import re
from .common import InfoExtractor
-from ..compat import compat_str
from ..utils import (
+ US_RATINGS,
ExtractorError,
determine_ext,
- int_or_none,
float_or_none,
+ int_or_none,
js_to_json,
orderedSet,
strip_jsonp,
strip_or_none,
+ traverse_obj,
unified_strdate,
url_or_none,
- US_RATINGS,
)
)
IE_NAME = 'pbs'
- IE_DESC = 'Public Broadcasting Service (PBS) and member stations: %s' % ', '.join(list(zip(*_STATIONS))[1])
+ IE_DESC = 'Public Broadcasting Service (PBS) and member stations: {}'.format(', '.join(list(zip(*_STATIONS))[1]))
_VALID_URL = r'''(?x)https?://
(?:
# Direct video URL
- (?:%s)/(?:(?:vir|port)alplayer|video)/(?P<id>[0-9]+)(?:[?/]|$) |
+ (?:{})/(?:(?:vir|port)alplayer|video)/(?P<id>[0-9]+)(?:[?/]|$) |
# Article with embedded player (or direct video)
- (?:www\.)?pbs\.org/(?:[^/]+/){
1,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
+ (?:www\.)?pbs\.org/(?:[^/]+/){
{1,5}}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
# Player
(?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)
)
- ''' % '|'.join(list(zip(*_STATIONS))[0])
+ '''.format('|'.join(next(zip(*_STATIONS))))
_GEO_COUNTRIES = ['US']
{
'url': 'https://player.pbs.org/portalplayer/3004638221/?uid=',
'only_matching': True,
- }
+ },
]
_ERRORS = {
101: 'We\'re sorry, but this video is not yet available.',
if not video_id:
video_info = self._extract_video_data(
player_page, 'video data', display_id)
- video_id = compat_str(
+ video_id = str(
video_info.get('id') or video_info['contentID'])
else:
video_id = mobj.group('id')
if isinstance(video_id, list):
entries = [self.url_result(
- 'http://video.pbs.org/video/%s' % vid_id, 'PBS', vid_id)
+ f'http://video.pbs.org/video/{vid_id}', 'PBS', vid_id)
for vid_id in video_id]
return self.playlist_result(entries, display_id)
# Player pages may also serve different qualities
for page in ('widget/partnerplayer', 'portalplayer'):
player = self._download_webpage(
- 'http://player.pbs.org/%s/%s' % (page, video_id),
- display_id, 'Downloading %s page' % page, fatal=False)
+ f'http://player.pbs.org/{page}/{video_id}',
+ display_id, f'Downloading {page} page', fatal=False)
if player:
video_info = self._extract_video_data(
- player, '%s video data' % page, display_id, fatal=False)
+ player, f'{page} video data', display_id, fatal=False)
if video_info:
extract_redirect_urls(video_info)
if not info:
redirect_id = redirect.get('eeid')
redirect_info = self._download_json(
- '%s?format=json' % redirect['url'], display_id,
+ '{}?format=json'.format(redirect['url']), display_id,
'Downloading %s video url info' % (redirect_id or num),
headers=self.geo_verification_headers())
self.raise_geo_restricted(
msg=message, countries=self._GEO_COUNTRIES)
raise ExtractorError(
- '%s said: %s' % (self.IE_NAME, message), expected=True)
+ f'{self.IE_NAME} said: {message}', expected=True)
format_url = redirect_info.get('url')
if not format_url:
f_url = re.sub(r'\d+k|baseline', bitrate + 'k', http_url)
# This may produce invalid links sometimes (e.g.
# http://www.pbs.org/wgbh/frontline/film/suicide-plan)
- if not self._is_valid_url(f_url, display_id, 'http-%sk video' % bitrate):
+ if not self._is_valid_url(f_url, display_id, f'http-{bitrate}k video'):
continue
f = m3u8_format.copy()
f.update({
captions = info.get('cc') or {}
for caption_url in captions.values():
subtitles.setdefault('en', []).append({
- 'url': caption_url
+ 'url': caption_url,
})
subtitles = self._merge_subtitles(subtitles, hls_subs)
'subtitles': subtitles,
'chapters': chapters,
}
+
+
+class PBSKidsIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?pbskids\.org/video/[\w-]+/(?P<id>\d+)'
+ _TESTS = [
+ {
+ 'url': 'https://pbskids.org/video/molly-of-denali/3030407927',
+ 'md5': '1ded20a017cc6b53446238f1804ce4c7',
+ 'info_dict': {
+ 'id': '3030407927',
+ 'title': 'Bird in the Hand/Bye-Bye Birdie',
+ 'channel': 'molly-of-denali',
+ 'duration': 1540,
+ 'ext': 'mp4',
+ 'series': 'Molly of Denali',
+ 'description': 'md5:d006b2211633685d8ebc8d03b6d5611e',
+ 'categories': ['Episode'],
+ 'upload_date': '20190718',
+ },
+ },
+ {
+ 'url': 'https://pbskids.org/video/plum-landing/2365205059',
+ 'md5': '92e5d189851a64ae1d0237a965be71f5',
+ 'info_dict': {
+ 'id': '2365205059',
+ 'title': 'Cooper\'s Favorite Place in Nature',
+ 'channel': 'plum-landing',
+ 'duration': 67,
+ 'ext': 'mp4',
+ 'series': 'Plum Landing',
+ 'description': 'md5:657e5fc4356a84ead1c061eb280ff05d',
+ 'categories': ['Episode'],
+ 'upload_date': '20140302',
+ },
+ },
+ ]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+ meta = self._search_json(r'window\._PBS_KIDS_DEEPLINK\s*=', webpage, 'video info', video_id)
+ formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+ traverse_obj(meta, ('video_obj', 'URI', {url_or_none})), video_id, ext='mp4')
+
+ return {
+ 'id': video_id,
+ 'formats': formats,
+ 'subtitles': subtitles,
+ **traverse_obj(meta, {
+ 'categories': ('video_obj', 'video_type', {str}, {lambda x: [x] if x else None}),
+ 'channel': ('show_slug', {str}),
+ 'description': ('video_obj', 'description', {str}),
+ 'duration': ('video_obj', 'duration', {int_or_none}),
+ 'series': ('video_obj', 'program_title', {str}),
+ 'title': ('video_obj', 'title', {str}),
+ 'upload_date': ('video_obj', 'air_date', {unified_strdate}),
+ }),
+ }
projects / yt-dlp.git / blobdiff