Exclude a bunch of unicode url-encoded patterns

gen-ignores.py

@@ -10,6 +10,7 @@
 import glob
 import json
 import os
+import re
 import sys
 
 archivebot_ignore_path = sys.argv[1]
@@ -24,6 +25,8 @@ for fn in glob.glob(os.path.join(archivebot_ignore_path, '*.json')):
                     # fancy PCRE constructs. This excludes <10
                     # patterns from the ignore list.
                     continue
+                if re.search(r'(?:%[0-9A-F]{2}){3,}', p):
+                    continue
                 p = p.replace('{primary_netloc}', '.*')
                 print('\t%s,' % json.dumps(p))
     except Exception as e: