etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-04 23:35:04 +00:00
Code Issues Projects Releases Wiki Activity

[crunchyroll] Extract uploader name that's not a link

Browse source 
Provide the Crunchyroll extractor with the ability to extract uploader
names that aren't links. Add a test for this new functionality.
This fixes #12267.
This commit is contained in:
xbe 2017-02-26 03:08:10 -08:00 committed by Sergey M
parent fd5c4aab59
commit 7fd4655256
1 changed files with 18 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
youtube_dl/extractor/crunchyroll.py
View file

@ -207,6 +207,21 @@ class CrunchyrollIE(CrunchyrollBaseIE):
# Just test metadata extraction # Just test metadata extraction
'skip_download': True, 'skip_download': True,
}, },
}, {
# make sure we can extract an uploader name that's not a link
'url': 'http://www.crunchyroll.com/hakuoki-reimeiroku/episode-1-dawn-of-the-divine-warriors-606899',
'info_dict': {
'id': '606899',
'ext': 'mp4',
'title': 'Hakuoki Reimeiroku Episode 1 – Dawn of the Divine Warriors',
'description': 'Ryunosuke was left to die, but Serizawa-san asked him a simple question "Do you want to live?"',
'uploader': 'Geneon Entertainment',
'upload_date': '20120717',
},
'params': {
# just test metadata extraction
'skip_download': True,
},
}] }]
_FORMAT_IDS = { _FORMAT_IDS = {
@ -388,8 +403,9 @@ def _real_extract(self, url):
if video_upload_date: if video_upload_date:
video_upload_date = unified_strdate(video_upload_date) video_upload_date = unified_strdate(video_upload_date)
video_uploader = self._html_search_regex( video_uploader = self._html_search_regex(
r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', webpage, # try looking for both an uploader that's a link and one that's not
'video_uploader', fatal=False) [r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', r'<div>\s*Publisher:\s*<span>\s*(.+?)\s*</span>\s*</div>'],
webpage, 'video_uploader', fatal=False)
available_fmts = [] available_fmts = []
for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage): for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage):