Update to ytdl-commit-3be0980

3be098010f
This commit is contained in:
pukkandan 2021-03-15 04:52:06 +05:30
parent 7275535116
commit 10db0d2f57
No known key found for this signature in database
GPG key ID: 0F00D95A001F4698
17 changed files with 356 additions and 253 deletions

View file

@ -1794,12 +1794,16 @@ class YoutubeDL(object):
if 'display_id' not in info_dict and 'id' in info_dict: if 'display_id' not in info_dict and 'id' in info_dict:
info_dict['display_id'] = info_dict['id'] info_dict['display_id'] = info_dict['id']
if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None: for ts_key, date_key in (
('timestamp', 'upload_date'),
('release_timestamp', 'release_date'),
):
if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
# Working around out-of-range timestamp values (e.g. negative ones on Windows, # Working around out-of-range timestamp values (e.g. negative ones on Windows,
# see http://bugs.python.org/issue1646728) # see http://bugs.python.org/issue1646728)
try: try:
upload_date = datetime.datetime.utcfromtimestamp(info_dict['timestamp']) upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
info_dict['upload_date'] = upload_date.strftime('%Y%m%d') info_dict[date_key] = upload_date.strftime('%Y%m%d')
except (ValueError, OverflowError, OSError): except (ValueError, OverflowError, OSError):
pass pass

View file

@ -42,6 +42,7 @@ class ApplePodcastsIE(InfoExtractor):
ember_data = self._parse_json(self._search_regex( ember_data = self._parse_json(self._search_regex(
r'id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<', r'id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
webpage, 'ember data'), episode_id) webpage, 'ember data'), episode_id)
ember_data = ember_data.get(episode_id) or ember_data
episode = ember_data['data']['attributes'] episode = ember_data['data']['attributes']
description = episode.get('description') or {} description = episode.get('description') or {}

View file

@ -49,6 +49,7 @@ class BandcampIE(InfoExtractor):
'uploader': 'Ben Prunty', 'uploader': 'Ben Prunty',
'timestamp': 1396508491, 'timestamp': 1396508491,
'upload_date': '20140403', 'upload_date': '20140403',
'release_timestamp': 1396483200,
'release_date': '20140403', 'release_date': '20140403',
'duration': 260.877, 'duration': 260.877,
'track': 'Lanius (Battle)', 'track': 'Lanius (Battle)',
@ -69,6 +70,7 @@ class BandcampIE(InfoExtractor):
'uploader': 'Mastodon', 'uploader': 'Mastodon',
'timestamp': 1322005399, 'timestamp': 1322005399,
'upload_date': '20111122', 'upload_date': '20111122',
'release_timestamp': 1076112000,
'release_date': '20040207', 'release_date': '20040207',
'duration': 120.79, 'duration': 120.79,
'track': 'Hail to Fire', 'track': 'Hail to Fire',
@ -197,7 +199,7 @@ class BandcampIE(InfoExtractor):
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'uploader': artist, 'uploader': artist,
'timestamp': timestamp, 'timestamp': timestamp,
'release_date': unified_strdate(tralbum.get('album_release_date')), 'release_timestamp': unified_timestamp(tralbum.get('album_release_date')),
'duration': duration, 'duration': duration,
'track': track, 'track': track,
'track_number': track_number, 'track_number': track_number,

View file

@ -138,11 +138,6 @@ class BiliBiliIE(InfoExtractor):
anime_id = mobj.group('anime_id') anime_id = mobj.group('anime_id')
page_id = mobj.group('page') page_id = mobj.group('page')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
headers = {
'Referer': url,
'Accept': '*/*'
}
headers.update(self.geo_verification_headers())
if 'anime/' not in url: if 'anime/' not in url:
cid = self._search_regex( cid = self._search_regex(
@ -160,8 +155,12 @@ class BiliBiliIE(InfoExtractor):
if 'no_bangumi_tip' not in smuggled_data: if 'no_bangumi_tip' not in smuggled_data:
self.to_screen('Downloading episode %s. To download all videos in anime %s, re-run yt-dlp with %s' % ( self.to_screen('Downloading episode %s. To download all videos in anime %s, re-run yt-dlp with %s' % (
video_id, anime_id, compat_urlparse.urljoin(url, '//bangumi.bilibili.com/anime/%s' % anime_id))) video_id, anime_id, compat_urlparse.urljoin(url, '//bangumi.bilibili.com/anime/%s' % anime_id)))
headers = {
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Referer': url
}
headers.update(self.geo_verification_headers())
headers['Content-Type'] = 'application/x-www-form-urlencoded; charset=UTF-8'
js = self._download_json( js = self._download_json(
'http://bangumi.bilibili.com/web_api/get_source', video_id, 'http://bangumi.bilibili.com/web_api/get_source', video_id,
data=urlencode_postdata({'episode_id': video_id}), data=urlencode_postdata({'episode_id': video_id}),
@ -170,6 +169,12 @@ class BiliBiliIE(InfoExtractor):
self._report_error(js) self._report_error(js)
cid = js['result']['cid'] cid = js['result']['cid']
headers = {
'Accept': 'application/json',
'Referer': url
}
headers.update(self.geo_verification_headers())
entries = [] entries = []
RENDITIONS = ('qn=80&quality=80&type=', 'quality=2&type=mp4') RENDITIONS = ('qn=80&quality=80&type=', 'quality=2&type=mp4')

