Merge branch 'master' into fix.25.12.2018
This commit is contained in:
Avi Peretz
commit
116be746cd
@ -7,6 +7,7 @@ import functools
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
try_get,
|
||||
@ -27,7 +28,7 @@ class ACastIE(InfoExtractor):
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
|
||||
'md5': 'a02393c74f3bdb1801c3ec2695577ce0',
|
||||
'md5': '16d936099ec5ca2d5869e3a813ee8dc4',
|
||||
'info_dict': {
|
||||
'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
|
||||
'ext': 'mp3',
|
||||
@ -46,28 +47,37 @@ class ACastIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'https://play.acast.com/s/rattegangspodden/s04e09-styckmordet-i-helenelund-del-22',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
channel, display_id = re.match(self._VALID_URL, url).groups()
|
||||
s = self._download_json(
|
||||
'https://play-api.acast.com/stitch/%s/%s' % (channel, display_id),
|
||||
display_id)['result']
|
||||
'https://feeder.acast.com/api/v1/shows/%s/episodes/%s' % (channel, display_id),
|
||||
display_id)
|
||||
media_url = s['url']
|
||||
if re.search(r'[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12}', display_id):
|
||||
episode_url = s.get('episodeUrl')
|
||||
if episode_url:
|
||||
display_id = episode_url
|
||||
else:
|
||||
channel, display_id = re.match(self._VALID_URL, s['link']).groups()
|
||||
cast_data = self._download_json(
|
||||
'https://play-api.acast.com/splash/%s/%s' % (channel, display_id),
|
||||
display_id)['result']
|
||||
e = cast_data['episode']
|
||||
title = e['name']
|
||||
title = e.get('name') or s['title']
|
||||
return {
|
||||
'id': compat_str(e['id']),
|
||||
'display_id': display_id,
|
||||
'url': media_url,
|
||||
'title': title,
|
||||
'description': e.get('description') or e.get('summary'),
|
||||
'description': e.get('summary') or clean_html(e.get('description') or s.get('description')),
|
||||
'thumbnail': e.get('image'),
|
||||
'timestamp': unified_timestamp(e.get('publishingDate')),
|
||||
'duration': float_or_none(s.get('duration') or e.get('duration')),
|
||||
'timestamp': unified_timestamp(e.get('publishingDate') or s.get('publishDate')),
|
||||
'duration': float_or_none(e.get('duration') or s.get('duration')),
|
||||
'filesize': int_or_none(e.get('contentLength')),
|
||||
'creator': try_get(cast_data, lambda x: x['show']['author'], compat_str),
|
||||
'series': try_get(cast_data, lambda x: x['show']['name'], compat_str),
|
||||
|
||||
@ -137,10 +137,16 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
urls = []
|
||||
# Look for embedded Dailymotion player
|
||||
matches = re.findall(
|
||||
r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
|
||||
return list(map(lambda m: unescapeHTML(m[1]), matches))
|
||||
# https://developer.dailymotion.com/player#player-parameters
|
||||
for mobj in re.finditer(
|
||||
r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage):
|
||||
urls.append(unescapeHTML(mobj.group('url')))
|
||||
for mobj in re.finditer(
|
||||
r'(?s)DM\.player\([^,]+,\s*{.*?video[\'"]?\s*:\s*["\']?(?P<id>[0-9a-zA-Z]+).+?}\s*\);', webpage):
|
||||
urls.append('https://www.dailymotion.com/embed/video/' + mobj.group('id'))
|
||||
return urls
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
@ -2104,6 +2104,23 @@ class GenericIE(InfoExtractor):
|
||||
},
|
||||
'expected_warnings': ['Failed to download MPD manifest'],
|
||||
},
|
||||
{
|
||||
# DailyMotion embed with DM.player
|
||||
'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
|
||||
'info_dict': {
|
||||
'id': 'k6aKkGHd9FJs4mtJN39',
|
||||
'ext': 'mp4',
|
||||
'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
|
||||
'description': 'This video is private.',
|
||||
'uploader_id': 'x1jf30l',
|
||||
'uploader': 'beIN SPORTS USA',
|
||||
'upload_date': '20190528',
|
||||
'timestamp': 1559062971,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
# {
|
||||
# # TODO: find another test
|
||||
# # http://schema.org/VideoObject
|
||||
|
||||
@ -243,7 +243,7 @@ class PhantomJSwrapper(object):
|
||||
|
||||
|
||||
class OpenloadIE(InfoExtractor):
|
||||
_DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|life|live|space|services|website)|oladblock\.(?:services|xyz|me)|openloed\.co)'
|
||||
_DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|life|live|space|services|website)|oladblock\.(?:services|xyz|me)|openloed\.co)'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?P<host>
|
||||
@ -365,6 +365,9 @@ class OpenloadIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'https://oload.life/embed/oOzZjNPw9Dc/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://oload.biz/f/bEk3Gp8ARr4/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://oladblock.services/f/b8NWEgkqNLI/',
|
||||
'only_matching': True,
|
||||
|
||||
@ -2,7 +2,7 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
import time
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urlparse
|
||||
from ..utils import (
|
||||
@ -247,7 +247,7 @@ class TwitterCardIE(TwitterBaseIE):
|
||||
'%s/guest/activate.json' % self._API_BASE, video_id,
|
||||
'Downloading guest token', data=b'',
|
||||
headers=headers)['guest_token']
|
||||
self._set_cookie('api.twitter.com', 'gt', guest_token)
|
||||
self._set_cookie('api.twitter.com', 'gt', guest_token, expire_time=time.time() + 3000)
|
||||
else:
|
||||
guest_token = guest_token_c.value
|
||||
|
||||
|
||||
@ -7,7 +7,7 @@ from ..utils import int_or_none
|
||||
|
||||
|
||||
class XiamiBaseIE(InfoExtractor):
|
||||
_API_BASE_URL = 'http://www.xiami.com/song/playlist/cat/json/id'
|
||||
_API_BASE_URL = 'https://emumo.xiami.com/song/playlist/cat/json/id'
|
||||
|
||||
def _download_webpage_handle(self, *args, **kwargs):
|
||||
webpage = super(XiamiBaseIE, self)._download_webpage_handle(*args, **kwargs)
|
||||
|
||||
@ -37,7 +37,7 @@ class YourPornIE(InfoExtractor):
|
||||
self._search_regex(
|
||||
r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
|
||||
group='data'),
|
||||
video_id)[video_id]).replace('/cdn/', '/cdn4/')
|
||||
video_id)[video_id]).replace('/cdn/', '/cdn5/')
|
||||
|
||||
title = (self._search_regex(
|
||||
r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user