mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-21 20:46:36 -05:00
[thescene] Fix extraction and improve style (Closes #8978)
This commit is contained in:
parent
4db441de72
commit
2156f16ca7
1 changed files with 11 additions and 7 deletions
|
@ -2,7 +2,7 @@
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
|
|
||||||
from ..compat import compat_urllib_parse
|
from ..compat import compat_urlparse
|
||||||
from ..utils import qualities
|
from ..utils import qualities
|
||||||
|
|
||||||
|
|
||||||
|
@ -21,17 +21,21 @@ class TheSceneIE(InfoExtractor):
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
display_id = self._match_id(url)
|
display_id = self._match_id(url)
|
||||||
|
|
||||||
webpage = self._download_webpage(url, display_id)
|
webpage = self._download_webpage(url, display_id)
|
||||||
player_url = compat_urllib_parse.urljoin(
|
|
||||||
|
player_url = compat_urlparse.urljoin(
|
||||||
url,
|
url,
|
||||||
self._html_search_regex(
|
self._html_search_regex(
|
||||||
r'id=\'js-player-script\'[^>]+src=\'(.+?)\'', webpage, 'player url'))
|
r'id=\'js-player-script\'[^>]+src=\'(.+?)\'', webpage, 'player url'))
|
||||||
|
|
||||||
self.to_screen(player_url)
|
player = self._download_webpage(player_url, display_id)
|
||||||
player = self._download_webpage(player_url, player_url)
|
info = self._parse_json(
|
||||||
info = self._parse_json(self._search_regex(r'(?m)var\s+video\s+=\s+({.+?});$', player, 'info json'), display_id)
|
self._search_regex(
|
||||||
|
r'(?m)var\s+video\s+=\s+({.+?});$', player, 'info json'),
|
||||||
|
display_id)
|
||||||
|
|
||||||
qualities_order = qualities(['low', 'high'])
|
qualities_order = qualities(('low', 'high'))
|
||||||
formats = [{
|
formats = [{
|
||||||
'format_id': '{0}-{1}'.format(f['type'].split('/')[0], f['quality']),
|
'format_id': '{0}-{1}'.format(f['type'].split('/')[0], f['quality']),
|
||||||
'url': f['src'],
|
'url': f['src'],
|
||||||
|
@ -41,8 +45,8 @@ def _real_extract(self, url):
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': info['id'],
|
'id': info['id'],
|
||||||
|
'display_id': display_id,
|
||||||
'title': info['title'],
|
'title': info['title'],
|
||||||
'formats': formats,
|
'formats': formats,
|
||||||
'thumbnail': info.get('poster_frame'),
|
'thumbnail': info.get('poster_frame'),
|
||||||
'display_id': display_id,
|
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in a new issue