From 12e42bbe06bea5a0f86e95630b184e86b41c95c7 Mon Sep 17 00:00:00 2001 From: Mikhail Korobov Date: Wed, 22 Aug 2018 04:20:55 +0500 Subject: [PATCH] switch SgmlLinkExtractor to .getall --- scrapy/linkextractors/sgml.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scrapy/linkextractors/sgml.py b/scrapy/linkextractors/sgml.py index f4ca4262a..5fa6b771c 100644 --- a/scrapy/linkextractors/sgml.py +++ b/scrapy/linkextractors/sgml.py @@ -141,7 +141,7 @@ class SgmlLinkExtractor(FilteringLinkExtractor): base_url = get_base_url(response) body = u''.join(f for x in self.restrict_xpaths - for f in response.xpath(x).extract() + for f in response.xpath(x).getall() ).encode(response.encoding, errors='xmlcharrefreplace') else: body = response.body