Merge branch 'master' of github.com:rg3/youtube-dl
* 'master' of github.com:rg3/youtube-dl: [soundcloud] Add support for new rendition and improve extraction (closes #20699) [ooyala] add support for geo verification proxy [nrl] Add new extractor(closes #15991) [vimeo] extract live archive source format(#19144) [vimeo] add support live streams and improve info extraction(closes #19144) [ntvcojp] Add new extractor [nhk] extract rtmpt format [nhk] add support for audio URLs [udemy] add another course id extraction pattern(closes #20491)
This commit is contained in:
Paolo de Dios
commit
f347809560
@ -2019,6 +2019,8 @@ class InfoExtractor(object):
|
||||
if res is False:
|
||||
return []
|
||||
mpd_doc, urlh = res
|
||||
if mpd_doc is None:
|
||||
return []
|
||||
mpd_base_url = base_url(urlh.geturl())
|
||||
|
||||
return self._parse_mpd_formats(
|
||||
|
||||
@ -808,6 +808,8 @@ from .nrk import (
|
||||
NRKTVSeasonIE,
|
||||
NRKTVSeriesIE,
|
||||
)
|
||||
from .nrl import NRLTVIE
|
||||
from .ntvcojp import NTVCoJpCUIE
|
||||
from .ntvde import NTVDeIE
|
||||
from .ntvru import NTVRuIE
|
||||
from .nytimes import (
|
||||
|
||||
@ -1,54 +1,81 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import ExtractorError
|
||||
|
||||
|
||||
class NhkVodIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/(?:vod|ondemand)/(?P<id>[^/]+/[^/?#&]+)'
|
||||
_VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[a-z]+-\d{8}-\d+)'
|
||||
# Content available only for a limited period of time. Visit
|
||||
# https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
|
||||
_TESTS = [{
|
||||
# Videos available only for a limited period of time. Visit
|
||||
# http://www3.nhk.or.jp/nhkworld/en/vod/ for working samples.
|
||||
'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815',
|
||||
'info_dict': {
|
||||
'id': 'A1bnNiNTE6nY3jLllS-BIISfcC_PpvF5',
|
||||
'ext': 'flv',
|
||||
'title': 'TOKYO FASHION EXPRESS - The Kimono as Global Fashion',
|
||||
'description': 'md5:db338ee6ce8204f415b754782f819824',
|
||||
'series': 'TOKYO FASHION EXPRESS',
|
||||
'episode': 'The Kimono as Global Fashion',
|
||||
},
|
||||
'skip': 'Videos available only for a limited period of time',
|
||||
}, {
|
||||
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/plugin-20190404-1/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_API_URL = 'http://api.nhk.or.jp/nhkworld/vodesdlist/v1/all/all/all.json?apikey=EJfK8jdS57GqlupFgAfAAwr573q01y6k'
|
||||
_API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sodesdlist/v7/episode/%s/%s/all%s.json'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
data = self._download_json(self._API_URL, video_id)
|
||||
|
||||
try:
|
||||
episode = next(
|
||||
e for e in data['data']['episodes']
|
||||
if e.get('url') and video_id in e['url'])
|
||||
except StopIteration:
|
||||
raise ExtractorError('Unable to find episode')
|
||||
|
||||
embed_code = episode['vod_id']
|
||||
lang, m_type, episode_id = re.match(self._VALID_URL, url).groups()
|
||||
if episode_id.isdigit():
|
||||
episode_id = episode_id[:4] + '-' + episode_id[4:]
|
||||
|
||||
is_video = m_type == 'video'
|
||||
episode = self._download_json(
|
||||
self._API_URL_TEMPLATE % ('v' if is_video else 'r', episode_id, lang, '/all' if is_video else ''),
|
||||
episode_id, query={'apikey': 'EJfK8jdS57GqlupFgAfAAwr573q01y6k'})['data']['episodes'][0]
|
||||
title = episode.get('sub_title_clean') or episode['sub_title']
|
||||
description = episode.get('description_clean') or episode.get('description')
|
||||
series = episode.get('title_clean') or episode.get('title')
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': 'Ooyala',
|
||||
'url': 'ooyala:%s' % embed_code,
|
||||
def get_clean_field(key):
|
||||
return episode.get(key + '_clean') or episode.get(key)
|
||||
|
||||
series = get_clean_field('title')
|
||||
|
||||
thumbnails = []
|
||||
for s, w, h in [('', 640, 360), ('_l', 1280, 720)]:
|
||||
img_path = episode.get('image' + s)
|
||||
if not img_path:
|
||||
continue
|
||||
thumbnails.append({
|
||||
'id': '%dp' % h,
|
||||
'height': h,
|
||||
'width': w,
|
||||
'url': 'https://www3.nhk.or.jp' + img_path,
|
||||
})
|
||||
|
||||
info = {
|
||||
'id': episode_id + '-' + lang,
|
||||
'title': '%s - %s' % (series, title) if series and title else title,
|
||||
'description': description,
|
||||
'description': get_clean_field('description'),
|
||||
'thumbnails': thumbnails,
|
||||
'series': series,
|
||||
'episode': title,
|
||||
}
|
||||
if is_video:
|
||||
info.update({
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': 'Ooyala',
|
||||
'url': 'ooyala:' + episode['vod_id'],
|
||||
})
|
||||
else:
|
||||
audio = episode['audio']
|
||||
audio_path = audio['audio']
|
||||
info['formats'] = self._extract_m3u8_formats(
|
||||
'https://nhks-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
|
||||
episode_id, 'm4a', m3u8_id='hls', fatal=False)
|
||||
for proto in ('rtmpt', 'rtmp'):
|
||||
info['formats'].append({
|
||||
'ext': 'flv',
|
||||
'format_id': proto,
|
||||
'url': '%s://flv.nhk.or.jp/ondemand/mp4:flv%s' % (proto, audio_path),
|
||||
'vcodec': 'none',
|
||||
})
|
||||
for f in info['formats']:
|
||||
f['language'] = lang
|
||||
return info
|
||||
|
||||
30
youtube_dl/extractor/nrl.py
Normal file
30
youtube_dl/extractor/nrl.py
Normal file
@ -0,0 +1,30 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class NRLTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?nrl\.com/tv(/[^/]+)*/(?P<id>[^/?&#]+)'
|
||||
_TEST = {
|
||||
'url': 'https://www.nrl.com/tv/news/match-highlights-titans-v-knights-862805/',
|
||||
'info_dict': {
|
||||
'id': 'YyNnFuaDE6kPJqlDhG4CGQ_w89mKTau4',
|
||||
'ext': 'mp4',
|
||||
'title': 'Match Highlights: Titans v Knights',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
'format': 'bestvideo',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
q_data = self._parse_json(self._search_regex(
|
||||
r"(?s)q-data='({.+?})'", webpage, 'player data'), display_id)
|
||||
ooyala_id = q_data['videoId']
|
||||
return self.url_result(
|
||||
'ooyala:' + ooyala_id, 'Ooyala', ooyala_id, q_data.get('title'))
|
||||
49
youtube_dl/extractor/ntvcojp.py
Normal file
49
youtube_dl/extractor/ntvcojp.py
Normal file
@ -0,0 +1,49 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
js_to_json,
|
||||
smuggle_url,
|
||||
)
|
||||
|
||||
|
||||
class NTVCoJpCUIE(InfoExtractor):
|
||||
IE_NAME = 'cu.ntv.co.jp'
|
||||
IE_DESC = 'Nippon Television Network'
|
||||
_VALID_URL = r'https?://cu\.ntv\.co\.jp/(?!program)(?P<id>[^/?&#]+)'
|
||||
_TEST = {
|
||||
'url': 'https://cu.ntv.co.jp/televiva-chill-gohan_181031/',
|
||||
'info_dict': {
|
||||
'id': '5978891207001',
|
||||
'ext': 'mp4',
|
||||
'title': '桜エビと炒り卵がポイント！ 「中華風 エビチリおにぎり」──『美虎』五十嵐美幸',
|
||||
'upload_date': '20181213',
|
||||
'description': 'md5:211b52f4fd60f3e0e72b68b0c6ba52a9',
|
||||
'uploader_id': '3855502814001',
|
||||
'timestamp': 1544669941,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
player_config = self._parse_json(self._search_regex(
|
||||
r'(?s)PLAYER_CONFIG\s*=\s*({.+?})',
|
||||
webpage, 'player config'), display_id, js_to_json)
|
||||
video_id = player_config['videoId']
|
||||
account_id = player_config.get('account') or '3855502814001'
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': self._search_regex(r'<h1[^>]+class="title"[^>]*>([^<]+)', webpage, 'title').strip(),
|
||||
'description': self._html_search_meta(['description', 'og:description'], webpage),
|
||||
'url': smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % (account_id, video_id), {'geo_countries': ['JP']}),
