Miroirs/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-30 22:24:28 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

[ted] Fix playlist extraction (closes #20844)

Browse source
This commit is contained in:
biwubo 2019-05-09 18:11:27 +00:00 committed by Sergey M․
parent 4831ef7fe4
commit c2ee6fa66a
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 16 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

30
youtube_dl/extractor/ted.py
View file

@ -5,8 +5,12 @@ import re
from .common import InfoExtractor
from ..compat import compat_str
from ..compat import (
compat_str,
compat_urlparse
)
from ..utils import (
extract_attributes,
float_or_none,
int_or_none,
try_get,
@ -20,7 +24,7 @@ class TEDIE(InfoExtractor):
(?P<proto>https?://)
(?P<type>www|embed(?:-ssl)?)(?P<urlmain>\.ted\.com/
(
(?P<type_playlist>playlists(?:/\d+)?) # We have a playlist
(?P<type_playlist>playlists(?:/(?P<playlist_id>\d+))?) # We have a playlist
|
((?P<type_talk>talks)) # We have a simple talk
|
@ -84,6 +88,7 @@ class TEDIE(InfoExtractor):
'info_dict': {
'id': '10',
'title': 'Who are the hackers?',
'description': 'md5:49a0dbe8fb76d81a0e64b4a80af7f15a'
},
'playlist_mincount': 6,
}, {
@ -150,22 +155,19 @@ class TEDIE(InfoExtractor):
webpage = self._download_webpage(url, name,
'Downloading playlist webpage')
info = self._extract_info(webpage)
playlist_info = try_get(
info, lambda x: x['__INITIAL_DATA__']['playlist'],
dict) or info['playlist']
playlist_entries = []
for entry in re.findall(r'(?s)<[^>]+data-ga-context="playlist"[^>]*>', webpage):
attrs = extract_attributes(entry)
entry_url = compat_urlparse.urljoin(url, attrs['href'])
playlist_entries.append(self.url_result(entry_url, self.ie_key()))
playlist_entries = [
self.url_result('http://www.ted.com/talks/' + talk['slug'], self.ie_key())
for talk in try_get(
info, lambda x: x['__INITIAL_DATA__']['talks'],
dict) or info['talks']
]
final_url = self._og_search_url(webpage)
return self.playlist_result(
playlist_entries,
playlist_id=compat_str(playlist_info['id']),
playlist_title=playlist_info['title'])
playlist_id=re.match(self._VALID_URL, final_url, re.VERBOSE).group('playlist_id'),
playlist_title=self._og_search_title(webpage),
playlist_description=self._og_search_description(webpage))
def _talk_info(self, url, video_name):
webpage = self._download_webpage(url, video_name)