View file

@ -27,7 +27,7 @@ class CBSBaseIE(ThePlatformFeedIE):
class CBSIE(CBSBaseIE): class CBSIE(CBSBaseIE):
_VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:(?:cbs\.com|paramountplus\.com)/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)' _VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:(?:cbs|paramountplus)\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/', 'url': 'https://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
@ -53,7 +53,7 @@ class CBSIE(CBSBaseIE):
'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/', 'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://www.paramountplus.com/shows/star-trek-discovery/video/l5ANMH9wM7kxwV1qr4u1xn88XOhYMlZX/star-trek-discovery-the-vulcan-hello/', 'url': 'https://www.paramountplus.com/shows/all-rise/video/QmR1WhNkh1a_IrdHZrbcRklm176X_rVc/all-rise-space/',
'only_matching': True, 'only_matching': True,
}] }]

View file

@ -231,8 +231,9 @@ class InfoExtractor(object):
uploader: Full name of the video uploader. uploader: Full name of the video uploader.
license: License name the video is licensed under. license: License name the video is licensed under.
creator: The creator of the video. creator: The creator of the video.
release_timestamp: UNIX timestamp of the moment the video was released.
release_date: The date (YYYYMMDD) when the video was released. release_date: The date (YYYYMMDD) when the video was released.
timestamp: UNIX timestamp of the moment the video became available. timestamp: UNIX timestamp of the moment the video was uploaded
upload_date: Video upload date (YYYYMMDD). upload_date: Video upload date (YYYYMMDD).
If not explicitly set, calculated from timestamp. If not explicitly set, calculated from timestamp.
uploader_id: Nickname or id of the video uploader. uploader_id: Nickname or id of the video uploader.

View file

@ -17,7 +17,7 @@ class FujiTVFODPlus7IE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
formats = self._extract_m3u8_formats( formats = self._extract_m3u8_formats(
self._BASE_URL + 'abr/pc_html5/%s.m3u8' % video_id, video_id) self._BASE_URL + 'abr/pc_html5/%s.m3u8' % video_id, video_id, 'mp4')
for f in formats: for f in formats:
wh = self._BITRATE_MAP.get(f.get('tbr')) wh = self._BITRATE_MAP.get(f.get('tbr'))
if wh: if wh:

View file

@ -6,8 +6,10 @@ import json
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_parse_qs,
compat_str, compat_str,
compat_urllib_parse_unquote, compat_urllib_parse_unquote,
compat_urllib_parse_urlparse,
) )
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
@ -62,6 +64,7 @@ class LBRYBaseIE(InfoExtractor):
'description': stream_value.get('description'), 'description': stream_value.get('description'),
'license': stream_value.get('license'), 'license': stream_value.get('license'),
'timestamp': int_or_none(stream.get('timestamp')), 'timestamp': int_or_none(stream.get('timestamp')),
'release_timestamp': int_or_none(stream_value.get('release_time')),
'tags': stream_value.get('tags'), 'tags': stream_value.get('tags'),
'duration': int_or_none(media.get('duration')), 'duration': int_or_none(media.get('duration')),
'channel': try_get(signing_channel, lambda x: x['value']['title']), 'channel': try_get(signing_channel, lambda x: x['value']['title']),
@ -94,6 +97,8 @@ class LBRYIE(LBRYBaseIE):
'description': 'md5:f6cb5c704b332d37f5119313c2c98f51', 'description': 'md5:f6cb5c704b332d37f5119313c2c98f51',
'timestamp': 1595694354, 'timestamp': 1595694354,
'upload_date': '20200725', 'upload_date': '20200725',
'release_timestamp': 1595340697,
'release_date': '20200721',
'width': 1280, 'width': 1280,
'height': 720, 'height': 720,
} }
@ -108,6 +113,8 @@ class LBRYIE(LBRYBaseIE):
'description': 'md5:661ac4f1db09f31728931d7b88807a61', 'description': 'md5:661ac4f1db09f31728931d7b88807a61',
'timestamp': 1591312601, 'timestamp': 1591312601,
'upload_date': '20200604', 'upload_date': '20200604',
'release_timestamp': 1591312421,
'release_date': '20200604',
'tags': list, 'tags': list,
'duration': 2570, 'duration': 2570,
'channel': 'The LBRY Foundation', 'channel': 'The LBRY Foundation',
@ -189,17 +196,18 @@ class LBRYChannelIE(LBRYBaseIE):
}] }]
_PAGE_SIZE = 50 _PAGE_SIZE = 50
def _fetch_page(self, claim_id, url, page): def _fetch_page(self, claim_id, url, params, page):
page += 1 page += 1
result = self._call_api_proxy( page_params = {
'claim_search', claim_id, {
'channel_ids': [claim_id], 'channel_ids': [claim_id],
'claim_type': 'stream', 'claim_type': 'stream',
'no_totals': True, 'no_totals': True,
'page': page, 'page': page,
'page_size': self._PAGE_SIZE, 'page_size': self._PAGE_SIZE,
'stream_types': self._SUPPORTED_STREAM_TYPES, }
}, 'page %d' % page) page_params.update(params)
result = self._call_api_proxy(
'claim_search', claim_id, page_params, 'page %d' % page)
for item in (result.get('items') or []): for item in (result.get('items') or []):
stream_claim_name = item.get('name') stream_claim_name = item.get('name')
stream_claim_id = item.get('claim_id') stream_claim_id = item.get('claim_id')
@ -220,8 +228,31 @@ class LBRYChannelIE(LBRYBaseIE):
result = self._resolve_url( result = self._resolve_url(
'lbry://' + display_id, display_id, 'channel') 'lbry://' + display_id, display_id, 'channel')
claim_id = result['claim_id'] claim_id = result['claim_id']
qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
content = qs.get('content', [None])[0]
params = {
'fee_amount': qs.get('fee_amount', ['>=0'])[0],
'order_by': {
'new': ['release_time'],
'top': ['effective_amount'],
'trending': ['trending_group', 'trending_mixed'],
}[qs.get('order', ['new'])[0]],
'stream_types': [content] if content in ['audio', 'video'] else self._SUPPORTED_STREAM_TYPES,
}
duration = qs.get('duration', [None])[0]
if duration:
params['duration'] = {
'long': '>=1200',
'short': '<=240',
}[duration]
language = qs.get('language', ['all'])[0]
if language != 'all':
languages = [language]
if language == 'en':
languages.append('none')
params['any_languages'] = languages
entries = OnDemandPagedList( entries = OnDemandPagedList(
functools.partial(self._fetch_page, claim_id, url), functools.partial(self._fetch_page, claim_id, url, params),
self._PAGE_SIZE) self._PAGE_SIZE)
result_value = result.get('value') or {} result_value = result.get('value') or {}
return self.playlist_result( return self.playlist_result(

View file

@ -599,11 +599,13 @@ class PeerTubeIE(InfoExtractor):
else: else:
age_limit = None age_limit = None
webpage_url = 'https://%s/videos/watch/%s' % (host, video_id)
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'description': description, 'description': description,
'thumbnail': urljoin(url, video.get('thumbnailPath')), 'thumbnail': urljoin(webpage_url, video.get('thumbnailPath')),
'timestamp': unified_timestamp(video.get('publishedAt')), 'timestamp': unified_timestamp(video.get('publishedAt')),
'uploader': account_data('displayName', compat_str), 'uploader': account_data('displayName', compat_str),
'uploader_id': str_or_none(account_data('id', int)), 'uploader_id': str_or_none(account_data('id', int)),
@ -621,5 +623,6 @@ class PeerTubeIE(InfoExtractor):
'tags': try_get(video, lambda x: x['tags'], list), 'tags': try_get(video, lambda x: x['tags'], list),
'categories': categories, 'categories': categories,
'formats': formats, 'formats': formats,
'subtitles': subtitles 'subtitles': subtitles,
'webpage_url': webpage_url,
} }

View file

@ -31,6 +31,7 @@ class PinterestBaseIE(InfoExtractor):
title = (data.get('title') or data.get('grid_title') or video_id).strip() title = (data.get('title') or data.get('grid_title') or video_id).strip()
urls = []
formats = [] formats = []
duration = None duration = None
if extract_formats: if extract_formats:
@ -38,8 +39,9 @@ class PinterestBaseIE(InfoExtractor):
if not isinstance(format_dict, dict): if not isinstance(format_dict, dict):
continue continue
format_url = url_or_none(format_dict.get('url')) format_url = url_or_none(format_dict.get('url'))
if not format_url: if not format_url or format_url in urls:
continue continue
urls.append(format_url)
duration = float_or_none(format_dict.get('duration'), scale=1000) duration = float_or_none(format_dict.get('duration'), scale=1000)
ext = determine_ext(format_url) ext = determine_ext(format_url)
if 'hls' in format_id.lower() or ext == 'm3u8': if 'hls' in format_id.lower() or ext == 'm3u8':

View file

@ -167,6 +167,7 @@ class PornHubIE(PornHubBaseIE):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
'skip': 'Video has been flagged for verification in accordance with our trust and safety policy',
}, { }, {
# subtitles # subtitles
'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7', 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
@ -265,7 +266,8 @@ class PornHubIE(PornHubBaseIE):
webpage = dl_webpage('pc') webpage = dl_webpage('pc')
error_msg = self._html_search_regex( error_msg = self._html_search_regex(
r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>', (r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
r'(?s)<section[^>]+class=["\']noVideo["\'][^>]*>(?P<error>.+?)</section>'),
webpage, 'error message', default=None, group='error') webpage, 'error message', default=None, group='error')
if error_msg: if error_msg:
error_msg = re.sub(r'\s+', ' ', error_msg) error_msg = re.sub(r'\s+', ' ', error_msg)
@ -394,6 +396,21 @@ class PornHubIE(PornHubBaseIE):
upload_date = None upload_date = None
formats = [] formats = []
def add_format(format_url, height=None):
tbr = None
mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', format_url)
if mobj:
if not height:
height = int(mobj.group('height'))
tbr = int(mobj.group('tbr'))
formats.append({
'url': format_url,
'format_id': '%dp' % height if height else None,
'height': height,
'tbr': tbr,
})
for video_url, height in video_urls: for video_url, height in video_urls:
if not upload_date: if not upload_date:
upload_date = self._search_regex( upload_date = self._search_regex(
@ -410,18 +427,19 @@ class PornHubIE(PornHubBaseIE):
video_url, video_id, 'mp4', entry_protocol='m3u8_native', video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)) m3u8_id='hls', fatal=False))
continue continue
tbr = None if '/video/get_media' in video_url:
mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url) medias = self._download_json(video_url, video_id, fatal=False)
if mobj: if isinstance(medias, list):
if not height: for media in medias:
height = int(mobj.group('height')) if not isinstance(media, dict):
tbr = int(mobj.group('tbr')) continue
formats.append({ video_url = url_or_none(media.get('videoUrl'))
'url': video_url, if not video_url:
'format_id': '%dp' % height if height else None, continue
'height': height, height = int_or_none(media.get('quality'))
'tbr': tbr, add_format(video_url, height)
}) continue
add_format(video_url)
self._sort_formats(formats) self._sort_formats(formats)
video_uploader = self._html_search_regex( video_uploader = self._html_search_regex(

View file

@ -2,8 +2,9 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import base64 import base64
import io
import re import re
import time import sys
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
@ -14,56 +15,13 @@ from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
float_or_none, float_or_none,
qualities,
remove_end, remove_end,
remove_start, remove_start,
sanitized_Request,
std_headers, std_headers,
) )
_bytes_to_chr = (lambda x: x) if sys.version_info[0] == 2 else (lambda x: map(chr, x))
def _decrypt_url(png):
encrypted_data = compat_b64decode(png)
text_index = encrypted_data.find(b'tEXt')
text_chunk = encrypted_data[text_index - 4:]
length = compat_struct_unpack('!I', text_chunk[:4])[0]
# Use bytearray to get integers when iterating in both python 2.x and 3.x
data = bytearray(text_chunk[8:8 + length])
data = [chr(b) for b in data if b != 0]
hash_index = data.index('#')
alphabet_data = data[:hash_index]
url_data = data[hash_index + 1:]
if url_data[0] == 'H' and url_data[3] == '%':
# remove useless HQ%% at the start
url_data = url_data[4:]
alphabet = []
e = 0
d = 0
for l in alphabet_data:
if d == 0:
alphabet.append(l)
d = e = (e + 1) % 4
else:
d -= 1
url = ''
f = 0
e = 3
b = 1
for letter in url_data:
if f == 0:
l = int(letter) * 10
f = 1
else:
if e == 0:
l += int(letter)
url += alphabet[l]
e = (b + 3) % 4
f = 0
b += 1
else:
e -= 1
return url
class RTVEALaCartaIE(InfoExtractor): class RTVEALaCartaIE(InfoExtractor):
@ -79,28 +37,31 @@ class RTVEALaCartaIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia', 'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
'duration': 5024.566, 'duration': 5024.566,
'series': 'Balonmano',
}, },
'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
}, { }, {
'note': 'Live stream', 'note': 'Live stream',
'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/', 'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
'info_dict': { 'info_dict': {
'id': '1694255', 'id': '1694255',
'ext': 'flv', 'ext': 'mp4',
'title': 'TODO', 'title': 're:^24H LIVE [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'is_live': True,
},
'params': {
'skip_download': 'live stream',
}, },
'skip': 'The f4m manifest can\'t be used yet',
}, { }, {
'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/', 'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
'md5': 'e55e162379ad587e9640eda4f7353c0f', 'md5': 'd850f3c8731ea53952ebab489cf81cbf',
'info_dict': { 'info_dict': {
'id': '4236788', 'id': '4236788',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Servir y proteger - Capítulo 104 ', 'title': 'Servir y proteger - Capítulo 104',
'duration': 3222.0, 'duration': 3222.0,
}, },
'params': { 'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
'skip_download': True, # requires ffmpeg
},
}, { }, {
'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve', 'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
'only_matching': True, 'only_matching': True,
@ -111,58 +72,102 @@ class RTVEALaCartaIE(InfoExtractor):
def _real_initialize(self): def _real_initialize(self):
user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8') user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
manager_info = self._download_json( self._manager = self._download_json(
'http://www.rtve.es/odin/loki/' + user_agent_b64, 'http://www.rtve.es/odin/loki/' + user_agent_b64,
None, 'Fetching manager info') None, 'Fetching manager info')['manager']
self._manager = manager_info['manager']
@staticmethod
def _decrypt_url(png):
encrypted_data = io.BytesIO(compat_b64decode(png)[8:])
while True:
length = compat_struct_unpack('!I', encrypted_data.read(4))[0]
chunk_type = encrypted_data.read(4)
if chunk_type == b'IEND':
break
data = encrypted_data.read(length)
if chunk_type == b'tEXt':
alphabet_data, text = data.split(b'\0')
quality, url_data = text.split(b'%%')
alphabet = []
e = 0
d = 0
for l in _bytes_to_chr(alphabet_data):
if d == 0:
alphabet.append(l)
d = e = (e + 1) % 4
else:
d -= 1
url = ''
f = 0
e = 3
b = 1
for letter in _bytes_to_chr(url_data):
if f == 0:
l = int(letter) * 10
f = 1
else:
if e == 0:
l += int(letter)
url += alphabet[l]
e = (b + 3) % 4
f = 0
b += 1
else:
e -= 1
yield quality.decode(), url
encrypted_data.read(4) # CRC
def _extract_png_formats(self, video_id):
png = self._download_webpage(
'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id),
video_id, 'Downloading url information', query={'q': 'v2'})
q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
formats = []
for quality, video_url in self._decrypt_url(png):
ext = determine_ext(video_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
elif ext == 'mpd':
formats.extend(self._extract_mpd_formats(
video_url, video_id, 'dash', fatal=False))
else:
formats.append({
'format_id': quality,
'quality': q(quality),
'url': video_url,
})
self._sort_formats(formats)
return formats
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
info = self._download_json( info = self._download_json(
'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id, 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
video_id)['page']['items'][0] video_id)['page']['items'][0]
if info['state'] == 'DESPU': if info['state'] == 'DESPU':
raise ExtractorError('The video is no longer available', expected=True) raise ExtractorError('The video is no longer available', expected=True)
title = info['title'] title = info['title'].strip()
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id) formats = self._extract_png_formats(video_id)
png_request = sanitized_Request(png_url)
png_request.add_header('Referer', url)
png = self._download_webpage(png_request, video_id, 'Downloading url information')
video_url = _decrypt_url(png)
ext = determine_ext(video_url)
formats = []
if not video_url.endswith('.f4m') and ext != 'm3u8':
if '?' not in video_url:
video_url = video_url.replace('resources/', 'auth/resources/')
video_url = video_url.replace('.net.rtve', '.multimedia.cdn.rtve')
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
video_url, video_id, f4m_id='hds', fatal=False))
else:
formats.append({
'url': video_url,
})
self._sort_formats(formats)
subtitles = None subtitles = None
if info.get('sbtFile') is not None: sbt_file = info.get('sbtFile')
subtitles = self.extract_subtitles(video_id, info['sbtFile']) if sbt_file:
subtitles = self.extract_subtitles(video_id, sbt_file)
is_live = info.get('live') is True
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': self._live_title(title) if is_live else title,
'formats': formats, 'formats': formats,
'thumbnail': info.get('image'), 'thumbnail': info.get('image'),
'page_url': url,
'subtitles': subtitles, 'subtitles': subtitles,
'duration': float_or_none(info.get('duration'), scale=1000), 'duration': float_or_none(info.get('duration'), 1000),
'is_live': is_live,
'series': info.get('programTitle'),
} }
def _get_subtitles(self, video_id, sub_file): def _get_subtitles(self, video_id, sub_file):
@ -174,48 +179,26 @@ class RTVEALaCartaIE(InfoExtractor):
for s in subs) for s in subs)
class RTVEInfantilIE(InfoExtractor): class RTVEInfantilIE(RTVEALaCartaIE):
IE_NAME = 'rtve.es:infantil' IE_NAME = 'rtve.es:infantil'
IE_DESC = 'RTVE infantil' IE_DESC = 'RTVE infantil'
_VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/' _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/[^/]+/video/[^/]+/(?P<id>[0-9]+)/'
_TESTS = [{ _TESTS = [{
'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/', 'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
'md5': '915319587b33720b8e0357caaa6617e6', 'md5': '5747454717aedf9f9fdf212d1bcfc48d',
'info_dict': { 'info_dict': {
'id': '3040283', 'id': '3040283',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Maneras de vivir', 'title': 'Maneras de vivir',
'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG', 'thumbnail': r're:https?://.+/1426182947956\.JPG',
'duration': 357.958, 'duration': 357.958,
}, },
'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
}] }]
def _real_extract(self, url):
video_id = self._match_id(url)
info = self._download_json(
'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
video_id)['page']['items'][0]
webpage = self._download_webpage(url, video_id) class RTVELiveIE(RTVEALaCartaIE):
vidplayer_id = self._search_regex(
r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
png = self._download_webpage(png_url, video_id, 'Downloading url information')
video_url = _decrypt_url(png)
return {
'id': video_id,
'ext': 'mp4',
'title': info['title'],
'url': video_url,
'thumbnail': info.get('image'),
'duration': float_or_none(info.get('duration'), scale=1000),
}
class RTVELiveIE(InfoExtractor):
IE_NAME = 'rtve.es:live' IE_NAME = 'rtve.es:live'
IE_DESC = 'RTVE.es live streams' IE_DESC = 'RTVE.es live streams'
_VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)' _VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
@ -225,7 +208,7 @@ class RTVELiveIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': 'la-1', 'id': 'la-1',
'ext': 'mp4', 'ext': 'mp4',
'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$', 'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
}, },
'params': { 'params': {
'skip_download': 'live stream', 'skip_download': 'live stream',
@ -234,29 +217,22 @@ class RTVELiveIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
start_time = time.gmtime()
video_id = mobj.group('id') video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es') title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
title = remove_start(title, 'Estoy viendo ') title = remove_start(title, 'Estoy viendo ')
title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
vidplayer_id = self._search_regex( vidplayer_id = self._search_regex(
(r'playerId=player([0-9]+)', (r'playerId=player([0-9]+)',
r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)', r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
r'data-id=["\'](\d+)'), r'data-id=["\'](\d+)'),
webpage, 'internal video ID') webpage, 'internal video ID')
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
png = self._download_webpage(png_url, video_id, 'Downloading url information')
m3u8_url = _decrypt_url(png)
formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': self._live_title(title),
'formats': formats, 'formats': self._extract_png_formats(vidplayer_id),
'is_live': True, 'is_live': True,
} }

