mirror of https://github.com/yt-dlp/yt-dlp
Merge branch 'master' of github.com-rndusr:rg3/youtube-dl into fix/str-item-assignment
Random User
8 years ago
commit
4f06c1c9fc
@ -0,0 +1,73 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
unescapeHTML,
|
||||
)
|
||||
|
||||
|
||||
class ATVAtIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?atv\.at/(?:[^/]+/){2}(?P<id>[dv]\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://atv.at/aktuell/di-210317-2005-uhr/v1698449/',
|
||||
'md5': 'c3b6b975fb3150fc628572939df205f2',
|
||||
'info_dict': {
|
||||
'id': '1698447',
|
||||
'ext': 'mp4',
|
||||
'title': 'DI, 21.03.17 | 20:05 Uhr 1/1',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://atv.at/aktuell/meinrad-knapp/d8416/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
video_data = self._parse_json(unescapeHTML(self._search_regex(
|
||||
r'class="[^"]*jsb_video/FlashPlayer[^"]*"[^>]+data-jsb="([^"]+)"',
|
||||
webpage, 'player data')), display_id)['config']['initial_video']
|
||||
|
||||
video_id = video_data['id']
|
||||
video_title = video_data['title']
|
||||
|
||||
parts = []
|
||||
for part in video_data.get('parts', []):
|
||||
part_id = part['id']
|
||||
part_title = part['title']
|
||||
|
||||
formats = []
|
||||
for source in part.get('sources', []):
|
||||
source_url = source.get('src')
|
||||
if not source_url:
|
||||
continue
|
||||
ext = determine_ext(source_url)
|
||||
if ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
source_url, part_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
else:
|
||||
formats.append({
|
||||
'format_id': source.get('delivery'),
|
||||
'url': source_url,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
parts.append({
|
||||
'id': part_id,
|
||||
'title': part_title,
|
||||
'thumbnail': part.get('preview_image_url'),
|
||||
'duration': int_or_none(part.get('duration')),
|
||||
'is_live': part.get('is_livestream'),
|
||||
'formats': formats,
|
||||
})
|
||||
|
||||
return {
|
||||
'_type': 'multi_video',
|
||||
'id': video_id,
|
||||
'title': video_title,
|
||||
'entries': parts,
|
||||
}
|
||||
@ -0,0 +1,72 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
)
|
||||
|
||||
|
||||
class BostonGlobeIE(InfoExtractor):
|
||||
_VALID_URL = r'(?i)https?://(?:www\.)?bostonglobe\.com/.*/(?P<id>[^/]+)/\w+(?:\.html)?'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.bostonglobe.com/metro/2017/02/11/tree-finally-succumbs-disease-leaving-hole-neighborhood/h1b4lviqzMTIn9sVy8F3gP/story.html',
|
||||
'md5': '0a62181079c85c2d2b618c9a738aedaf',
|
||||
'info_dict': {
|
||||
'title': 'A tree finally succumbs to disease, leaving a hole in a neighborhood',
|
||||
'id': '5320421710001',
|
||||
'ext': 'mp4',
|
||||
'description': 'It arrived as a sapling when the Back Bay was in its infancy, a spindly American elm tamped down into a square of dirt cut into the brick sidewalk of 1880s Marlborough Street, no higher than the first bay window of the new brownstone behind it.',
|
||||
'timestamp': 1486877593,
|
||||
'upload_date': '20170212',
|
||||
'uploader_id': '245991542',
|
||||
},
|
||||
},
|
||||
{
|
||||
# Embedded youtube video; we hand it off to the Generic extractor.
|
||||
'url': 'https://www.bostonglobe.com/lifestyle/names/2017/02/17/does-ben-affleck-play-matt-damon-favorite-version-batman/ruqkc9VxKBYmh5txn1XhSI/story.html',
|
||||
'md5': '582b40327089d5c0c949b3c54b13c24b',
|
||||
'info_dict': {
|
||||
'title': "Who Is Matt Damon's Favorite Batman?",
|
||||
'id': 'ZW1QCnlA6Qc',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20170217',
|
||||
'description': 'md5:3b3dccb9375867e0b4d527ed87d307cb',
|
||||
'uploader': 'The Late Late Show with James Corden',
|
||||
'uploader_id': 'TheLateLateShow',
|
||||
},
|
||||
'expected_warnings': ['404'],
|
||||
},
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
page_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, page_id)
|
||||
|
||||
page_title = self._og_search_title(webpage, default=None)
|
||||
|
||||
# <video data-brightcove-video-id="5320421710001" data-account="245991542" data-player="SJWAiyYWg" data-embed="default" class="video-js" controls itemscope itemtype="http://schema.org/VideoObject">
|
||||
entries = []
|
||||
for video in re.findall(r'(?i)(<video[^>]+>)', webpage):
|
||||
attrs = extract_attributes(video)
|
||||
|
||||
video_id = attrs.get('data-brightcove-video-id')
|
||||
account_id = attrs.get('data-account')
|
||||
player_id = attrs.get('data-player')
|
||||
embed = attrs.get('data-embed')
|
||||
|
||||
if video_id and account_id and player_id and embed:
|
||||
entries.append(
|
||||
'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
|
||||
% (account_id, player_id, embed, video_id))
|
||||
|
||||
if len(entries) == 0:
|
||||
return self.url_result(url, 'Generic')
|
||||
elif len(entries) == 1:
|
||||
return self.url_result(entries[0], 'BrightcoveNew')
|
||||
else:
|
||||
return self.playlist_from_matches(entries, page_id, page_title, ie='BrightcoveNew')
|
||||
@ -1,97 +1,56 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_HTTPError,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
HEADRequest,
|
||||
remove_end,
|
||||
str_to_int,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
class CloudyIE(InfoExtractor):
|
||||
_IE_DESC = 'cloudy.ec'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?cloudy\.ec/
|
||||
(?:v/|embed\.php\?id=)
|
||||
(?P<id>[A-Za-z0-9]+)
|
||||
'''
|
||||
_EMBED_URL = 'http://www.cloudy.ec/embed.php?id=%s'
|
||||
_API_URL = 'http://www.cloudy.ec/api/player.api.php'
|
||||
_MAX_TRIES = 2
|
||||
_TEST = {
|
||||
_VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.cloudy.ec/v/af511e2527aac',
|
||||
'md5': '5cb253ace826a42f35b4740539bedf07',
|
||||
'md5': '29832b05028ead1b58be86bf319397ca',
|
||||
'info_dict': {
|
||||
'id': 'af511e2527aac',
|
||||
'ext': 'flv',
|
||||
'ext': 'mp4',
|
||||
'title': 'Funny Cats and Animals Compilation june 2013',
|
||||
'upload_date': '20130913',
|
||||
'view_count': int,
|
||||
}
|
||||
}
|
||||
|
||||
def _extract_video(self, video_id, file_key, error_url=None, try_num=0):
|
||||
|
||||
if try_num > self._MAX_TRIES - 1:
|
||||
raise ExtractorError('Unable to extract video URL', expected=True)
|
||||
|
||||
form = {
|
||||
'file': video_id,
|
||||
'key': file_key,
|
||||
}
|
||||
|
||||
if error_url:
|
||||
form.update({
|
||||
'numOfErrors': try_num,
|
||||
'errorCode': '404',
|
||||
'errorUrl': error_url,
|
||||
})
|
||||
}, {
|
||||
'url': 'http://www.cloudy.ec/embed.php?autoplay=1&id=af511e2527aac',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