|
||||
'ie_key': 'BrightcoveNew',
|
||||
}
|
||||
@ -36,7 +36,7 @@ class OoyalaBaseIE(InfoExtractor):
|
||||
'domain': domain,
|
||||
'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds,dash,smooth',
|
||||
'embedToken': embed_token,
|
||||
}), video_id)
|
||||
}), video_id, headers=self.geo_verification_headers())
|
||||
|
||||
cur_auth_data = auth_data['authorization_data'][embed_code]
|
||||
|
||||
|
||||
@ -15,7 +15,12 @@ from ..compat import (
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
KNOWN_EXTENSIONS,
|
||||
merge_dicts,
|
||||
mimetype2ext,
|
||||
str_or_none,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
update_url_query,
|
||||
@ -57,7 +62,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
'uploader': 'E.T. ExTerrestrial Music',
|
||||
'timestamp': 1349920598,
|
||||
'upload_date': '20121011',
|
||||
'duration': 143,
|
||||
'duration': 143.216,
|
||||
'license': 'all-rights-reserved',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
@ -100,7 +105,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
'uploader': 'jaimeMF',
|
||||
'timestamp': 1386604920,
|
||||
'upload_date': '20131209',
|
||||
'duration': 9,
|
||||
'duration': 9.927,
|
||||
'license': 'all-rights-reserved',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
@ -120,7 +125,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
'uploader': 'jaimeMF',
|
||||
'timestamp': 1386604920,
|
||||
'upload_date': '20131209',
|
||||
'duration': 9,
|
||||
'duration': 9.927,
|
||||
'license': 'all-rights-reserved',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
@ -140,7 +145,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
'uploader': 'oddsamples',
|
||||
'timestamp': 1389232924,
|
||||
'upload_date': '20140109',
|
||||
'duration': 17,
|
||||
'duration': 17.346,
|
||||
'license': 'cc-by-sa',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
@ -160,7 +165,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
'uploader': 'Ori Uplift Music',
|
||||
'timestamp': 1504206263,
|
||||
'upload_date': '20170831',
|
||||
'duration': 7449,
|
||||
'duration': 7449.096,
|
||||
'license': 'all-rights-reserved',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
@ -180,7 +185,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
'uploader': 'garyvee',
|
||||
'timestamp': 1488152409,
|
||||
'upload_date': '20170226',
|
||||
'duration': 207,
|
||||
'duration': 207.012,
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'license': 'all-rights-reserved',
|
||||
'view_count': int,
|
||||
@ -192,9 +197,31 @@ class SoundcloudIE(InfoExtractor):
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
# not avaialble via api.soundcloud.com/i1/tracks/id/streams
|
||||
{
|
||||
'url': 'https://soundcloud.com/giovannisarani/mezzo-valzer',
|
||||
'md5': 'e22aecd2bc88e0e4e432d7dcc0a1abf7',
|
||||
'info_dict': {
|
||||
'id': '583011102',
|
||||
'ext': 'mp3',
|
||||
'title': 'Mezzo Valzer',
|
||||
'description': 'md5:4138d582f81866a530317bae316e8b61',
|
||||
'uploader': 'Giovanni Sarani',
|
||||
'timestamp': 1551394171,
|
||||
'upload_date': '20190228',
|
||||
'duration': 180.157,
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'license': 'all-rights-reserved',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
},
|
||||
'expected_warnings': ['Unable to download JSON metadata'],
|
||||
}
|
||||
]
|
||||
|
||||
_CLIENT_ID = 'NmW1FlPaiL94ueEu7oziOWjYEzZzQDcK'
|
||||
_CLIENT_ID = 'FweeGBOOEOYJWLJN3oEyToGLKhmSz0I7'
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
@ -202,10 +229,6 @@ class SoundcloudIE(InfoExtractor):
|
||||
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1',
|
||||
webpage)]
|
||||
|
||||
def report_resolve(self, video_id):
|
||||
"""Report information extraction."""
