']),
|
|
|
|
|
|
|
|
'thumbnail': more_info['promo'],
|
|
|
|
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
def _extract(self, player_url, video_id):
|
|
|
|
formats = []
|
|
|
|
player = self._download_webpage(player_url, video_id)
|
|
|
|
for supported_format in ('mp4', 'm3u8', 'hds', 'rtmp'):
|
|
|
|
mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
|
|
|
|
|
|
|
|
player, 'mobile player url')
|
|
|
|
|
|
|
|
# Looks like some videos are only available for particular devices
|
|
|
|
|
|
|
|
# (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0
|
|
|
|
|
|
|
|
# is only available for ipad)
|
|
|
|
|
|
|
|
# Working around with fetching URLs for all the devices found starting with 'unknown'
|
|
|
|
|
|
|
|
# until we succeed or eventually fail for each device.
|
|
|
|
|
|
|
|
devices = re.findall(r'device\s*=\s*"([^"]+)";', player)
|
|
|
|
|
|
|
|
devices.remove('unknown')
|
|
|
|
|
|
|
|
devices.insert(0, 'unknown')
|
|
|
|
|
|
|
|
for device in devices:
|
|
|
|
|
|
|
|
mobile_player = self._download_webpage(
|
|
|
|
|
|
|
|
'%s&device=%s' % (mobile_url, device), video_id,
|
|
|
|
|
|
|
|
'Downloading mobile player JS for %s device' % device)
|
|
|
|
|
|
|
|
videos_info = self._search_regex(
|
|
|
|
|
|
|
|
r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
|
|
|
|
|
|
|
|
mobile_player, 'info', fatal=False, default=None)
|
|
|
|
|
|
|
|
if videos_info:
|
|
|
|
|
|
|
|
break
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if not videos_info:
|
|
|
|
|
|
|
|
formats = []
|
|
|
|
|
|
|
|
auth_data = self._download_json(
|
|
|
|
auth_data = self._download_json(
|
|
|
|
'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?domain=www.example.org&supportedFormats=mp4,webm' % (video_id, video_id),
|
|
|
|
'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?' % (pcode, embed_code) + compat_urllib_parse.urlencode({'domain': domain, 'supportedFormats': supported_format}),
|
|
|
|
video_id)
|
|
|
|
video_id, 'Downloading %s JSON' % supported_format)
|
|
|
|
|
|
|
|
|
|
|
|
cur_auth_data = auth_data['authorization_data'][video_id]
|
|
|
|
cur_auth_data = auth_data['authorization_data'][embed_code]
|
|
|
|
|
|
|
|
|
|
|
|
for stream in cur_auth_data['streams']:
|
|
|
|
if cur_auth_data['authorized']:
|
|
|
|
formats.append({
|
|
|
|
for stream in cur_auth_data['streams']:
|
|
|
|
'url': base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8'),
|
|
|
|
url = base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8')
|
|
|
|
'ext': stream.get('delivery_type'),
|
|
|
|
delivery_type = stream['delivery_type']
|
|
|
|
'format': stream.get('video_codec'),
|
|
|
|
if delivery_type == 'remote_asset':
|
|
|
|
'format_id': stream.get('profile'),
|
|
|
|
video_info['url'] = url
|
|
|
|
'width': int_or_none(stream.get('width')),
|
|
|
|
return video_info
|
|
|
|
'height': int_or_none(stream.get('height')),
|
|
|
|
if delivery_type == 'hls':
|
|
|
|
'abr': int_or_none(stream.get('audio_bitrate')),
|
|
|
|
formats.extend(self._extract_m3u8_formats(url, embed_code, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
|
|
|
|
'vbr': int_or_none(stream.get('video_bitrate')),
|
|
|
|
elif delivery_type == 'hds':
|
|
|
|
})
|
|
|
|
formats.extend(self._extract_f4m_formats(url, embed_code, -1, 'hds', fatal=False))
|
|
|
|
if formats:
|
|
|
|
else:
|
|
|
|
return {
|
|
|
|
formats.append({
|
|
|
|
'id': video_id,
|
|
|
|
'url': url,
|
|
|
|
'formats': formats,
|
|
|
|
'ext': stream.get('delivery_type'),
|
|
|
|
'title': 'Ooyala video',
|
|
|
|
'vcodec': stream.get('video_codec'),
|
|
|
|
}
|
|
|
|
'format_id': '%s-%s-%sp' % (stream.get('profile'), delivery_type, stream.get('height')),
|
|
|
|
|
|
|
|
'width': int_or_none(stream.get('width')),
|
|
|
|
if not cur_auth_data['authorized']:
|
|
|
|
'height': int_or_none(stream.get('height')),
|
|
|
|
raise ExtractorError(cur_auth_data['message'], expected=True)
|
|
|
|
'abr': int_or_none(stream.get('audio_bitrate')),
|
|
|
|
|
|
|
|
'vbr': int_or_none(stream.get('video_bitrate')),
|
|
|
|
if not videos_info:
|
|
|
|
'fps': float_or_none(stream.get('framerate')),
|
|
|
|
raise ExtractorError('Unable to extract info')
|
|
|
|
})
|
|
|
|
videos_info = videos_info.replace('\\"', '"')
|
|
|
|
else:
|
|
|
|
videos_more_info = self._search_regex(
|
|
|
|
raise ExtractorError('%s said: %s' % (self.IE_NAME, cur_auth_data['message']), expected=True)
|
|
|
|
r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"')
|
|
|
|
self._sort_formats(formats)
