w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[cbc] Improve extraction for videos embedded with clipId

Browse source
This commit is contained in:
Sergey M․ 2016-07-26 22:58:50 +07:00
parent 7f8b92e3cf
commit 88bd486b9a
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 25 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

29
youtube_dl/extractor/cbc.py
View file

@ -4,9 +4,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
js_to_json,
smuggle_url,
try_get,
)
@ -27,7 +29,20 @@ class CBCIE(InfoExtractor):
},
'skip': 'Geo-restricted to Canada',
}, {
# with clipId
# with clipId, feed available via tpfeed.cbc.ca and feed.theplatform.com
'url': 'http://www.cbc.ca/22minutes/videos/22-minutes-update/22-minutes-update-episode-4',
'md5': '162adfa070274b144f4fdc3c3b8207db',
'info_dict': {
'id': '2414435309',
'ext': 'mp4',
'title': '22 Minutes Update: What Not To Wear Quebec',
'description': "This week's latest Canadian top political story is What Not To Wear Quebec.",
'upload_date': '20131025',
'uploader': 'CBCC-NEW',
'timestamp': 1382717907,
},
}, {
# with clipId, feed only available via tpfeed.cbc.ca
'url': 'http://www.cbc.ca/archives/entry/1978-robin-williams-freestyles-on-90-minutes-live',
'md5': '0274a90b51a9b4971fe005c63f592f12',
'info_dict': {
@ -83,9 +98,15 @@ class CBCIE(InfoExtractor):
media_id = player_info.get('mediaId')
if not media_id:
clip_id = player_info['clipId']
media_id = self._download_json(
'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
clip_id)['entries'][0]['id'].split('/')[-1]
feed = self._download_json(
'http://tpfeed.cbc.ca/f/ExhSPC/vms_5akSXx4Ng_Zn?byCustomValue={:mpsReleases}{%s}'% clip_id,
clip_id, fatal=False)
if feed:
media_id = try_get(feed, lambda x: x['entries'][0]['guid'], compat_str)
if not media_id:
media_id = self._download_json(
'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
clip_id)['entries'][0]['id'].split('/')[-1]
return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
else:
entries = [self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)]