catch unicode errors, returning nothing

2016-01-06 16:02:54 +01:00
parent 3480491013
commit eb79b8bf80
1 changed files with 2 additions and 0 deletions
--- a/common.py
+++ b/common.py
@@ -144,6 +144,8 @@ def extract_title(url):
        (html_text, headers) = fetch_page(url)
    except URLError as e:
        return None
+    except UnicodeDecodeError:
+        return None
    except Exception as e:
        return 'failed: %s for %s' % (str(e), url)