From 5b58821823c08eb63d138ca5245aff010ed4fa46 Mon Sep 17 00:00:00 2001 From: satunnainen Date: Sun, 9 Jul 2017 18:55:54 +0300 Subject: [PATCH 1/2] [slideshare] fix extraction --- youtube_dl/extractor/slideshare.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/slideshare.py b/youtube_dl/extractor/slideshare.py index 74a1dc672..870b16821 100644 --- a/youtube_dl/extractor/slideshare.py +++ b/youtube_dl/extractor/slideshare.py @@ -31,7 +31,7 @@ class SlideshareIE(InfoExtractor): page_title = mobj.group('title') webpage = self._download_webpage(url, page_title) slideshare_obj = self._search_regex( - r'\$\.extend\(slideshare_object,\s*(\{.*?\})\);', + r'\$\.extend\(.*slideshare_object,\s*(\{.*?\})\);', webpage, 'slideshare object') info = json.loads(slideshare_obj) if info['slideshow']['type'] != 'video': From f3c56e21adcb86163564bcf7c845a4d0243d8dfc Mon Sep 17 00:00:00 2001 From: satunnainen Date: Sun, 9 Jul 2017 19:37:53 +0300 Subject: [PATCH 2/2] fix greedy regex --- youtube_dl/extractor/slideshare.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/slideshare.py b/youtube_dl/extractor/slideshare.py index 870b16821..e89ebebe7 100644 --- a/youtube_dl/extractor/slideshare.py +++ b/youtube_dl/extractor/slideshare.py @@ -31,7 +31,7 @@ class SlideshareIE(InfoExtractor): page_title = mobj.group('title') webpage = self._download_webpage(url, page_title) slideshare_obj = self._search_regex( - r'\$\.extend\(.*slideshare_object,\s*(\{.*?\})\);', + r'\$\.extend\(.*?slideshare_object,\s*(\{.*?\})\);', webpage, 'slideshare object') info = json.loads(slideshare_obj) if info['slideshow']['type'] != 'video':