|
|
|
|
videos_info = json.loads(videos_info)
|
|
|
|
|
|
|
|
videos_more_info = json.loads(videos_more_info)
|
|
|
|
video_info['formats'] = formats
|
|
|
|
|
|
|
|
return video_info
|
|
|
|
if videos_more_info.get('lineup'):
|
|
|
|
|
|
|
|
videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
|
|
|
'_type': 'playlist',
|
|
|
|
|
|
|
|
'id': video_id,
|
|
|
|
|
|
|
|
'title': unescapeHTML(videos_more_info['title']),
|
|
|
|
|
|
|
|
'entries': videos,
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
else:
|
|
|
|
|
|
|
|
return self._extract_result(videos_info[0], videos_more_info)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class OoyalaIE(OoyalaBaseIE):
|
|
|
|
class OoyalaIE(OoyalaBaseIE):
|
|
|
|
@ -117,6 +78,7 @@ class OoyalaIE(OoyalaBaseIE):
|
|
|
|
'ext': 'mp4',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'title': 'Explaining Data Recovery from Hard Drives and SSDs',
|
|
|
|
'title': 'Explaining Data Recovery from Hard Drives and SSDs',
|
|
|
|
'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
|
|
|
|
'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
|
|
|
|
|
|
|
|
'duration': 853386,
|
|
|
|
},
|
|
|
|
},
|
|
|
|
}, {
|
|
|
|
}, {
|
|
|
|
# Only available for ipad
|
|
|
|
# Only available for ipad
|
|
|
|
@ -125,7 +87,7 @@ class OoyalaIE(OoyalaBaseIE):
|
|
|
|
'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
|
|
|
|
'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'title': 'Simulation Overview - Levels of Simulation',
|
|
|
|
'title': 'Simulation Overview - Levels of Simulation',
|
|
|
|
'description': '',
|
|
|
|
'duration': 194948,
|
|
|
|
},
|
|
|
|
},
|
|
|
|
},
|
|
|
|
},
|
|
|
|
{
|
|
|
|
{
|
|
|
|
@ -136,7 +98,8 @@ class OoyalaIE(OoyalaBaseIE):
|
|
|
|
'info_dict': {
|
|
|
|
'info_dict': {
|
|
|
|
'id': 'FiOG81ZTrvckcchQxmalf4aQj590qTEx',
|
|
|
|
'id': 'FiOG81ZTrvckcchQxmalf4aQj590qTEx',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'title': 'Ooyala video',
|
|
|
|
'title': 'Divide Tool Path.mp4',
|
|
|
|
|
|
|
|
'duration': 204405,
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
]
|
|
|
|
]
|
|
|
|
@ -151,9 +114,11 @@ class OoyalaIE(OoyalaBaseIE):
|
|
|
|
ie=cls.ie_key())
|
|
|
|
ie=cls.ie_key())
|
|
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
|
|
|
url, smuggled_data = unsmuggle_url(url, {})
|
|
|
|
embed_code = self._match_id(url)
|
|
|
|
embed_code = self._match_id(url)
|
|
|
|
player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code
|
|
|
|
domain = smuggled_data.get('domain')
|
|
|
|
return self._extract(player_url, embed_code)
|
|
|
|
content_tree_url = 'http://player.ooyala.com/player_api/v1/content_tree/embed_code/%s/%s' % (embed_code, embed_code)
|
|
|
|
|
|
|
|
return self._extract(content_tree_url, embed_code, domain)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class OoyalaExternalIE(OoyalaBaseIE):
|
|
|
|
class OoyalaExternalIE(OoyalaBaseIE):
|
|
|
|
@ -170,7 +135,7 @@ class OoyalaExternalIE(OoyalaBaseIE):
|
|
|
|
.*?&pcode=
|
|
|
|
.*?&pcode=
|
|
|
|
)
|
|
|
|
)
|
|
|
|
(?P<pcode>.+?)
|
|
|
|
(?P<pcode>.+?)
|
|
|
|
(&|$)
|
|
|
|
(?:&|$)
|
|
|
|
'''
|
|
|
|
'''
|
|
|
|
|
|
|
|
|
|
|
|
_TEST = {
|
|
|
|
_TEST = {
|
|
|
|
@ -179,7 +144,7 @@ class OoyalaExternalIE(OoyalaBaseIE):
|
|
|
|
'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
|
|
|
|
'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'title': 'dm_140128_30for30Shorts___JudgingJewellv2',
|
|
|
|
'title': 'dm_140128_30for30Shorts___JudgingJewellv2',
|
|
|
|
'description': '',
|
|
|
|
'duration': 1302000,
|
|
|
|
},
|
|
|
|
},
|
|
|
|
'params': {
|
|
|
|
'params': {
|
|
|
|
# m3u8 download
|
|
|
|
# m3u8 download
|
|
|
|
@ -188,9 +153,6 @@ class OoyalaExternalIE(OoyalaBaseIE):
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
def _real_extract(self, url):
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
partner_id, video_id, pcode = re.match(self._VALID_URL, url).groups()
|
|
|
|
partner_id = mobj.group('partner_id')
|
|
|
|
content_tree_url = 'http://player.ooyala.com/player_api/v1/content_tree/external_id/%s/%s:%s' % (pcode, partner_id, video_id)
|
|
|
|
video_id = mobj.group('id')
|
|
|
|
return self._extract(content_tree_url, video_id)
|
|
|
|
pcode = mobj.group('pcode')
|
|
|
|
|
|
|
|
player_url = 'http://player.ooyala.com/player.js?externalId=%s:%s&pcode=%s' % (partner_id, video_id, pcode)
|
|
|
|
|
|
|
|
return self._extract(player_url, video_id)
|
|
|
|
|
|
|
|
|
remitamine
9 years ago