catch unicode errors, returning nothing
This commit is contained in:
@@ -144,6 +144,8 @@ def extract_title(url):
|
|||||||
(html_text, headers) = fetch_page(url)
|
(html_text, headers) = fetch_page(url)
|
||||||
except URLError as e:
|
except URLError as e:
|
||||||
return None
|
return None
|
||||||
|
except UnicodeDecodeError:
|
||||||
|
return None
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
return 'failed: %s for %s' % (str(e), url)
|
return 'failed: %s for %s' % (str(e), url)
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user