github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-25 22:54:29 +00:00
Code Issues Projects Releases Packages Wiki Activity

[arte] Improve extraction (Closes #8768)

Browse source
This commit is contained in:
Sergey M․ 2016-03-07 02:19:54 +06:00
parent 1818e4c2b4
commit 46c329d6f6
1 changed files with 6 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
youtube_dl/extractor/arte.py
View file

@ -121,7 +121,10 @@ def find_iframe_url(webpage, default=NO_DEFAULT):
json_url = compat_parse_qs( json_url = compat_parse_qs(
compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0] compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
if json_url: if json_url:
return self._extract_from_json_url(json_url, video_id, lang) title = self._search_regex(
r'<h3[^>]+title=(["\'])(?P<title>.+?)\1',
webpage, 'title', default=None, group='title')
return self._extract_from_json_url(json_url, video_id, lang, title=title)
# Different kind of embed URL (e.g. # Different kind of embed URL (e.g.
# http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium) # http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium)
embed_url = self._search_regex( embed_url = self._search_regex(
@ -129,7 +132,7 @@ def find_iframe_url(webpage, default=NO_DEFAULT):
webpage, 'embed url', group='url') webpage, 'embed url', group='url')
return self.url_result(embed_url) return self.url_result(embed_url)
def _extract_from_json_url(self, json_url, video_id, lang): def _extract_from_json_url(self, json_url, video_id, lang, title=None):
info = self._download_json(json_url, video_id) info = self._download_json(json_url, video_id)
player_info = info['videoJsonPlayer'] player_info = info['videoJsonPlayer']
@ -137,7 +140,7 @@ def _extract_from_json_url(self, json_url, video_id, lang):
if not upload_date_str: if not upload_date_str:
upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0] upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0]
title = player_info['VTI'].strip() title = (player_info.get('VTI') or title or player_info['VID']).strip()
subtitle = player_info.get('VSU', '').strip() subtitle = player_info.get('VSU', '').strip()
if subtitle: if subtitle:
title += ' - %s' % subtitle title += ' - %s' % subtitle