From 46c329d6f66368a7129e136ffe3fdf40dbb67b91 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Mon, 7 Mar 2016 02:19:54 +0600
Subject: [PATCH] [arte] Improve extraction (Closes #8768)
---
youtube_dl/extractor/arte.py | 9 ++++++---
1 file 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