View file

@ -51,13 +51,16 @@ class ShahidIE(ShahidBaseIE):
_NETRC_MACHINE = 'shahid' _NETRC_MACHINE = 'shahid'
_VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)' _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AC%D9%84%D8%B3-%D8%A7%D9%84%D8%B4%D8%A8%D8%A7%D8%A8-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-275286', 'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AA%D8%AD%D9%81-%D8%A7%D9%84%D8%AF%D8%AD%D9%8A%D8%AD-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-816924',
'info_dict': { 'info_dict': {
'id': '275286', 'id': '816924',
'ext': 'mp4', 'ext': 'mp4',
'title': 'مجلس الشباب الموسم 1 كليب 1', 'title': 'متحف الدحيح الموسم 1 كليب 1',
'timestamp': 1506988800, 'timestamp': 1602806400,
'upload_date': '20171003', 'upload_date': '20201016',
'description': 'برومو',
'duration': 22,
'categories': ['كوميديا'],
}, },
'params': { 'params': {
# m3u8 download # m3u8 download
@ -109,12 +112,15 @@ class ShahidIE(ShahidBaseIE):
page_type = 'episode' page_type = 'episode'
playout = self._call_api( playout = self._call_api(
'playout/url/' + video_id, video_id)['playout'] 'playout/new/url/' + video_id, video_id)['playout']
if not self._downloader.params.get('allow_unplayable_formats') and playout.get('drm'): if not self._downloader.params.get('allow_unplayable_formats') and playout.get('drm'):
raise ExtractorError('This video is DRM protected.', expected=True) raise ExtractorError('This video is DRM protected.', expected=True)
formats = self._extract_m3u8_formats(playout['url'], video_id, 'mp4') formats = self._extract_m3u8_formats(re.sub(
# https://docs.aws.amazon.com/mediapackage/latest/ug/manifest-filtering.html
r'aws\.manifestfilter=[\w:;,-]+&?',
'', playout['url']), video_id, 'mp4')
self._sort_formats(formats) self._sort_formats(formats)
# video = self._call_api( # video = self._call_api(

View file

@ -6,9 +6,9 @@ from .mtv import MTVServicesInfoExtractor
class SouthParkIE(MTVServicesInfoExtractor): class SouthParkIE(MTVServicesInfoExtractor):
IE_NAME = 'southpark.cc.com' IE_NAME = 'southpark.cc.com'
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|(?:full-)?episodes|collections)/(?P<id>.+?)(\?|#|$))' _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark(?:\.cc|studios)\.com/(?:clips|(?:full-)?episodes|collections)/(?P<id>.+?)(\?|#|$))'
_FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss' _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
_TESTS = [{ _TESTS = [{
'url': 'http://southpark.cc.com/clips/104437/bat-daded#tab=featured', 'url': 'http://southpark.cc.com/clips/104437/bat-daded#tab=featured',
@ -23,8 +23,20 @@ class SouthParkIE(MTVServicesInfoExtractor):
}, { }, {
'url': 'http://southpark.cc.com/collections/7758/fan-favorites/1', 'url': 'http://southpark.cc.com/collections/7758/fan-favorites/1',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://www.southparkstudios.com/episodes/h4o269/south-park-stunning-and-brave-season-19-ep-1',
'only_matching': True,
}] }]
def _get_feed_query(self, uri):
return {
'accountOverride': 'intl.mtvi.com',
'arcEp': 'shared.southpark.global',
'ep': '90877963',
'imageEp': 'shared.southpark.global',
'mgid': uri,
}
class SouthParkEsIE(SouthParkIE): class SouthParkEsIE(SouthParkIE):
IE_NAME = 'southpark.cc.com:español' IE_NAME = 'southpark.cc.com:español'

