From 01441efe7564e31e465c84377518ec33176fb893 Mon Sep 17 00:00:00 2001
From: jesopo
Date: Thu, 6 Feb 2020 11:54:04 +0000
Subject: only pull 'charset' from <meta> content-type when it definitely
 exists

---
 src/utils/http.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'src/utils/http.py')

diff --git a/src/utils/http.py b/src/utils/http.py
index f5595a2a..239ae11a 100644
--- a/src/utils/http.py
+++ b/src/utils/http.py
@@ -153,7 +153,9 @@ def _find_encoding(headers: typing.Dict[str, str], data: bytes
         meta_content_type = soup.findAll("meta",
             {"http-equiv": lambda v: (v or "").lower() == "content-type"})
         if meta_content_type:
-            return _split_content(meta_content_type[0].get("content"))["charset"]
+            meta_content = _split_content(meta_content_type[0].get("content"))
+            if "charset" in meta_content:
+                return meta_content["charset"]
 
     doctype = [item for item in soup.contents if isinstance(item,
         bs4.Doctype)] or None
-- 
cgit v1.3.1-10-gc9f91