From ad36a4a6ae8376a779f9feb08adfb2ca4a59dbb4 Mon Sep 17 00:00:00 2001
From: Mikhail Korobov <kmike84@gmail.com>
Date: Wed, 8 Feb 2017 16:58:38 +0500
Subject: [PATCH] RegexLinkExtractor: add \x0c to whitespace characters, as per
 html5 standard

---
 scrapy/linkextractors/regex.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/scrapy/linkextractors/regex.py b/scrapy/linkextractors/regex.py
index 0fc7b079f..e689b4727 100644
--- a/scrapy/linkextractors/regex.py
+++ b/scrapy/linkextractors/regex.py
@@ -10,9 +10,10 @@ linkre = re.compile(
         "<a\s.*?href=(\"[.#]+?\"|\'[.#]+?\'|[^\s]+?)(>|\s.*?>)(.*?)<[/ ]?a>",
         re.DOTALL | re.IGNORECASE)
 
+
 def clean_link(link_text):
     """Remove leading and trailing whitespace and punctuation"""
-    return link_text.strip("\t\r\n '\"")
+    return link_text.strip("\t\r\n '\"\x0c")
 
 
 class RegexLinkExtractor(SgmlLinkExtractor):