1
0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-10 16:39:59 +08:00

Merge pull request #286 from ytdl-org/master

[pull] master from ytdl-org:master
This commit is contained in:
pull[bot] 2020-03-13 23:04:58 +00:00 committed by GitHub
commit eb336fac03
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 16 additions and 14 deletions

View File

@ -7,6 +7,7 @@ from .common import InfoExtractor
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
int_or_none, int_or_none,
merge_dicts,
parse_iso8601, parse_iso8601,
qualities, qualities,
try_get, try_get,
@ -87,21 +88,25 @@ class NDRIE(NDRBaseIE):
def _extract_embed(self, webpage, display_id): def _extract_embed(self, webpage, display_id):
embed_url = self._html_search_meta( embed_url = self._html_search_meta(
'embedURL', webpage, 'embed URL', fatal=True) 'embedURL', webpage, 'embed URL',
default=None) or self._search_regex(
r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'embed URL', group='url')
description = self._search_regex( description = self._search_regex(
r'<p[^>]+itemprop="description">([^<]+)</p>', r'<p[^>]+itemprop="description">([^<]+)</p>',
webpage, 'description', default=None) or self._og_search_description(webpage) webpage, 'description', default=None) or self._og_search_description(webpage)
timestamp = parse_iso8601( timestamp = parse_iso8601(
self._search_regex( self._search_regex(
r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"', r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"',
webpage, 'upload date', fatal=False)) webpage, 'upload date', default=None))
return { info = self._search_json_ld(webpage, display_id, default={})
return merge_dicts({
'_type': 'url_transparent', '_type': 'url_transparent',
'url': embed_url, 'url': embed_url,
'display_id': display_id, 'display_id': display_id,
'description': description, 'description': description,
'timestamp': timestamp, 'timestamp': timestamp,
} }, info)
class NJoyIE(NDRBaseIE): class NJoyIE(NDRBaseIE):

View File

@ -6,7 +6,7 @@ from .common import InfoExtractor
class NhkVodIE(InfoExtractor): class NhkVodIE(InfoExtractor):
_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+)' _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[^/]+?-\d{8}-\d+)'
# 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 = [{
@ -30,6 +30,9 @@ class NhkVodIE(InfoExtractor):
}, { }, {
'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/', 'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/j_art-20150903-1/',
'only_matching': True,
}] }]
_API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7a/episode/%s/%s/all%s.json' _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7a/episode/%s/%s/all%s.json'
@ -82,15 +85,9 @@ class NhkVodIE(InfoExtractor):
audio = episode['audio'] audio = episode['audio']
audio_path = audio['audio'] audio_path = audio['audio']
info['formats'] = self._extract_m3u8_formats( info['formats'] = self._extract_m3u8_formats(
'https://nhks-vh.akamaihd.net/i%s/master.m3u8' % audio_path, 'https://nhkworld-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
episode_id, 'm4a', m3u8_id='hls', fatal=False) episode_id, 'm4a', entry_protocol='m3u8_native',
for proto in ('rtmpt', 'rtmp'): m3u8_id='hls', fatal=False)
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']: for f in info['formats']:
f['language'] = lang f['language'] = lang
return info return info