mirror/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl.git synced 2024-12-26 09:36:46 +00:00
Code Releases Activity

[theplatform] Support URLs with 'guid='

Browse source
This commit is contained in:
Yen Chi Hsuan 2015-08-20 01:38:39 +08:00
parent 26e1c3514f
commit 05fe2594e4
1 changed files with 36 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
youtube_dl/extractor/theplatform.py
View file

@ -9,6 +9,10 @@ import hashlib
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
@ -120,6 +124,20 @@ class ThePlatformIE(ThePlatformBaseIE):
}, { }, {
'url': 'http://player.theplatform.com/p/NnzsPC/widget/select/media/4Y0TlYUr_ZT7', 'url': 'http://player.theplatform.com/p/NnzsPC/widget/select/media/4Y0TlYUr_ZT7',
'only_matching': True, 'only_matching': True,
}, {
'url': 'http://player.theplatform.com/p/2E2eJC/nbcNewsOffsite?guid=tdy_or_siri_150701',
'md5': '734f3790fb5fc4903da391beeebc4836',
'info_dict': {
'id': 'tdy_or_siri_150701',
'ext': 'mp4',
'title': 'iPhone Siri’s sassy response to a math question has people talking',
'description': 'md5:a565d1deadd5086f3331d57298ec6333',
'duration': 83.0,
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1435752600,
'upload_date': '20150701',
'categories': ['Today/Shows/Orange Room', 'Today/Sections/Money', 'Today/Topics/Tech', "Today/Topics/Editor's picks"],
},
}] }]
@staticmethod @staticmethod
@ -154,6 +172,24 @@ class ThePlatformIE(ThePlatformBaseIE):
path += '/media' path += '/media'
path += '/' + video_id path += '/' + video_id
qs_dict = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
if 'guid' in qs_dict:
webpage = self._download_webpage(url, video_id)
scripts = re.findall(r'<script[^>]+src="([^"]+)"', webpage)
feed_id = None
# feed id usually locates in the last script.
# Seems there's no pattern for the interested script filename, so
# I try one by one
for script in reversed(scripts):
feed_script = self._download_webpage(script, video_id, 'Downloading feed script')
feed_id = self._search_regex(r'defaultFeedId\s*:\s*"([^"]+)"', feed_script, 'default feed id', default=None)
if feed_id is not None:
break
if feed_id is None:
raise ExtractorError('Unable to find feed id')
return self.url_result('http://feed.theplatform.com/f/%s/%s?byGuid=%s' % (
provider_id, feed_id, qs_dict['guid'][0]))
if smuggled_data.get('force_smil_url', False): if smuggled_data.get('force_smil_url', False):
smil_url = url smil_url = url
elif mobj.group('config'): elif mobj.group('config'):