player_data = self._download_webpage(
|
||||
self._API_URL, video_id, 'Downloading player data', query=form)
|
||||
data = compat_parse_qs(player_data)
|
||||
|
||||
try_num += 1
|
||||
|
||||
if 'error' in data:
|
||||
raise ExtractorError(
|
||||
'%s error: %s' % (self.IE_NAME, ' '.join(data['error_msg'])),
|
||||
expected=True)
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
title = data.get('title', [None])[0]
|
||||
if title:
|
||||
title = remove_end(title, '&asdasdas').strip()
|
||||
webpage = self._download_webpage(
|
||||
'http://www.cloudy.ec/embed.php?id=%s' % video_id, video_id)
|
||||
|
||||
video_url = data.get('url', [None])[0]
|
||||
info = self._parse_html5_media_entries(url, webpage, video_id)[0]
|
||||
|
||||
if video_url:
|
||||
try:
|
||||
self._request_webpage(HEADRequest(video_url), video_id, 'Checking video URL')
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code in [404, 410]:
|
||||
self.report_warning('Invalid video URL, requesting another', video_id)
|
||||
return self._extract_video(video_id, file_key, video_url, try_num)
|
||||
webpage = self._download_webpage(
|
||||
'https://www.cloudy.ec/v/%s' % video_id, video_id, fatal=False)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
if webpage:
|
||||
info.update({
|
||||
'title': self._search_regex(
|
||||
r'<h\d[^>]*>([^<]+)<', webpage, 'title'),
|
||||
'upload_date': unified_strdate(self._search_regex(
|
||||
r'>Published at (\d{4}-\d{1,2}-\d{1,2})', webpage,
|
||||
'upload date', fatal=False)),
|
||||
'view_count': str_to_int(self._search_regex(
|
||||
r'([\d,.]+) views<', webpage, 'view count', fatal=False)),
|
||||
})
|
||||
|
||||
url = self._EMBED_URL % video_id
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
if not info.get('title'):
|
||||
info['title'] = video_id
|
||||
|
||||
file_key = self._search_regex(
|
||||
[r'key\s*:\s*"([^"]+)"', r'filekey\s*=\s*"([^"]+)"'],
|
||||
webpage, 'file_key')
|
||||
info['id'] = video_id
|
||||
|
||||
return self._extract_video(video_id, file_key)
|
||||
return info
|
||||
|
||||
@ -0,0 +1,259 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class MedialaanIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:www\.)?
|
||||
(?:
|
||||
(?P<site_id>vtm|q2|vtmkzoom)\.be/
|
||||
(?:
|
||||
video(?:/[^/]+/id/|/?\?.*?\baid=)|
|
||||
(?:[^/]+/)*
|
||||
)
|
||||
)
|
||||
(?P<id>[^/?#&]+)
|
||||
'''
|
||||
_NETRC_MACHINE = 'medialaan'
|
||||
_APIKEY = '3_HZ0FtkMW_gOyKlqQzW5_0FHRC7Nd5XpXJZcDdXY4pk5eES2ZWmejRW5egwVm4ug-'
|
||||
_SITE_TO_APP_ID = {
|
||||
'vtm': 'vtm_watch',
|
||||
'q2': 'q2',
|
||||
'vtmkzoom': 'vtmkzoom',
|
||||
}
|
||||
_TESTS = [{
|
||||
# vod
|
||||
'url': 'http://vtm.be/video/volledige-afleveringen/id/vtm_20170219_VM0678361_vtmwatch',
|
||||
'info_dict': {
|
||||
'id': 'vtm_20170219_VM0678361_vtmwatch',
|
||||
'ext': 'mp4',
|
||||
'title': 'Allemaal Chris afl. 6',
|
||||
'description': 'md5:4be86427521e7b07e0adb0c9c554ddb2',
|
||||
'timestamp': 1487533280,
|
||||
'upload_date': '20170219',
|
||||
'duration': 2562,
|
||||
'series': 'Allemaal Chris',
|
||||
'season': 'Allemaal Chris',
|
||||
'season_number': 1,
|
||||
'season_id': '256936078124527',
|
||||
'episode': 'Allemaal Chris afl. 6',
|
||||
'episode_number': 6,
|
||||
'episode_id': '256936078591527',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'Requires account credentials',
|
||||
}, {
|
||||
# clip
|
||||
'url': 'http://vtm.be/video?aid=168332',
|
||||
'info_dict': {
|
||||
'id': '168332',
|
||||
'ext': 'mp4',
|
||||
'title': '"Veronique liegt!"',
|
||||
'description': 'md5:1385e2b743923afe54ba4adc38476155',
|
||||
'timestamp': 1489002029,
|
||||
'upload_date': '20170308',
|
||||
'duration': 96,
|
||||
},
|
||||
}, {
|
||||
# vod
|
||||
'url': 'http://vtm.be/video/volledige-afleveringen/id/257107153551000',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# vod
|
||||
'url': 'http://vtm.be/video?aid=163157',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# vod
|
||||
'url': 'http://www.q2.be/video/volledige-afleveringen/id/2be_20170301_VM0684442_q2',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# clip
|
||||
'url': 'http://vtmkzoom.be/k3-dansstudio/een-nieuw-seizoen-van-k3-dansstudio',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
self._logged_in = False
|
||||
|
||||
def _login(self):
|
||||
username, password = self._get_login_info()
|
||||
if username is None:
|
||||
self.raise_login_required()
|
||||
|
||||
auth_data = {
|
||||
'APIKey': self._APIKEY,
|
||||
'sdk': 'js_6.1',
|
||||
'format': 'json',
|
||||
'loginID': username,
|
||||
'password': password,
|
||||
}
|
||||
|
||||
auth_info = self._download_json(
|
||||
'https://accounts.eu1.gigya.com/accounts.login', None,
|
||||
note='Logging in', errnote='Unable to log in',
|
||||
data=urlencode_postdata(auth_data))
|
||||
|
||||
error_message = auth_info.get('errorDetails') or auth_info.get('errorMessage')
|
||||
if error_message:
|
||||
raise ExtractorError(
|
||||
'Unable to login: %s' % error_message, expected=True)
|
||||
|
||||
self._uid = auth_info['UID']
|
||||
self._uid_signature = auth_info['UIDSignature']
|
||||
self._signature_timestamp = auth_info['signatureTimestamp']
|
||||
|
||||
self._logged_in = True
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id, site_id = mobj.group('id', 'site_id')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
config = self._parse_json(
|
||||
self._search_regex(
|
||||
r'videoJSConfig\s*=\s*JSON\.parse\(\'({.+?})\'\);',
|
||||
webpage, 'config', default='{}'), video_id,
|
||||
transform_source=lambda s: s.replace(
|
||||
'\\\\', '\\').replace(r'\"', '"').replace(r"\'", "'"))
|
||||
|
||||
vod_id = config.get('vodId') or self._search_regex(
|
||||
(r'\\"vodId\\"\s*:\s*\\"(.+?)\\"',
|
||||
r'<[^>]+id=["\']vod-(\d+)'),
|
||||
webpage, 'video_id', default=None)
|
||||
|
||||
# clip, no authentication required
|
||||
if not vod_id:
|
||||
player = self._parse_json(
|
||||
self._search_regex(
|
||||
r'vmmaplayer\(({.+?})\);', webpage, 'vmma player',
|
||||
default=''),
|
||||
video_id, transform_source=lambda s: '[%s]' % s, fatal=False)
|
||||
if player:
|
||||
video = player[-1]
|
||||
info = {
|
||||
'id': video_id,
|
||||
'url': video['videoUrl'],
|
||||
'title': video['title'],
|
||||
'thumbnail': video.get('imageUrl'),
|
||||
'timestamp': int_or_none(video.get('createdDate')),
|
||||
'duration': int_or_none(video.get('duration')),
|
||||
}
|
||||
else:
|
||||
info = self._parse_html5_media_entries(
|
||||
url, webpage, video_id, m3u8_id='hls')[0]
|
||||
info.update({
|
||||
'id': video_id,
|
||||
'title': self._html_search_meta('description', webpage),
|
||||
'duration': parse_duration(self._html_search_meta('duration', webpage)),
|
||||
})
|
||||
# vod, authentication required
|
||||
else:
|
||||
if not self._logged_in:
|
||||
self._login()
|
||||
|
||||
settings = self._parse_json(
|
||||
self._search_regex(
|
||||
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
|
||||
webpage, 'drupal settings', default='{}'),
|
||||
video_id)
|
||||
|
||||
def get(container, item):
|
||||
return try_get(
|
||||
settings, lambda x: x[container][item],
|
||||
compat_str) or self._search_regex(
|
||||
r'"%s"\s*:\s*"([^"]+)' % item, webpage, item,
|
||||
default=None)
|
||||
|
||||
