Browse Source

removed duplicate and somemtimes incorrect logic for parsing upload date as this job is already taken care of automatically by YoutubeDL.py

totalwebcasting
codesparkle 10 years ago
parent
commit
69f8364042
3 changed files with 20 additions and 30 deletions
  1. +6
    -9
      youtube_dl/extractor/aftonbladet.py
  2. +12
    -18
      youtube_dl/extractor/blinkx.py
  3. +2
    -3
      youtube_dl/extractor/mailru.py

+ 6
- 9
youtube_dl/extractor/aftonbladet.py View File

@ -1,7 +1,6 @@
# encoding: utf-8
from __future__ import unicode_literals
import datetime
import re
from .common import InfoExtractor
@ -16,6 +15,7 @@ class AftonbladetIE(InfoExtractor):
'ext': 'mp4',
'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
'description': 'Jupiters måne mest aktiv av alla himlakroppar',
'timestamp': 1394142732,
'upload_date': '20140306',
},
}
@ -27,17 +27,17 @@ class AftonbladetIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
# find internal video meta data
META_URL = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
internal_meta_id = self._html_search_regex(
r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id')
internal_meta_url = META_URL % internal_meta_id
internal_meta_url = meta_url % internal_meta_id
internal_meta_json = self._download_json(
internal_meta_url, video_id, 'Downloading video meta data')
# find internal video formats
FORMATS_URL = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
format_url = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
internal_video_id = internal_meta_json['videoId']
internal_formats_url = FORMATS_URL % internal_video_id
internal_formats_url = format_url % internal_video_id
internal_formats_json = self._download_json(
internal_formats_url, video_id, 'Downloading video formats')
@ -54,16 +54,13 @@ class AftonbladetIE(InfoExtractor):
})
self._sort_formats(formats)
timestamp = datetime.datetime.fromtimestamp(internal_meta_json['timePublished'])
upload_date = timestamp.strftime('%Y%m%d')
return {
'id': video_id,
'title': internal_meta_json['title'],
'formats': formats,
'thumbnail': internal_meta_json['imageUrl'],
'description': internal_meta_json['shortPreamble'],
'upload_date': upload_date,
'timestamp': internal_meta_json['timePublished'],
'duration': internal_meta_json['duration'],
'view_count': internal_meta_json['views'],
}

+ 12
- 18
youtube_dl/extractor/blinkx.py View File

@ -1,6 +1,5 @@
from __future__ import unicode_literals
import datetime
import json
import re
@ -19,15 +18,16 @@ class BlinkxIE(InfoExtractor):
'file': '8aQUy7GV.mp4',
'md5': '2e9a07364af40163a908edbf10bb2492',
'info_dict': {
"title": "Police Car Rolls Away",
"uploader": "stupidvideos.com",
"upload_date": "20131215",
"description": "A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!",
"duration": 14.886,
"thumbnails": [{
"width": 100,
"height": 76,
"url": "http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg",
'title': 'Police Car Rolls Away',
'uploader': 'stupidvideos.com',
'upload_date': '20131215',
'timestamp': 1387068000,
'description': 'A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!',
'duration': 14.886,
'thumbnails': [{
'width': 100,
'height': 76,
'url': 'http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg',
}],
},
}
@ -41,9 +41,6 @@ class BlinkxIE(InfoExtractor):
'video=%s' % video_id)
data_json = self._download_webpage(api_url, display_id)
data = json.loads(data_json)['api']['results'][0]
dt = datetime.datetime.fromtimestamp(data['pubdate_epoch'])
pload_date = dt.strftime('%Y%m%d')
duration = None
thumbnails = []
formats = []
@ -64,10 +61,7 @@ class BlinkxIE(InfoExtractor):
vcodec = remove_start(m['vcodec'], 'ff')
acodec = remove_start(m['acodec'], 'ff')
tbr = (int(m['vbr']) + int(m['abr'])) // 1000
format_id = (u'%s-%sk-%s' %
(vcodec,
tbr,
m['w']))
format_id = u'%s-%sk-%s' % (vcodec, tbr, m['w'])
formats.append({
'format_id': format_id,
'url': m['link'],
@ -88,7 +82,7 @@ class BlinkxIE(InfoExtractor):
'title': data['title'],
'formats': formats,
'uploader': data['channel_name'],
'upload_date': pload_date,
'timestamp': data['pubdate_epoch'],
'description': data.get('description'),
'thumbnails': thumbnails,
'duration': duration,


+ 2
- 3
youtube_dl/extractor/mailru.py View File

@ -2,7 +2,6 @@
from __future__ import unicode_literals
import re
import datetime
from .common import InfoExtractor
@ -19,6 +18,7 @@ class MailRuIE(InfoExtractor):
'id': '46301138',
'ext': 'mp4',
'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
'timestamp': 1393232740,
'upload_date': '20140224',
'uploader': 'sonypicturesrus',
'uploader_id': 'sonypicturesrus@mail.ru',
@ -43,7 +43,6 @@ class MailRuIE(InfoExtractor):
thumbnail = movie['poster']
duration = movie['duration']
upload_date = datetime.datetime.fromtimestamp(video_data['timestamp']).strftime('%Y%m%d')
view_count = video_data['views_count']
formats = [
@ -57,7 +56,7 @@ class MailRuIE(InfoExtractor):
'id': content_id,
'title': title,
'thumbnail': thumbnail,
'upload_date': upload_date,
'timestamp': video_data['timestamp'],
'uploader': uploader,
'uploader_id': uploader_id,
'duration': duration,


Loading…
Cancel
Save