Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[SlidesLive] Use token for JSON retrieval and improve metadata extraction #29958

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

[SlidesLive] Use token for JSON retrieval and improve metadata extraction #29958

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
91557e7
Use player_token in JSON retrieval
dirkf Sep 13, 2021
666a963
Improve metadata extraction
dirkf Sep 13, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
42 changes: 35 additions & 7 deletions youtube_dl/extractor/slideslive.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,13 @@

from .common import InfoExtractor
from ..utils import (
ExtractorError,
bool_or_none,
extract_attributes,
int_or_none,
smuggle_url,
try_get,
unified_timestamp,
url_or_none,
)

Expand All @@ -23,17 +27,20 @@ class SlidesLiveIE(InfoExtractor):
'description': 'Watch full version of this video at https://slideslive.com/38902413.',
'uploader': 'SlidesLive Videos - A',
'uploader_id': 'UC62SdArr41t_-_fX40QCLRw',
'timestamp': 1597615266,
'timestamp': 1618809663,
'upload_date': '20170925',
}
}, {
# video_service_name = yoda
'url': 'https://slideslive.com/38935785',
'md5': '575cd7a6c0acc6e28422fe76dd4bcb1a',
'md5': '575cd7a6c0acc6e28422fe76dd4bcb1a', # d735b130beb40013a839de1c58a74689
'info_dict': {
'id': 'RMraDYN5ozA_',
'id': 'F31OTzeGyDK_',
'display_id': '38935785',
'ext': 'mp4',
'title': 'Offline Reinforcement Learning: From Algorithms to Practical Challenges',
'upload_date': '20210220',
'timestamp': 1613785940,
},
'params': {
'format': 'bestvideo',
Expand All @@ -54,8 +61,17 @@ class SlidesLiveIE(InfoExtractor):

def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
player = self._search_regex(
r'<div\s[^>]*?id\s*=\s*(?P<q>\'|"|\b)player(?P=q)(?:\s[^>]*)?>.*?</div>',
webpage, 'player div', fatal=False, group=0)
player = (player and extract_attributes(player)) or {}
token = player.get('data-player-token')
if not token:
raise ExtractorError('Unable to get player token', expected=True)
video_data = self._download_json(
'https://ben.slideslive.com/player/' + video_id, video_id)
'https://ben.slideslive.com/player/' + video_id, video_id,
query={'player_token': token, })
service_name = video_data['video_service_name'].lower()
assert service_name in ('url', 'yoda', 'vimeo', 'youtube')
service_id = video_data['video_service_id']
Expand All @@ -72,12 +88,23 @@ def _real_extract(self, url):
})
info = {
'id': video_id,
'thumbnail': video_data.get('thumbnail'),
'thumbnail': video_data.get(
'thumbnail',
self._html_search_meta(('thumbnailUrl', 'thumbnailURL'), webpage)),
'is_live': bool_or_none(video_data.get('is_live')),
'subtitles': subtitles,
'timestamp': (
int_or_none(video_data.get('updated_at'))
or unified_timestamp(
self._html_search_meta('uploadDate', webpage))),
'creator': self._og_search_property('author', webpage, fatal=False),
}
title = (
video_data.get('title')
or self._html_search_meta('name', webpage, display_name='meta title')
or self._og_search_title(webpage, fatal=False))
if service_name in ('url', 'yoda'):
info['title'] = video_data['title']
info['title'] = title or video_data['title']
if service_name == 'url':
info['url'] = service_id
else:
Expand All @@ -93,14 +120,15 @@ def _real_extract(self, url):
self._sort_formats(formats)
info.update({
'id': service_id,
'display_id': video_id,
'formats': formats,
})
else:
info.update({
'_type': 'url_transparent',
'url': service_id,
'ie_key': service_name.capitalize(),
'title': video_data.get('title'),
'title': title,
})
if service_name == 'vimeo':
info['url'] = smuggle_url(
Expand Down