app_id = get('vod', 'app_id') or self._SITE_TO_APP_ID.get(site_id, 'vtm_watch')
|
||||
sso = get('vod', 'gigyaDatabase') or 'vtm-sso'
|
||||
|
||||
data = self._download_json(
|
||||
'http://vod.medialaan.io/api/1.0/item/%s/video' % vod_id,
|
||||
video_id, query={
|
||||
'app_id': app_id,
|
||||
'user_network': sso,
|
||||
'UID': self._uid,
|
||||
'UIDSignature': self._uid_signature,
|
||||
'signatureTimestamp': self._signature_timestamp,
|
||||
})
|
||||
|
||||
formats = self._extract_m3u8_formats(
|
||||
data['response']['uri'], video_id, entry_protocol='m3u8_native',
|
||||
ext='mp4', m3u8_id='hls')
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
info = {
|
||||
'id': vod_id,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
api_key = get('vod', 'apiKey')
|
||||
channel = get('medialaanGigya', 'channel')
|
||||
|
||||
if api_key:
|
||||
videos = self._download_json(
|
||||
'http://vod.medialaan.io/vod/v2/videos', video_id, fatal=False,
|
||||
query={
|
||||
'channels': channel,
|
||||
'ids': vod_id,
|
||||
'limit': 1,
|
||||
'apikey': api_key,
|
||||
})
|
||||
if videos:
|
||||
video = try_get(
|
||||
videos, lambda x: x['response']['videos'][0], dict)
|
||||
if video:
|
||||
def get(container, item, expected_type=None):
|
||||
return try_get(
|
||||
video, lambda x: x[container][item], expected_type)
|
||||
|
||||
def get_string(container, item):
|
||||
return get(container, item, compat_str)
|
||||
|
||||
info.update({
|
||||
'series': get_string('program', 'title'),
|
||||
'season': get_string('season', 'title'),
|
||||
'season_number': int_or_none(get('season', 'number')),
|
||||
'season_id': get_string('season', 'id'),
|
||||
'episode': get_string('episode', 'title'),
|
||||
'episode_number': int_or_none(get('episode', 'number')),
|
||||
'episode_id': get_string('episode', 'id'),
|
||||
'duration': int_or_none(
|
||||
video.get('duration')) or int_or_none(
|
||||
video.get('durationMillis'), scale=1000),
|
||||
'title': get_string('episode', 'title'),
|
||||
'description': get_string('episode', 'text'),
|
||||
'timestamp': unified_timestamp(get_string(
|
||||
'publication', 'begin')),
|
||||
})
|
||||
|
||||
if not info.get('title'):
|
||||
info['title'] = try_get(
|
||||
config, lambda x: x['videoConfig']['title'],
|
||||
compat_str) or self._html_search_regex(
|
||||
r'\\"title\\"\s*:\s*\\"(.+?)\\"', webpage, 'title',
|
||||
default=None) or self._og_search_title(webpage)
|
||||
|
||||
if not info.get('description'):
|
||||
info['description'] = self._html_search_regex(
|
||||
r'<div[^>]+class="field-item\s+even">\s*<p>(.+?)</p>',
|
||||
webpage, 'description', default=None)
|
||||
|
||||
return info
|
||||
@ -0,0 +1,122 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_HTTPError
|
||||
from ..utils import (
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
try_get,
|
||||
# unified_timestamp,
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
|
||||
class RedBullTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?redbull\.tv/(?:video|film)/(?P<id>AP-\w+)'
|
||||
_TESTS = [{
|
||||
# film
|
||||
'url': 'https://www.redbull.tv/video/AP-1Q756YYX51W11/abc-of-wrc',
|
||||
'md5': 'fb0445b98aa4394e504b413d98031d1f',
|
||||
'info_dict': {
|
||||
'id': 'AP-1Q756YYX51W11',
|
||||
'ext': 'mp4',
|
||||
'title': 'ABC of...WRC',
|
||||
'description': 'md5:5c7ed8f4015c8492ecf64b6ab31e7d31',
|
||||
'duration': 1582.04,
|
||||
# 'timestamp': 1488405786,
|
||||
# 'upload_date': '20170301',
|
||||
},
|
||||
}, {
|
||||
# episode
|
||||
'url': 'https://www.redbull.tv/video/AP-1PMT5JCWH1W11/grime?playlist=shows:shows-playall:web',
|
||||
'info_dict': {