|
||||
self.to_screen('%s: Resolving id' % video_id)
|
||||
|
||||
@classmethod
|
||||
def _resolv_url(cls, url):
|
||||
return 'https://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID
|
||||
@ -224,6 +247,10 @@ class SoundcloudIE(InfoExtractor):
|
||||
def extract_count(key):
|
||||
return int_or_none(info.get('%s_count' % key))
|
||||
|
||||
like_count = extract_count('favoritings')
|
||||
if like_count is None:
|
||||
like_count = extract_count('likes')
|
||||
|
||||
result = {
|
||||
'id': track_id,
|
||||
'uploader': username,
|
||||
@ -231,15 +258,17 @@ class SoundcloudIE(InfoExtractor):
|
||||
'title': title,
|
||||
'description': info.get('description'),
|
||||
'thumbnail': thumbnail,
|
||||
'duration': int_or_none(info.get('duration'), 1000),
|
||||
'duration': float_or_none(info.get('duration'), 1000),
|
||||
'webpage_url': info.get('permalink_url'),
|
||||
'license': info.get('license'),
|
||||
'view_count': extract_count('playback'),
|
||||
'like_count': extract_count('favoritings'),
|
||||
'like_count': like_count,
|
||||
'comment_count': extract_count('comment'),
|
||||
'repost_count': extract_count('reposts'),
|
||||
'genre': info.get('genre'),
|
||||
}
|
||||
|
||||
format_urls = set()
|
||||
formats = []
|
||||
query = {'client_id': self._CLIENT_ID}
|
||||
if secret_token is not None:
|
||||
@ -248,6 +277,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
# We can build a direct link to the song
|
||||
format_url = update_url_query(
|
||||
'https://api.soundcloud.com/tracks/%s/download' % track_id, query)
|
||||
format_urls.add(format_url)
|
||||
formats.append({
|
||||
'format_id': 'download',
|
||||
'ext': info.get('original_format', 'mp3'),
|
||||
@ -256,12 +286,17 @@ class SoundcloudIE(InfoExtractor):
|
||||
'preference': 10,
|
||||
})
|
||||
|
||||
# We have to retrieve the url
|
||||
# Old API, does not work for some tracks (e.g.
|
||||
# https://soundcloud.com/giovannisarani/mezzo-valzer)
|
||||
format_dict = self._download_json(
|
||||
'https://api.soundcloud.com/i1/tracks/%s/streams' % track_id,
|
||||
track_id, 'Downloading track url', query=query)
|
||||
track_id, 'Downloading track url', query=query, fatal=False)
|
||||
|
||||
if format_dict:
|
||||
for key, stream_url in format_dict.items():
|
||||
if stream_url in format_urls:
|
||||
continue
|
||||
format_urls.add(stream_url)
|
||||
ext, abr = 'mp3', None
|
||||
mobj = re.search(r'_([^_]+)_(\d+)_url', key)
|
||||
if mobj:
|
||||
@ -295,6 +330,48 @@ class SoundcloudIE(InfoExtractor):
|
||||
|
||||
formats.extend(stream_formats)
|
||||
|
||||
# New API
|
||||
transcodings = try_get(
|
||||
info, lambda x: x['media']['transcodings'], list) or []
|
||||
for t in transcodings:
|
||||
if not isinstance(t, dict):
|
||||
continue
|
||||
format_url = url_or_none(t.get('url'))
|
||||
if not format_url:
|
||||
continue
|
||||
stream = self._download_json(
|
||||
update_url_query(format_url, query), track_id, fatal=False)
|
||||
if not isinstance(stream, dict):
|
||||
continue
|
||||
stream_url = url_or_none(stream.get('url'))
|
||||
if not stream_url:
|
||||
continue
|
||||
if stream_url in format_urls:
|
||||
continue
|
||||
format_urls.add(stream_url)
|
||||
protocol = try_get(t, lambda x: x['format']['protocol'], compat_str)
|
||||
if protocol != 'hls' and '/hls' in format_url:
|
||||
protocol = 'hls'
|
||||
ext = None
|
||||
preset = str_or_none(t.get('preset'))
|
||||
if preset:
|
||||
ext = preset.split('_')[0]
|
||||
if ext not in KNOWN_EXTENSIONS:
|
||||
mimetype = try_get(
|
||||
t, lambda x: x['format']['mime_type'], compat_str)
|
||||
ext = mimetype2ext(mimetype) or 'mp3'
|
||||
format_id_list = []
|
||||
if protocol:
|
||||
format_id_list.append(protocol)
|
||||
format_id_list.append(ext)
|
||||
format_id = '_'.join(format_id_list)
|
||||
formats.append({
|
||||
'url': stream_url,
|
||||
'format_id': format_id,
|
||||
'ext': ext,
|
||||
'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
|
||||
})
|
||||
|
||||
if not formats:
|
||||
# We fallback to the stream_url in the original info, this
|
||||
# cannot be always used, sometimes it can give an HTTP 404 error
|
||||
@ -303,11 +380,11 @@ class SoundcloudIE(InfoExtractor):
|
||||
'url': update_url_query(info['stream_url'], query),
|
||||
'ext': 'mp3',
|
||||
})
|
||||
self._check_formats(formats, track_id)
|
||||
|
||||
for f in formats:
|
||||
f['vcodec'] = 'none'
|
||||
|
||||
self._check_formats(formats, track_id)
|
||||
self._sort_formats(formats)
|
||||
result['formats'] = formats
|
||||
|
||||
@ -319,6 +396,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
raise ExtractorError('Invalid URL: %s' % url)
|
||||
|
||||
track_id = mobj.group('track_id')
|
||||
new_info = {}
|
||||
|
||||
if track_id is not None:
|
||||
info_json_url = 'https://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
|
||||
@ -344,13 +422,31 @@ class SoundcloudIE(InfoExtractor):
|
||||
if token:
|
||||
resolve_title += '/%s' % token
|
||||
|
||||
self.report_resolve(full_title)
|
||||
webpage = self._download_webpage(url, full_title, fatal=False)
|
||||
if webpage:
|
||||
entries = self._parse_json(
|
||||
self._search_regex(
|
||||
r'var\s+c\s*=\s*(\[.+?\])\s*,\s*o\s*=Date\b', webpage,
|
||||
'data', default='[]'), full_title, fatal=False)
|
||||
if entries:
|
||||
for e in entries:
|
||||
if not isinstance(e, dict):
|
||||
continue
|
||||
if e.get('id') != 67:
|
||||
continue
|
||||
data = try_get(e, lambda x: x['data'][0], dict)
|
||||
if data:
|
||||
new_info = data
|
||||
break
|
||||
info_json_url = self._resolv_url(
|
||||
'https://soundcloud.com/%s' % resolve_title)
|
||||
|
||||
url = 'https://soundcloud.com/%s' % resolve_title
|
||||
info_json_url = self._resolv_url(url)
|
||||
info = self._download_json(info_json_url, full_title, 'Downloading info JSON')
|
||||
# Contains some additional info missing from new_info
|
||||
info = self._download_json(
|
||||
info_json_url, full_title, 'Downloading info JSON')
|
||||
|
||||
return self._extract_info_dict(info, full_title, secret_token=token)
|
||||
return self._extract_info_dict(
|
||||
merge_dicts(info, new_info), full_title, secret_token=token)
|
||||
|
||||
|
||||
class SoundcloudPlaylistBaseIE(SoundcloudIE):
|
||||
@ -396,8 +492,6 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
|
||||
full_title += '/' + token
|
||||
url += '/' + token
|
||||
|
||||
self.report_resolve(full_title)
|
||||
|
||||
resolv_url = self._resolv_url(url)
|
||||
info = self._download_json(resolv_url, full_title)
|
||||
|
||||
|
||||
@ -76,7 +76,10 @@ class UdemyIE(InfoExtractor):
|
||||
webpage, 'course', default='{}')),
|
||||
video_id, fatal=False) or {}
|
||||
course_id = course.get('id') or self._search_regex(
|
||||
r'data-course-id=["\'](\d+)', webpage, 'course id')
|
||||
[
|
||||
r'data-course-id=["\'](\d+)',
|
||||
r'"courseId"\s*:\s*(\d+)'
|
||||
], webpage, 'course id')
|
||||
return course_id, course.get('title')
|
||||
|
||||
def _enroll_course(self, base_url, webpage, course_id):
|
||||
|
||||
@ -109,23 +109,9 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
||||
|
||||
def _parse_config(self, config, video_id):
|
||||
video_data = config['video']
|
||||
# Extract title
|
||||
video_title = video_data['title']
|
||||
|
||||
# Extract uploader, uploader_url and uploader_id
|
||||
video_uploader = video_data.get('owner', {}).get('name')
|
||||
video_uploader_url = video_data.get('owner', {}).get('url')
|
||||
video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
|
||||
|
||||
# Extract video thumbnail
|
