Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-02-03 07:02:56 +08:00
Code Issues Releases Wiki Activity

Remove fields not always present

Browse Source
This commit is contained in:
Jicksaw 2018-01-28 02:25:53 +02:00
parent 4d2cf22b80
commit a6ed22973e
1 changed files with 3 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
youtube_dl/extractor/bilibili.py
View File

@ -82,9 +82,8 @@ class BiliBiliIE(InfoExtractor):
'title': '【游戏混剪】各种妹子', 'title': '【游戏混剪】各种妹子',
'description': 'md5:4729a611536a756821ab59ca217f0328', 'description': 'md5:4729a611536a756821ab59ca217f0328',
'duration': 187.65, 'duration': 187.65,
'timestamp': 1511129709, 'timestamp': 1511129700,
'upload_date': '20171119', 'upload_date': '20171119',
'release_date': '20171119',
'thumbnail': r're:^https?://.+\.jpg', 'thumbnail': r're:^https?://.+\.jpg',
'uploader': '丁克Whovian', 'uploader': '丁克Whovian',
'uploader_id': '242283', 'uploader_id': '242283',
@ -205,7 +204,6 @@ class BiliBiliIE(InfoExtractor):
title = self._html_search_regex(['<h1[^>]*>([^<]+)</h1>', r'<h1 title=["\']([^>]+)["\']>'], webpage, 'title') title = self._html_search_regex(['<h1[^>]*>([^<]+)</h1>', r'<h1 title=["\']([^>]+)["\']>'], webpage, 'title')
thumbnail = self._html_search_meta(['og:image', 'thumbnailUrl'], webpage, default=None) thumbnail = self._html_search_meta(['og:image', 'thumbnailUrl'], webpage, default=None)
upload_date = self._html_search_meta('uploadDate', webpage, default=None) upload_date = self._html_search_meta('uploadDate', webpage, default=None)
release_date = self._html_search_meta('datePublished', webpage, default=None)
uploader = self._html_search_meta('author', webpage) or\ uploader = self._html_search_meta('author', webpage) or\
self._search_regex(r'["\'](?:(?:upData)|(?:owner))["\']:.*["\']name["\']:["\']([^"\']+)["\']', self._search_regex(r'["\'](?:(?:upData)|(?:owner))["\']:.*["\']name["\']:["\']([^"\']+)["\']',
webpage, 'uploader', default=None) webpage, 'uploader', default=None)
@ -214,8 +212,7 @@ class BiliBiliIE(InfoExtractor):
r'["\'](?:(?:upData)|(?:owner))["\']:{["\']mid["\']:["\']?(\d+)(?:["\']|,)', r'["\'](?:(?:upData)|(?:owner))["\']:{["\']mid["\']:["\']?(\d+)(?:["\']|,)',
webpage, 'uploader_id', default=None) webpage, 'uploader_id', default=None)
timestamp = self._html_search_regex(r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', default=None) or\ timestamp = self._html_search_regex(r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', default=None)
release_date or upload_date
# For older webpage type # For older webpage type
uploader_mobj = re.search( uploader_mobj = re.search(
@ -236,7 +233,6 @@ class BiliBiliIE(InfoExtractor):
'uploader': uploader, 'uploader': uploader,
'uploader_id': uploader_id, 'uploader_id': uploader_id,
'upload_date': unified_strdate(upload_date), 'upload_date': unified_strdate(upload_date),
'release_date': unified_strdate(release_date),
} }
for entry in entries: for entry in entries: