diff options
| author | Sergey M․ <dstftw@gmail.com> | 2016-03-07 02:19:54 +0600 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2016-03-07 02:19:54 +0600 |
| commit | 46c329d6f66368a7129e136ffe3fdf40dbb67b91 (patch) | |
| tree | 343cef7ee51c4f904f002cb3048144fdb3bba404 | |
| parent | 1818e4c2b4e0f55169d65131f257bb87d1ce52d5 (diff) | |
[arte] Improve extraction (Closes #8768)
| -rw-r--r-- | youtube_dl/extractor/arte.py | 9 |
1 files changed, 6 insertions, 3 deletions
diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 7f99effa9..3e119e21b 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -121,7 +121,10 @@ class ArteTVPlus7IE(InfoExtractor): json_url = compat_parse_qs( compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0] 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. # http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium) embed_url = self._search_regex( @@ -129,7 +132,7 @@ class ArteTVPlus7IE(InfoExtractor): webpage, 'embed url', group='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) player_info = info['videoJsonPlayer'] @@ -137,7 +140,7 @@ class ArteTVPlus7IE(InfoExtractor): if not upload_date_str: 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() if subtitle: title += ' - %s' % subtitle |