mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-05-19 11:39:28 +00:00
Merge 8c6aa13dbd
into e0727e4ab6
This commit is contained in:
commit
0d570298fd
|
@ -21,68 +21,6 @@ class NhkBaseIE(InfoExtractor):
|
||||||
m_id, lang, '/all' if is_video else ''),
|
m_id, lang, '/all' if is_video else ''),
|
||||||
m_id, query={'apikey': 'EJfK8jdS57GqlupFgAfAAwr573q01y6k'})['data']['episodes'] or []
|
m_id, query={'apikey': 'EJfK8jdS57GqlupFgAfAAwr573q01y6k'})['data']['episodes'] or []
|
||||||
|
|
||||||
def _extract_episode_info(self, url, episode=None):
|
|
||||||
fetch_episode = episode is None
|
|
||||||
lang, m_type, episode_id = re.match(NhkVodIE._VALID_URL, url).groups()
|
|
||||||
if len(episode_id) == 7:
|
|
||||||
episode_id = episode_id[:4] + '-' + episode_id[4:]
|
|
||||||
|
|
||||||
is_video = m_type == 'video'
|
|
||||||
if fetch_episode:
|
|
||||||
episode = self._call_api(
|
|
||||||
episode_id, lang, is_video, True, episode_id[:4] == '9999')[0]
|
|
||||||
title = episode.get('sub_title_clean') or episode['sub_title']
|
|
||||||
|
|
||||||
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': get_clean_field('description'),
|
|
||||||
'thumbnails': thumbnails,
|
|
||||||
'series': series,
|
|
||||||
'episode': title,
|
|
||||||
}
|
|
||||||
if is_video:
|
|
||||||
vod_id = episode['vod_id']
|
|
||||||
info.update({
|
|
||||||
'_type': 'url_transparent',
|
|
||||||
'ie_key': 'Piksel',
|
|
||||||
'url': 'https://player.piksel.com/v/refid/nhkworld/prefid/' + vod_id,
|
|
||||||
'id': vod_id,
|
|
||||||
})
|
|
||||||
else:
|
|
||||||
if fetch_episode:
|
|
||||||
audio_path = episode['audio']['audio']
|
|
||||||
info['formats'] = self._extract_m3u8_formats(
|
|
||||||
'https://nhkworld-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
|
|
||||||
episode_id, 'm4a', entry_protocol='m3u8_native',
|
|
||||||
m3u8_id='hls', fatal=False)
|
|
||||||
for f in info['formats']:
|
|
||||||
f['language'] = lang
|
|
||||||
else:
|
|
||||||
info.update({
|
|
||||||
'_type': 'url_transparent',
|
|
||||||
'ie_key': NhkVodIE.ie_key(),
|
|
||||||
'url': url,
|
|
||||||
})
|
|
||||||
return info
|
|
||||||
|
|
||||||
|
|
||||||
class NhkVodIE(NhkBaseIE):
|
class NhkVodIE(NhkBaseIE):
|
||||||
# the 7-character IDs can have alphabetic chars too: assume [a-z] rather than just [a-f], eg
|
# the 7-character IDs can have alphabetic chars too: assume [a-z] rather than just [a-f], eg
|
||||||
|
@ -90,8 +28,21 @@ class NhkVodIE(NhkBaseIE):
|
||||||
# Content available only for a limited period of time. Visit
|
# Content available only for a limited period of time. Visit
|
||||||
# https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
|
# https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
|
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2061601/',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'yd8322ch',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'description': 'NHK WORLD-JAPAN presents a sumo highlights program for fans around the globe. Today the'
|
||||||
|
' show features all top-division bouts from May 14, Day 1 of the Grand Sumo Tournament in'
|
||||||
|
' Tokyo.',
|
||||||
|
'title': 'GRAND SUMO Highlights - [Recap] May Tournament Day 1 (Opening Day)',
|
||||||
|
'upload_date': '20230514',
|
||||||
|
'timestamp': 1684083791,
|
||||||
|
},
|
||||||
|
}, {
|
||||||
# video clip
|
# video clip
|
||||||
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999011/',
|
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999011/',
|
||||||
|
'only_matching': True,
|
||||||
'md5': '7a90abcfe610ec22a6bfe15bd46b30ca',
|
'md5': '7a90abcfe610ec22a6bfe15bd46b30ca',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'a95j5iza',
|
'id': 'a95j5iza',
|
||||||
|
@ -141,14 +92,84 @@ class NhkVodIE(NhkBaseIE):
|
||||||
}
|
}
|
||||||
}]
|
}]
|
||||||
|
|
||||||
|
def _extract_episode_info(self, url, episode=None):
|
||||||
|
fetch_episode = episode is None
|
||||||
|
lang, m_type, episode_id = re.match(NhkVodIE._VALID_URL, url).groups()
|
||||||
|
if len(episode_id) == 7:
|
||||||
|
episode_id = episode_id[:4] + '-' + episode_id[4:]
|
||||||
|
|
||||||
|
is_video = m_type == 'video'
|
||||||
|
if fetch_episode:
|
||||||
|
episode = self._call_api(
|
||||||
|
episode_id, lang, is_video, True, episode_id[:4] == '9999')[0]
|
||||||
|
title = episode.get('sub_title_clean') or episode['sub_title']
|
||||||
|
|
||||||
|
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': get_clean_field('description'),
|
||||||
|
'thumbnails': thumbnails,
|
||||||
|
'series': series,
|
||||||
|
'episode': title,
|
||||||
|
}
|
||||||
|
if is_video:
|
||||||
|
vod_id = episode['vod_id']
|
