diff --git a/crawler.py b/crawler.py index ff6debe..8c216e3 100644 --- a/crawler.py +++ b/crawler.py @@ -48,6 +48,7 @@ def IP_URL_FILTERING(filters_welcome): file[i] = re.sub('/..+\Z', '', file[i]) file[i] = re.sub(':(\d\d\d\d\d|\d\d\d\d|\d\d\d|\d\d|\d)', '', file[i]) file[i] = re.sub('(\d|\d\d|\d\d\d)\.(\d|\d\d|\d\d\d)\.(\d|\d\d|\d\d\d)\.(\d|\d\d|\d\d\d)\Z', '', file[i]) + file[i] = re.sub('\[..*\]', '', file[i]) with open(filters_welcome, 'w') as f1: f1.writelines(["%s\n" % item for item in file]) print("Ip Address and Url Path filtering Operation Completed!")