|
||||
'id': 'AP-1PMT5JCWH1W11',
|
||||
'ext': 'mp4',
|
||||
'title': 'Grime - Hashtags S2 E4',
|
||||
'description': 'md5:334b741c8c1ce65be057eab6773c1cf5',
|
||||
'duration': 904.6,
|
||||
# 'timestamp': 1487290093,
|
||||
# 'upload_date': '20170217',
|
||||
'series': 'Hashtags',
|
||||
'season_number': 2,
|
||||
'episode_number': 4,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.redbull.tv/film/AP-1MSKKF5T92111/in-motion',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
session = self._download_json(
|
||||
'https://api-v2.redbull.tv/session', video_id,
|
||||
note='Downloading access token', query={
|
||||
'build': '4.370.0',
|
||||
'category': 'personal_computer',
|
||||
'os_version': '1.0',
|
||||
'os_family': 'http',
|
||||
})
|
||||
if session.get('code') == 'error':
|
||||
raise ExtractorError('%s said: %s' % (
|
||||
self.IE_NAME, session['message']))
|
||||
auth = '%s %s' % (session.get('token_type', 'Bearer'), session['access_token'])
|
||||
|
||||
try:
|
||||
info = self._download_json(
|
||||
'https://api-v2.redbull.tv/content/%s' % video_id,
|
||||
video_id, note='Downloading video information',
|
||||
headers={'Authorization': auth}
|
||||
)
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
|
||||
error_message = self._parse_json(
|
||||
e.cause.read().decode(), video_id)['message']
|
||||
raise ExtractorError('%s said: %s' % (
|
||||
self.IE_NAME, error_message), expected=True)
|
||||
raise
|
||||
|
||||
video = info['video_product']
|
||||
|
||||
title = info['title'].strip()
|
||||
|
||||
formats = self._extract_m3u8_formats(
|
||||
video['url'], video_id, 'mp4', 'm3u8_native')
|
||||
self._sort_formats(formats)
|
||||
|
||||
subtitles = {}
|
||||
for _, captions in (try_get(
|
||||
video, lambda x: x['attachments']['captions'],
|
||||
dict) or {}).items():
|
||||
if not captions or not isinstance(captions, list):
|
||||
continue
|
||||
for caption in captions:
|
||||
caption_url = caption.get('url')
|
||||
if not caption_url:
|
||||
continue
|
||||
ext = caption.get('format')
|
||||
if ext == 'xml':
|
||||
ext = 'ttml'
|
||||
subtitles.setdefault(caption.get('lang') or 'en', []).append({
|
||||
'url': caption_url,
|
||||
'ext': ext,
|
||||
})
|
||||
|
||||
subheading = info.get('subheading')
|
||||
if subheading:
|
||||
title += ' - %s' % subheading
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': info.get('long_description') or info.get(
|
||||
'short_description'),
|
||||
'duration': float_or_none(video.get('duration'), scale=1000),
|
||||
# 'timestamp': unified_timestamp(info.get('published')),
|
||||
'series': info.get('show_title'),
|
||||
'season_number': int_or_none(info.get('season_number')),
|
||||
'episode_number': int_or_none(info.get('episode_number')),
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
@ -0,0 +1,81 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
)
|
||||
|
||||
|
||||
class ToonGogglesIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?toongoggles\.com/shows/(?P<show_id>\d+)(?:/[^/]+/episodes/(?P<episode_id>\d+))?'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.toongoggles.com/shows/217143/bernard-season-2/episodes/217147/football',
|
||||
'md5': '18289fc2b951eff6b953a9d8f01e6831',
|
||||
'info_dict': {
|
||||
'id': '217147',
|
||||
'ext': 'mp4',
|
||||
'title': 'Football',
|
||||
'uploader_id': '1',
|
||||
'description': 'Bernard decides to play football in order to be better than Lloyd and tries to beat him no matter how, he even cheats.',
|
||||
'upload_date': '20160718',
|
||||
'timestamp': 1468879330,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.toongoggles.com/shows/227759/om-nom-stories-around-the-world',
