administration/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-17 14:41:44 +00:00
Code Issues Projects Releases Wiki Activity

[extractor/pbs] Add extractor PBSKidsIE (#7602)

Browse Source 
Authored by: snixon
Fixes #2440
This commit is contained in:
Steve 2023-07-31 10:08:37 -07:00 committed by GitHub
parent 6014355c61
commit 6d6081dda1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 60 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
yt_dlp/extractor/_extractors.py
View File

@ -1420,7 +1420,7 @@ from .patreon import (
PatreonIE,
PatreonCampaignIE
)
from .pbs import PBSIE
from .pbs import PBSIE, PBSKidsIE
from .pearvideo import PearVideoIE
from .peekvids import PeekVidsIE, PlayVidsIE
from .peertube import (

59
yt_dlp/extractor/pbs.py
View File

@ -11,6 +11,7 @@ from ..utils import (
orderedSet,
strip_jsonp,
strip_or_none,
traverse_obj,
unified_strdate,
url_or_none,
US_RATINGS,
@ -696,3 +697,61 @@ class PBSIE(InfoExtractor):
'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}),
})
}