Handle IDNA encoding failures for netloc part

Author: redapple

w3lib/url.py

@@ -90,11 +90,18 @@ def safe_url_string(url, encoding='utf8', path_encoding='utf8'):
     parts = urlsplit(to_unicode(url, encoding=encoding,
                                 errors='percentencode'))
 
+    # IDNA encoding can fail for too long labels (>63 characters)
+    # or missing labels (e.g. http://.example.com)
+    try:
+        netloc = parts.netloc.encode('idna')
+    except UnicodeError:
+        netloc = parts.netloc
+
     # quote() in Python2 return type follows input type;
     # quote() in Python3 always returns Unicode (native str)
     return urlunsplit((
         to_native_str(parts.scheme),
-        to_native_str(parts.netloc.encode('idna')),
+        to_native_str(netloc),
 
         # default encoding for path component SHOULD be UTF-8
         quote(to_bytes(parts.path, path_encoding), _safe_chars),