From b3f8f55f230d266bcd53f6321490326e8e286188 Mon Sep 17 00:00:00 2001
From: Ofa <chunghsianghsueh@gmail.com>
Date: Wed, 14 Jun 2023 22:21:05 -0400
Subject: [PATCH] Update parsers.py

fix starts with requires bytes issue
---
 newspaper/parsers.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/newspaper/parsers.py b/newspaper/parsers.py
index a4d030c0..560d4052 100644
--- a/newspaper/parsers.py
+++ b/newspaper/parsers.py
@@ -63,7 +63,7 @@ def fromstring(cls, html):
         # down due to one article (out of potentially many in a `Source`)
         try:
             # lxml does not play well with <? ?> encoding tags
-            if html.startswith('<?'):
+            if html.startswith(b'<?'):
                 html = re.sub(r'^\<\?.*?\?\>', '', html, flags=re.DOTALL)
             cls.doc = lxml.html.fromstring(html)
             return cls.doc