||||||
|
info.update({
|
||||||
|
'_type': 'url_transparent',
|
||||||
|
'ie_key': 'Piksel',
|
||||||
|
'url': 'https://movie-s.nhk.or.jp/v/refid/nhkworld/prefid/' + vod_id,
|
||||||
|
'id': vod_id,
|
||||||
|
})
|
||||||
|
else:
|
||||||
|
if fetch_episode:
|
||||||
|
audio_path = episode['audio']['audio']
|
||||||
|
info['formats'] = self._extract_m3u8_formats(
|
||||||
|
'https://nhkworld-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
|
||||||
|
episode_id, 'm4a', entry_protocol='m3u8_native',
|
||||||
|
m3u8_id='hls', fatal=False)
|
||||||
|
for f in info['formats']:
|
||||||
|
f['language'] = lang
|
||||||
|
else:
|
||||||
|
info.update({
|
||||||
|
'_type': 'url_transparent',
|
||||||
|
'ie_key': NhkVodIE.ie_key(),
|
||||||
|
'url': url,
|
||||||
|
})
|
||||||
|
return info
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
return self._extract_episode_info(url)
|
return self._extract_episode_info(url)
|
||||||
|
|
||||||
|
|
||||||
class NhkVodProgramIE(NhkBaseIE):
|
class NhkVodProgramIE(NhkVodIE):
|
||||||
_VALID_URL = r'%s/program%s(?P<id>[0-9a-z]+)(?:.+?\btype=(?P<episode_type>clip|(?:radio|tv)Episode))?' % (NhkBaseIE._BASE_URL_REGEX, NhkBaseIE._TYPE_REGEX)
|
_VALID_URL = r'%s/program%s(?P<id>[0-9a-z]+)(?:.+?\btype=(?P<episode_type>clip|(?:radio|tv)Episode))?' % (
|
||||||
|
NhkBaseIE._BASE_URL_REGEX, NhkBaseIE._TYPE_REGEX)
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
# video program episodes
|
# video program episodes
|
||||||
|
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/program/video/sumo',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'sumo',
|
||||||
|
'title': 'GRAND SUMO Highlights',
|
||||||
|
},
|
||||||
|
'playlist_mincount': 1,
|
||||||
|
}, {
|
||||||
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/program/video/japanrailway',
|
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/program/video/japanrailway',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'japanrailway',
|
'id': 'japanrailway',
|
||||||
|
|
|
@ -10,8 +10,10 @@ from ..utils import (
|
||||||
ExtractorError,
|
ExtractorError,
|
||||||
int_or_none,
|
int_or_none,
|
||||||
parse_iso8601,
|
parse_iso8601,
|
||||||
|
traverse_obj,
|
||||||
try_get,
|
try_get,
|
||||||
unescapeHTML,
|
unescapeHTML,
|
||||||
|
urljoin,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
|
@ -73,10 +75,10 @@ class PikselIE(InfoExtractor):
|
||||||
if mobj:
|
if mobj:
|
||||||
return mobj.group('url')
|
return mobj.group('url')
|
||||||
|
|
||||||
def _call_api(self, app_token, resource, display_id, query, fatal=True):
|
def _call_api(self, app_token, resource, display_id, query, host='https://player.piksel.com', fatal=True):
|
||||||
response = (self._download_json(
|
url = urljoin(host, '/ws/ws_%s/api/%s/mode/json/apiv/5' % (resource, app_token))
|
||||||
'http://player.piksel.com/ws/ws_%s/api/%s/mode/json/apiv/5' % (resource, app_token),
|
response = self._download_json(url, display_id, query=query, fatal=fatal)
|
||||||
display_id, query=query, fatal=fatal) or {}).get('response')
|
response = traverse_obj(response, 'response', expected_type=dict) or {}
|
||||||
failure = try_get(response, lambda x: x['failure']['reason'])
|
failure = try_get(response, lambda x: x['failure']['reason'])
|
||||||
if failure:
|
if failure:
|
||||||
if fatal:
|
if fatal:
|
||||||
|
@ -93,7 +95,7 @@ class PikselIE(InfoExtractor):
|
||||||
], webpage, 'app token')
|
], webpage, 'app token')
|
||||||
query = {'refid': ref_id, 'prefid': display_id} if ref_id else {'v': display_id}
|
query = {'refid': ref_id, 'prefid': display_id} if ref_id else {'v': display_id}
|
||||||
program = self._call_api(
|
program = self._call_api(
|
||||||
app_token, 'program', display_id, query)['WsProgramResponse']['program']
|
app_token, 'program', display_id, query, url)['WsProgramResponse']['program']
|
||||||
video_id = program['uuid']
|
video_id = program['uuid']
|
||||||
video_data = program['asset']
|
video_data = program['asset']
|
||||||
title = video_data['title']
|
title = video_data['title']
|
||||||
|
@ -143,7 +145,7 @@ class PikselIE(InfoExtractor):
|
||||||
process_asset_files(try_get(self._call_api(
|
process_asset_files(try_get(self._call_api(
|
||||||
app_token, 'asset_file', display_id, {
|
app_token, 'asset_file', display_id, {
|
||||||
'assetid': asset_id,
|
'assetid': asset_id,
|
||||||
}, False), lambda x: x['WsAssetFileResponse']['AssetFiles']))
|
}, url, False), lambda x: x['WsAssetFileResponse']['AssetFiles']))
|
||||||
|
|
||||||
m3u8_url = dict_get(video_data, [
|
m3u8_url = dict_get(video_data, [
|
||||||
'm3u8iPadURL',
|
'm3u8iPadURL',
|
||||||
|
|
Loading…
Reference in a new issue