|
||||
'info_dict': {
|
||||
'id': '227759',
|
||||
'title': 'Om Nom Stories Around The World',
|
||||
},
|
||||
'playlist_mincount': 11,
|
||||
}]
|
||||
|
||||
def _call_api(self, action, page_id, query):
|
||||
query.update({
|
||||
'for_ng': 1,
|
||||
'for_web': 1,
|
||||
'show_meta': 1,
|
||||
'version': 7.0,
|
||||
})
|
||||
return self._download_json('http://api.toongoggles.com/' + action, page_id, query=query)
|
||||
|
||||
def _parse_episode_data(self, episode_data):
|
||||
title = episode_data['episode_name']
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': episode_data['episode_id'],
|
||||
'title': title,
|
||||
'url': 'kaltura:513551:' + episode_data['entry_id'],
|
||||
'thumbnail': episode_data.get('thumbnail_url'),
|
||||
'description': episode_data.get('description'),
|
||||
'duration': parse_duration(episode_data.get('hms')),
|
||||
'series': episode_data.get('show_name'),
|
||||
'season_number': int_or_none(episode_data.get('season_num')),
|
||||
'episode_id': episode_data.get('episode_id'),
|
||||
'episode': title,
|
||||
'episode_number': int_or_none(episode_data.get('episode_num')),
|
||||
'categories': episode_data.get('categories'),
|
||||
'ie_key': 'Kaltura',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
show_id, episode_id = re.match(self._VALID_URL, url).groups()
|
||||
if episode_id:
|
||||
episode_data = self._call_api('search', episode_id, {
|
||||
'filter': 'episode',
|
||||
'id': episode_id,
|
||||
})['objects'][0]
|
||||
return self._parse_episode_data(episode_data)
|
||||
else:
|
||||
show_data = self._call_api('getepisodesbyshow', show_id, {
|
||||
'max': 1000000000,
|
||||
'showid': show_id,
|
||||
})
|
||||
entries = []
|
||||
for episode_data in show_data.get('objects', []):
|
||||
entries.append(self._parse_episode_data(episode_data))
|
||||
return self.playlist_result(entries, show_id, show_data.get('show_name'))
|
||||
@ -0,0 +1,90 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
)
|
||||
|
||||
|
||||
class TunePkIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
(?:www\.)?tune\.pk/(?:video/|player/embed_player.php?.*?\bvid=)|
|
||||
embed\.tune\.pk/play/
|
||||
)
|
||||
(?P<id>\d+)
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'https://tune.pk/video/6919541/maudie-2017-international-trailer-1-ft-ethan-hawke-sally-hawkins',
|
||||
'md5': '0c537163b7f6f97da3c5dd1e3ef6dd55',
|
||||
'info_dict': {
|
||||
'id': '6919541',
|
||||
'ext': 'mp4',
|
||||
'title': 'Maudie (2017) | International Trailer # 1 ft Ethan Hawke, Sally Hawkins',
|
||||
'description': 'md5:eb5a04114fafef5cec90799a93a2d09c',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'timestamp': 1487327564,
|
||||
'upload_date': '20170217',
|
||||
'uploader': 'Movie Trailers',
|
||||
'duration': 107,
|
||||
'view_count': int,
|
||||
}
|
||||
}, {
|
||||
'url': 'https://tune.pk/player/embed_player.php?vid=6919541&folder=2017/02/17/&width=600&height=350&autoplay=no',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://embed.tune.pk/play/6919541?autoplay=no&ssl=yes&inline=true',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(
|
||||
'https://tune.pk/video/%s' % video_id, video_id)
|
||||
|
||||
details = self._parse_json(
|
||||
self._search_regex(
|
||||
r'new\s+TunePlayer\(({.+?})\)\s*;\s*\n', webpage, 'tune player'),
|
||||
video_id)['details']
|
||||
|
||||
video = details['video']
|
||||
title = video.get('title') or self._og_search_title(
|
||||
webpage, default=None) or self._html_search_meta(
|
||||
'title', webpage, 'title', fatal=True)
|
||||
|
||||
