def wash_sensitive_info(self, data): ''' 清洗敏感信息 :param data: :return: ''' replace_str_list = [ ('小红书', '优秀网'), ('xiaohongshu', '优秀网'), ('XIAOHONGSHU', '优秀网'), ('某宝', '优秀网'), ('薯队长', '秀队长'), ('薯宝宝', '秀客'), ('红薯们', '秀客们'), ('小红薯', '小秀客'), ] add_sensitive_str_list = [ '#.*#', '@.*?薯', ] return wash_sensitive_info( data=data, replace_str_list=replace_str_list, add_sensitive_str_list=add_sensitive_str_list)
def _wash_comment(self, comment): ''' 清洗评论 :param comment: :return: ''' add_sensitive_str_list = [ '天猫超市', '天猫国际', '天猫全球购', '天猫大药房', '某淘', '某宝', '天猫', '淘宝', 'tmall', 'Tmall', 'TMALL', 'TAOBAO', 'taobao', ] comment = wash_sensitive_info( data=comment, add_sensitive_str_list=add_sensitive_str_list) return comment
def _wash_sensitive_info(self, data): add_sensitive_str_list = [ '【官方授权】', ] return wash_sensitive_info( data, add_sensitive_str_list=add_sensitive_str_list, )
def _wash_sensitive_info(self, target_str): ''' 清洗敏感信息 :param target_str: :return: ''' add_sensitive_str_list = [ '小米有品', ] target_str = wash_sensitive_info(data=target_str, replace_str_list=[], add_sensitive_str_list=add_sensitive_str_list) return target_str