From 04423589420a563cc0244e2b5a282c279e48c47e Mon Sep 17 00:00:00 2001
From: Dario <4755+dariobig@users.noreply.github.com>
Date: Sat, 16 Nov 2019 19:44:34 -0500
Subject: [PATCH] Catch LookupError in case of bad encoding string

I've seen cases where bad encoding strings will result in errors, catching LookupError should solve the problem by falling back onto `chardet` or `utf-8`

Here's one case:

```
 textPayload: "Traceback (most recent call last):
  File "/opt/conda/lib/python3.7/site-packages/readability/readability.py", line 189, in summary
    self._html(True)
  File "/opt/conda/lib/python3.7/site-packages/readability/readability.py", line 132, in _html
    self.html = self._parse(self.input)
  File "/opt/conda/lib/python3.7/site-packages/readability/readability.py", line 141, in _parse
    doc, self.encoding = build_doc(input)
  File "/opt/conda/lib/python3.7/site-packages/readability/htmls.py", line 17, in build_doc
    encoding = get_encoding(page) or 'utf-8'
  File "/opt/conda/lib/python3.7/site-packages/readability/encoding.py", line 46, in get_encoding
    page.decode(encoding)
LookupError: unknown encoding: utf-8, ie=edge, chrome=1
```
---
 readability/encoding.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/readability/encoding.py b/readability/encoding.py
index cc14320..ebacded 100644
--- a/readability/encoding.py
+++ b/readability/encoding.py
@@ -46,7 +46,7 @@ def get_encoding(page):
             page.decode(encoding)
             # It worked!
             return encoding
-        except UnicodeDecodeError:
+        except (UnicodeDecodeError, LookupError):
             pass
 
     # Fallback to chardet if declared encodings fail