formats = self._parse_jwplayer_formats(
|
||||
details['player']['sources'], video_id)
|
||||
self._sort_formats(formats)
|
||||
|
||||
description = self._og_search_description(
|
||||
webpage, default=None) or self._html_search_meta(
|
||||
'description', webpage, 'description')
|
||||
|
||||
thumbnail = video.get('thumb') or self._og_search_thumbnail(
|
||||
webpage, default=None) or self._html_search_meta(
|
||||
'thumbnail', webpage, 'thumbnail')
|
||||
|
||||
timestamp = unified_timestamp(video.get('date_added'))
|
||||
uploader = try_get(
|
||||
video, lambda x: x['uploader']['name'],
|
||||
compat_str) or self._html_search_meta('author', webpage, 'author')
|
||||
|
||||
duration = int_or_none(video.get('duration'))
|
||||
view_count = int_or_none(video.get('views'))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'timestamp': timestamp,
|
||||
'uploader': uploader,
|
||||
'duration': duration,
|
||||
'view_count': view_count,
|
||||
'formats': formats,
|
||||
}
|
||||
@ -0,0 +1,80 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .brightcove import BrightcoveNewIE
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_age_limit,
|
||||
smuggle_url,
|
||||
unescapeHTML,
|
||||
)
|
||||
|
||||
|
||||
class VrakIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?vrak\.tv/videos\?.*?\btarget=(?P<id>[\d.]+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.vrak.tv/videos?target=1.2306782&filtre=emission&id=1.1806721',
|
||||
'info_dict': {
|
||||
'id': '5345661243001',
|
||||
'ext': 'mp4',
|
||||
'title': 'Obésité, film de hockey et Roseline Filion',
|
||||
'timestamp': 1488492126,
|
||||
'upload_date': '20170302',
|
||||
'uploader_id': '2890187628001',
|
||||
'creator': 'VRAK.TV',
|
||||
'age_limit': 8,
|
||||
'series': 'ALT (Actualité Légèrement Tordue)',
|
||||
'episode': 'Obésité, film de hockey et Roseline Filion',
|
||||
'tags': list,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/2890187628001/default_default/index.html?videoId=%s'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'<h\d\b[^>]+\bclass=["\']videoTitle["\'][^>]*>([^<]+)',
|
||||
webpage, 'title', default=None) or self._og_search_title(webpage)
|
||||
|
||||
content = self._parse_json(
|
||||
self._search_regex(
|
||||
r'data-player-options-content=(["\'])(?P<content>{.+?})\1',
|
||||
webpage, 'content', default='{}', group='content'),
|
||||
video_id, transform_source=unescapeHTML)
|
||||
|
||||
ref_id = content.get('refId') or self._search_regex(
|
||||
r'refId":"([^&]+)"', webpage, 'ref id')
|
||||
|
||||
brightcove_id = self._search_regex(
|
||||
r'''(?x)
|
||||
java\.lang\.String\s+value\s*=\s*["']brightcove\.article\.\d+\.%s
|
||||
[^>]*
|
||||
java\.lang\.String\s+value\s*=\s*["'](\d+)
|
||||
''' % re.escape(ref_id), webpage, 'brightcove id')
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': BrightcoveNewIE.ie_key(),
|
||||
'url': smuggle_url(
|
||||
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
|
||||
{'geo_countries': ['CA']}),
|
||||
'id': brightcove_id,
|
||||
'description': content.get('description'),
|
||||
'creator': content.get('brand'),
|
||||
'age_limit': parse_age_limit(content.get('rating')),
|
||||
'series': content.get('showName') or content.get(
|
||||
'episodeName'), # this is intentional
|
||||
'season_number': int_or_none(content.get('seasonNumber')),
|
||||
'episode': title,
|
||||
'episode_number': int_or_none(content.get('episodeNumber')),
|
||||
'tags': content.get('tags', []),
|
||||
}
|
||||
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2017.02.27'
|
||||
__version__ = '2017.03.24'
|
||||
|
||||
Loading…
Reference in New Issue