github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

make all IEs return 'upload_date' and 'uploader', even if only u'NA'

Browse source
This commit is contained in:
Filippo Valsorda 2012-11-27 17:57:12 +01:00
parent b49e75ff9a
commit 9ce5d9ee75
1 changed files with 24 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

35
youtube_dl/InfoExtractors.py
View file

@ -40,7 +40,7 @@ class InfoExtractor(object):
id: Video identifier.
url: Final video URL.
uploader: Nickname of the video uploader.
uploader: Nickname of the video uploader, unescaped.
upload_date: Video upload date (YYYYMMDD).
title: Video title, unescaped.
ext: Video filename extension.
@ -52,6 +52,8 @@ class InfoExtractor(object):
description: One-line video description.
player_url: SWF Player URL (used for rtmpdump).
The fields should all be Unicode strings.
Subclasses of this one should re-define the _real_initialize() and
_real_extract() methods and define a _VALID_URL regexp.
Probably, they should also be added to the list of extractors.
@ -1018,7 +1020,6 @@ def _real_extract(self, url, new_video=True):
'ext': video_extension.decode('utf-8'),
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description,
'thumbnail': video_thumbnail,
}]
@ -2129,6 +2130,8 @@ def _real_extract(self, url):
info = {
'id': title,
'url': url,
'uploader': u'NA',
'upload_date': u'NA',
'title': title,
'ext': ext,
'urlhandle': urlh
@ -2486,7 +2489,7 @@ def _real_extract(self, url):
'id': videoId,
'url': videoUrl,
'uploader': showName,
'upload_date': None,
'upload_date': u'NA',
'title': showName,
'ext': 'flv',
'thumbnail': imgUrl,
@ -2535,6 +2538,8 @@ def _real_extract(self, url):
info = {
'id': video_id,
'internal_id': internal_video_id,
'uploader': u'NA',
'upload_date': u'NA',
}
self.report_extraction(video_id)
@ -2619,8 +2624,8 @@ def _real_extract(self, url):
info = {
'id': video_id,
'url': video_url,
'uploader': None,
'upload_date': None,
'uploader': u'NA',
'upload_date': u'NA',
'title': video_title,
'ext': 'flv',
'thumbnail': video_thumbnail,
@ -2700,7 +2705,7 @@ def _real_extract(self, url):
description = mobj.group(1)
# upload date
upload_date = None
upload_date = u'NA'
mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage)
if mobj:
try:
@ -2781,8 +2786,8 @@ def _real_extract(self, url):
info = {
'id': video_id,
'url': video_url,
'uploader': None,
'upload_date': None,
'uploader': u'NA',
'upload_date': u'NA',
'title': video_title,
'ext': extension, # Extension is always(?) mp4, but seems to be flv
'thumbnail': None,
@ -2929,6 +2934,8 @@ def _real_extract(self, url):
video = mobj.group('video')
info = {
'id': course + '_' + video,
'uploader': u'NA',
'upload_date': u'NA',
}
self.report_extraction(info['id'])
@ -2953,6 +2960,8 @@ def _real_extract(self, url):
info = {
'id': course,
'type': 'playlist',
'uploader': u'NA',
'upload_date': u'NA',
}
self.report_download_webpage(info['id'])
@ -2989,6 +2998,8 @@ def _real_extract(self, url):
info = {
'id': 'Stanford OpenClassroom',
'type': 'playlist',
'uploader': u'NA',
'upload_date': u'NA',
}
self.report_download_webpage(info['id'])
@ -3097,6 +3108,7 @@ def _real_extract(self, url):
'id': video_id,
'url': video_url,
'uploader': performer,
'upload_date': u'NA',
'title': video_title,
'ext': ext,
'format': format,
@ -3217,7 +3229,8 @@ def _real_extract(self, url):
info = {
'id': '%s_part%02d' % (video_id, index),
'url': download_url,
'uploader': None,
'uploader': u'NA',
'upload_date': u'NA',
'title': video_title,
'ext': ext,
}
@ -3280,8 +3293,8 @@ def _real_extract(self, url):
return [{
'id': video_id,
'url': video_url,
'uploader': None,
'upload_date': None,
'uploader': u'NA',
'upload_date': u'NA',
'title': video_title,
'ext': 'flv',
'thumbnail': video_thumbnail,