View file

@ -1,82 +1,105 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import ( from ..utils import (
clean_html,
float_or_none,
int_or_none,
parse_iso8601, parse_iso8601,
sanitized_Request, strip_or_none,
try_get,
) )
class SportDeutschlandIE(InfoExtractor): class SportDeutschlandIE(InfoExtractor):
_VALID_URL = r'https?://sportdeutschland\.tv/(?P<sport>[^/?#]+)/(?P<id>[^?#/]+)(?:$|[?#])' _VALID_URL = r'https?://sportdeutschland\.tv/(?P<id>(?:[^/]+/)?[^?#/&]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0', 'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0',
'info_dict': { 'info_dict': {
'id': 're-live-deutsche-meisterschaften-2020-halbfinals', 'id': '5318cac0275701382770543d7edaf0a0',
'ext': 'mp4', 'ext': 'mp4',
'title': 're:Re-live: Deutsche Meisterschaften 2020.*Halbfinals', 'title': 'Re-live: Deutsche Meisterschaften 2020 - Halbfinals - Teil 1',
'categories': ['Badminton-Deutschland'], 'duration': 16106.36,
'view_count': int,
'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
'timestamp': int,
'upload_date': '20200201',
'description': 're:.*', # meaningless description for THIS video
}, },
'params': {
'noplaylist': True,
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0',
'info_dict': {
'id': 'c6e2fdd01f63013854c47054d2ab776f',
'title': 'Re-live: Deutsche Meisterschaften 2020 - Halbfinals',
'description': 'md5:5263ff4c31c04bb780c9f91130b48530',
'duration': 31397,
},
'playlist_count': 2,
}, {
'url': 'https://sportdeutschland.tv/freeride-world-tour-2021-fieberbrunn-oesterreich',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) display_id = self._match_id(url)
video_id = mobj.group('id') data = self._download_json(
sport_id = mobj.group('sport') 'https://backend.sportdeutschland.tv/api/permalinks/' + display_id,
display_id, query={'access_token': 'true'})
api_url = 'https://proxy.vidibusdynamic.net/ssl/backend.sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % (
sport_id, video_id)
req = sanitized_Request(api_url, headers={
'Accept': 'application/vnd.vidibus.v2.html+json',
'Referer': url,
})
data = self._download_json(req, video_id)
asset = data['asset'] asset = data['asset']
categories = [data['section']['title']] title = (asset.get('title') or asset['label']).strip()
asset_id = asset.get('id') or asset.get('uuid')
formats = [] info = {
smil_url = asset['video'] 'id': asset_id,
if '.smil' in smil_url: 'title': title,
m3u8_url = smil_url.replace('.smil', '.m3u8') 'description': clean_html(asset.get('body') or asset.get('description')) or asset.get('teaser'),
formats.extend( 'duration': int_or_none(asset.get('seconds')),
self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')) }
videos = asset.get('videos') or []
smil_doc = self._download_xml( if len(videos) > 1:
smil_url, video_id, note='Downloading SMIL metadata') playlist_id = compat_parse_qs(compat_urllib_parse_urlparse(url).query).get('playlistId', [None])[0]
base_url_el = smil_doc.find('./head/meta') if playlist_id:
if base_url_el: if self._downloader.params.get('noplaylist'):
base_url = base_url_el.attrib['base'] videos = [videos[int(playlist_id)]]
formats.extend([{ self.to_screen('Downloading just a single video because of --no-playlist')
'format_id': 'rmtp',
'url': base_url if base_url_el else n.attrib['src'],
'play_path': n.attrib['src'],
'ext': 'flv',
'preference': -100,
'format_note': 'Seems to fail at example stream',
} for n in smil_doc.findall('./body/video')])
else: else:
formats.append({'url': smil_url}) self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % asset_id)
self._sort_formats(formats) def entries():
for i, video in enumerate(videos, 1):
return { video_id = video.get('uuid')
video_url = video.get('url')
if not (video_id and video_url):
continue
formats = self._extract_m3u8_formats(
video_url.replace('.smil', '.m3u8'), video_id, 'mp4', fatal=False)
if not formats:
continue
yield {
'id': video_id, 'id': video_id,
'formats': formats, 'formats': formats,
'title': asset['title'], 'title': title + ' - ' + (video.get('label') or 'Teil %d' % i),
'thumbnail': asset.get('image'), 'duration': float_or_none(video.get('duration')),
'description': asset.get('teaser'),
'duration': asset.get('duration'),
'categories': categories,
'view_count': asset.get('views'),
'rtmp_live': asset.get('live'),
'timestamp': parse_iso8601(asset.get('date')),
} }
info.update({
'_type': 'multi_video',
'entries': entries(),
})
else:
formats = self._extract_m3u8_formats(
videos[0]['url'].replace('.smil', '.m3u8'), asset_id, 'mp4')
section_title = strip_or_none(try_get(data, lambda x: x['section']['title']))
info.update({
'formats': formats,
'display_id': asset.get('permalink'),
'thumbnail': try_get(asset, lambda x: x['images'][0]),
'categories': [section_title] if section_title else None,
'view_count': int_or_none(asset.get('views')),
'is_live': asset.get('is_live') is True,
'timestamp': parse_iso8601(asset.get('date') or asset.get('published_at')),
})
return info

View file

@ -9,6 +9,7 @@ from ..utils import (
int_or_none, int_or_none,
remove_start, remove_start,
smuggle_url, smuggle_url,
strip_or_none,
try_get, try_get,
) )
@ -25,6 +26,10 @@ class TVerIE(InfoExtractor):
}, { }, {
'url': 'https://tver.jp/episode/79622438', 'url': 'https://tver.jp/episode/79622438',
'only_matching': True, 'only_matching': True,
}, {
# subtitle = ' '
'url': 'https://tver.jp/corner/f0068870',
'only_matching': True,
}] }]
_TOKEN = None _TOKEN = None
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
@ -47,8 +52,12 @@ class TVerIE(InfoExtractor):
} }
if service == 'cx': if service == 'cx':
title = main['title']
subtitle = strip_or_none(main.get('subtitle'))
if subtitle:
title += ' - ' + subtitle
info.update({ info.update({
'title': main.get('subtitle') or main['title'], 'title': title,
'url': 'https://i.fod.fujitv.co.jp/plus7/web/%s/%s.html' % (p_id[:4], p_id), 'url': 'https://i.fod.fujitv.co.jp/plus7/web/%s/%s.html' % (p_id[:4], p_id),
'ie_key': 'FujiTVFODPlus7', 'ie_key': 'FujiTVFODPlus7',
}) })

View file

@ -7,6 +7,8 @@ from ..compat import compat_urllib_parse_unquote
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
try_get,
unified_timestamp,
) )
@ -19,14 +21,17 @@ class VoxMediaVolumeIE(OnceIE):
setup = self._parse_json(self._search_regex( setup = self._parse_json(self._search_regex(
r'setup\s*=\s*({.+});', webpage, 'setup'), video_id) r'setup\s*=\s*({.+});', webpage, 'setup'), video_id)
video_data = setup.get('video') or {} player_setup = setup.get('player_setup') or setup
video_data = player_setup.get('video') or {}
formatted_metadata = video_data.get('formatted_metadata') or {}
info = { info = {
'id': video_id, 'id': video_id,
'title': video_data.get('title_short'), 'title': player_setup.get('title') or video_data.get('title_short'),
'description': video_data.get('description_long') or video_data.get('description_short'), 'description': video_data.get('description_long') or video_data.get('description_short'),
'thumbnail': video_data.get('brightcove_thumbnail') 'thumbnail': formatted_metadata.get('thumbnail') or video_data.get('brightcove_thumbnail'),
'timestamp': unified_timestamp(formatted_metadata.get('video_publish_date')),
} }
asset = setup.get('asset') or setup.get('params') or {} asset = try_get(setup, lambda x: x['embed_assets']['chorus'], dict) or {}
formats = [] formats = []
hls_url = asset.get('hls_url') hls_url = asset.get('hls_url')
@ -47,6 +52,7 @@ class VoxMediaVolumeIE(OnceIE):
if formats: if formats:
self._sort_formats(formats) self._sort_formats(formats)
info['formats'] = formats info['formats'] = formats
info['duration'] = int_or_none(asset.get('duration'))
return info return info
for provider_video_type in ('ooyala', 'youtube', 'brightcove'): for provider_video_type in ('ooyala', 'youtube', 'brightcove'):
@ -84,7 +90,7 @@ class VoxMediaIE(InfoExtractor):
}, { }, {
# Volume embed, Youtube # Volume embed, Youtube
'url': 'http://www.theverge.com/2014/10/21/7025853/google-nexus-6-hands-on-photos-video-android-phablet', 'url': 'http://www.theverge.com/2014/10/21/7025853/google-nexus-6-hands-on-photos-video-android-phablet',
'md5': '4c8f4a0937752b437c3ebc0ed24802b5', 'md5': 'fd19aa0cf3a0eea515d4fd5c8c0e9d68',
'info_dict': { 'info_dict': {
'id': 'Gy8Md3Eky38', 'id': 'Gy8Md3Eky38',
'ext': 'mp4', 'ext': 'mp4',
@ -93,6 +99,7 @@ class VoxMediaIE(InfoExtractor):
'uploader_id': 'TheVerge', 'uploader_id': 'TheVerge',
'upload_date': '20141021', 'upload_date': '20141021',
'uploader': 'The Verge', 'uploader': 'The Verge',
'timestamp': 1413907200,
}, },
'add_ie': ['Youtube'], 'add_ie': ['Youtube'],
'skip': 'similar to the previous test', 'skip': 'similar to the previous test',
@ -100,13 +107,13 @@ class VoxMediaIE(InfoExtractor):
# Volume embed, Youtube # Volume embed, Youtube
'url': 'http://www.vox.com/2016/3/31/11336640/mississippi-lgbt-religious-freedom-bill', 'url': 'http://www.vox.com/2016/3/31/11336640/mississippi-lgbt-religious-freedom-bill',
'info_dict': { 'info_dict': {
'id': 'YCjDnX-Xzhg', 'id': '22986359b',
'ext': 'mp4', 'ext': 'mp4',
'title': "Mississippi's laws are so bad that its anti-LGBTQ law isn't needed to allow discrimination", 'title': "Mississippi's laws are so bad that its anti-LGBTQ law isn't needed to allow discrimination",
'description': 'md5:fc1317922057de31cd74bce91eb1c66c', 'description': 'md5:fc1317922057de31cd74bce91eb1c66c',
'uploader_id': 'voxdotcom',
'upload_date': '20150915', 'upload_date': '20150915',
'uploader': 'Vox', 'timestamp': 1442332800,
'duration': 285,
}, },
'add_ie': ['Youtube'], 'add_ie': ['Youtube'],
'skip': 'similar to the previous test', 'skip': 'similar to the previous test',
@ -160,6 +167,9 @@ class VoxMediaIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Post-Post-PC CEO: The Full Code Conference Video of Microsoft\'s Satya Nadella', 'title': 'Post-Post-PC CEO: The Full Code Conference Video of Microsoft\'s Satya Nadella',
'description': 'The longtime veteran was chosen earlier this year as the software giant\'s third leader in its history.', 'description': 'The longtime veteran was chosen earlier this year as the software giant\'s third leader in its history.',
'timestamp': 1402938000,
'upload_date': '20140616',
'duration': 4114,
}, },
'add_ie': ['VoxMediaVolume'], 'add_ie': ['VoxMediaVolume'],
}] }]