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

This commit is contained in:
Filippo Valsorda 2012-11-27 17:57:12 +01:00
parent b49e75ff9a
commit 9ce5d9ee75

View File

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