Merge pull request #112 from haron/patch-1

Fix for UnicodeDecodeError: 'utf-8' codec can't decode bytes
alan-turing-institute · Nov 25, 2024 · f9b9987 · f9b9987
2 parents 41d47eb + 3e7a9de
commit f9b9987
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/readabilipy/__main__.py b/readabilipy/__main__.py
@@ -55,7 +55,7 @@ def main():
 
     args = parser.parse_args()
 
-    with open(args.input_file, encoding="utf-8") as h:
+    with open(args.input_file, encoding="utf-8", errors="replace") as h:
         html = h.read()
 
     article = simple_json_from_html_string(