From d7c78decb0fb4adcf84e5e74cd0d4f858d48e2ee Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Fri, 10 Apr 2015 22:41:26 +0600
Subject: [PATCH] [rai] Improve extraction
---
youtube_dl/extractor/rai.py | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py
index 115cc64cc..12127c634 100644
--- a/youtube_dl/extractor/rai.py
+++ b/youtube_dl/extractor/rai.py
@@ -82,9 +82,9 @@ class RaiIE(InfoExtractor):
iframe_path = self._search_regex(
r'<iframe[^>]+src="/?(dl/[^"]+\?iframe\b[^"]*)"',
webpage, 'iframe')
- iframe_page = self._download_webpage(
+ webpage = self._download_webpage(
'%s/%s' % (host, iframe_path), video_id)
- relinker_url = self._extract_relinker_url(iframe_page)
+ relinker_url = self._extract_relinker_url(webpage)
relinker = self._download_json(
'%s&output=47' % relinker_url, video_id)
@@ -112,15 +112,15 @@ class RaiIE(InfoExtractor):
uploader = media.get('author')
upload_date = unified_strdate(media.get('date'))
else:
- title = self._search_regex(
- r'var\s+videoTitolo\s*=\s*"([^"]+)";',
- webpage, 'title', default=None) or self._og_search_title(webpage)
+ title = (self._search_regex(
+ r'var\s+videoTitolo\s*=\s*"(.+?)";',
+ webpage, 'title', default=None) or self._og_search_title(webpage)).replace('\\"', '"')
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
duration = None
uploader = self._html_search_meta('Editore', webpage, 'uploader')
upload_date = unified_strdate(self._html_search_meta(
- 'item-date', webpage, 'upload date'))
+ 'item-date', webpage, 'upload date', default=None))
subtitles = self.extract_subtitles(video_id, webpage)