midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[nytimes] Add new cooking.nytimes.com extractor (#27143)

Browse source 
* [nytimes] support cooking.nytimes.com, resolves #27112

Co-authored-by: remitamine <remitamine@gmail.com>
This commit is contained in:
Jia Rong Yee 2020-11-22 21:12:47 +08:00 committed by GitHub
parent cb6e24f946
commit 15f2734791
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 39 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
youtube_dl/extractor/extractors.py
View file

@ -782,6 +782,7 @@ from .ntvru import NTVRuIE
from .nytimes import (
NYTimesIE,
NYTimesArticleIE,
NYTimesCookingIE,
)
from .nuvid import NuvidIE
from .nzz import NZZIE

38
youtube_dl/extractor/nytimes.py
View file

@ -221,3 +221,41 @@ class NYTimesArticleIE(NYTimesBaseIE):
r'NYTD\.FlexTypes\.push\s*\(\s*({.+})\s*\)\s*;'),
webpage, 'podcast data')
return self._extract_podcast_from_json(podcast_data, page_id, webpage)
class NYTimesCookingIE(NYTimesBaseIE):
_VALID_URL = r'https?://cooking\.nytimes\.com/(?:guid|recip)es/(?P<id>\d+)'
_TESTS = [{
'url': 'https://cooking.nytimes.com/recipes/1017817-cranberry-curd-tart',
'md5': 'dab81fa2eaeb3f9ed47498bdcfcdc1d3',
'info_dict': {
'id': '100000004756089',
'ext': 'mov',
'timestamp': 1479383008,
'uploader': 'By SHAW LASH, ADAM SAEWITZ and JAMES HERRON',
'title': 'Cranberry Tart',
'upload_date': '20161117',
'description': 'If you are a fan of lemon curd or the classic French tarte au citron, you will love this cranberry version.',
},
}, {
'url': 'https://cooking.nytimes.com/guides/13-how-to-cook-a-turkey',
'md5': '4b2e8c70530a89b8d905a2b572316eb8',
'info_dict': {
'id': '100000003951728',
'ext': 'mov',
'timestamp': 1445509539,
'description': 'Turkey guide',
'upload_date': '20151022',
'title': 'Turkey',
}
}]
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
video_id = self._search_regex(
r'data-video-id=["\'](\d+)', webpage, 'video id')
return self._extract_video_from_id(video_id)