||||
video_thumbnail = video_data.get('thumbnail')
|
||||
if video_thumbnail is None:
|
||||
video_thumbs = video_data.get('thumbs')
|
||||
if video_thumbs and isinstance(video_thumbs, dict):
|
||||
_, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
|
||||
|
||||
# Extract video duration
|
||||
video_duration = int_or_none(video_data.get('duration'))
|
||||
live_event = video_data.get('live_event') or {}
|
||||
is_live = live_event.get('status') == 'started'
|
||||
|
||||
formats = []
|
||||
config_files = video_data.get('files') or config['request'].get('files', {})
|
||||
@ -142,6 +128,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
||||
'tbr': int_or_none(f.get('bitrate')),
|
||||
})
|
||||
|
||||
# TODO: fix handling of 308 status code returned for live archive manifest requests
|
||||
for files_type in ('hls', 'dash'):
|
||||
for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items():
|
||||
manifest_url = cdn_data.get('url')
|
||||
@ -151,7 +138,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
||||
if files_type == 'hls':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
manifest_url, video_id, 'mp4',
|
||||
'm3u8_native', m3u8_id=format_id,
|
||||
'm3u8' if is_live else 'm3u8_native', m3u8_id=format_id,
|
||||
note='Downloading %s m3u8 information' % cdn_name,
|
||||
fatal=False))
|
||||
elif files_type == 'dash':
|
||||
@ -164,6 +151,10 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
||||
else:
|
||||
mpd_manifest_urls = [(format_id, manifest_url)]
|
||||
for f_id, m_url in mpd_manifest_urls:
|
||||
if 'json=1' in m_url:
|
||||
real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
|
||||
if real_m_url:
|
||||
m_url = real_m_url
|
||||
mpd_formats = self._extract_mpd_formats(
|
||||
m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
|
||||
'Downloading %s MPD information' % cdn_name,
|
||||
@ -175,6 +166,15 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
||||
f['preference'] = -40
|
||||
formats.extend(mpd_formats)
|
||||
|
||||
live_archive = live_event.get('archive') or {}
|
||||
live_archive_source_url = live_archive.get('source_url')
|
||||
if live_archive_source_url and live_archive.get('status') == 'done':
|
||||
formats.append({
|
||||
'format_id': 'live-archive-source',
|
||||
'url': live_archive_source_url,
|
||||
'preference': 1,
|
||||
})
|
||||
|
||||
subtitles = {}
|
||||
text_tracks = config['request'].get('text_tracks')
|
||||
if text_tracks:
|
||||
@ -184,15 +184,33 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
||||
'url': 'https://vimeo.com' + tt['url'],
|
||||
}]
|
||||
|
||||
thumbnails = []
|
||||
if not is_live:
|
||||
for key, thumb in video_data.get('thumbs', {}).items():
|
||||
thumbnails.append({
|
||||
'id': key,
|
||||
'width': int_or_none(key),
|
||||
'url': thumb,
|
||||
})
|
||||
thumbnail = video_data.get('thumbnail')
|
||||
if thumbnail:
|
||||
thumbnails.append({
|
||||
'url': thumbnail,
|
||||
})
|
||||
|
||||
owner = video_data.get('owner') or {}
|
||||
video_uploader_url = owner.get('url')
|
||||
|
||||
return {
|
||||
'title': video_title,
|
||||
'uploader': video_uploader,
|
||||
'uploader_id': video_uploader_id,
|
||||
'title': self._live_title(video_title) if is_live else video_title,
|
||||
'uploader': owner.get('name'),
|
||||
'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
|
||||
'uploader_url': video_uploader_url,
|
||||
'thumbnail': video_thumbnail,
|
||||
'duration': video_duration,
|
||||
'thumbnails': thumbnails,
|
||||
'duration': int_or_none(video_data.get('duration')),
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
'is_live': is_live,
|
||||
}
|
||||
|
||||
def _extract_original_format(self, url, video_id):
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user