网上搜的过滤敏感词的一段代码，测试后发现在过

网上搜的过滤敏感词的一段代码，测试后发现在过滤不干净。各位大神有空帮看下哪里的问题吧。

[Python] 纯文本查看 复制代码

?

001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050 051 052 053 054 055 056 057 058 059 060 061 062 063 064 065 066 067 068 069 070 071 072 073 074 075 076 077 078 079 080 081 082 083 084 085 086 087 088 089 090 091 092 093 094 095 096 097 098 099 100 101 102 103 104 105 106 107 108 109 110

import time time1=time.time()   # AC自动机算法 class node(object):     def __init__(self):         self.next = {}         self.fail = None         self.isWord = False         self.word = ""   class ac_automation(object):       def __init__(self):         self.root = node()       # 添加敏感词函数     def addword(self, word):         temp_root = self.root         for char in word:             if char not in temp_root.next:                 temp_root.next[char] = node()             temp_root = temp_root.next[char]         temp_root.isWord = True         temp_root.word = word       # 失败指针函数     def make_fail(self):         temp_que = []         temp_que.append(self.root)         while len(temp_que) != 0:             temp = temp_que.pop(0)             p = None             for key,value in temp.next.item():                 if temp == self.root:                     temp.next[key].fail = self.root                 else:                     p = temp.fail                     while p is not None:                         if key in p.next:                             temp.next[key].fail = p.fail                             break                         p = p.fail                     if p is None:                         temp.next[key].fail = self.root                 temp_que.append(temp.next[key])       # 查找敏感词函数     def search(self, content):         p = self.root         result = []         currentposition = 0           while currentposition < len(content):             word = content[currentposition]             while word in p.next == False and p != self.root:                 p = p.fail               if word in p.next:                 p = p.next[word]             else:                 p = self.root               if p.isWord:                 result.append(p.word)                 p = self.root             currentposition += 1         return result       # 加载敏感词库函数     def parse(self, path):         with open(path,encoding='utf-8') as f:             for keyword in f:                 self.addword(str(keyword).strip())       # 敏感词替换函数     def words_replace(self, text):         """         :param ah: AC自动机         :param text: 文本         :return: 过滤敏感词之后的文本         """         result = list(set(self.search(text)))         for x in result:             m = text.replace(x, '*' * len(x))             text = m         return text           if __name__ == '__main__':       ah = ac_automation()     path='e:/baidu_filter.txt'     ah.parse(path)     filename="e:/lbj.txt"     fp=open(filename,'r')     data=fp.read()           text1=data     text2=ah.words_replace(text1)     rs=open("e:/rs.txt","w")     rs.write(text2)     rs.close()     print(text1)     print(text2)       time2 = time.time()

下面是词库 [词库](链接：pan.baidu.com/s/1QYviLOHIkxKiDUYCf... 提取码：tf5q 复制这段内容后打开百度网盘手机 App，操作更方便哦–来自百度网盘超级会员 V4 的分享 “词库”)
这里是原文链接：pan.baidu.com/s/193rF_C7fg5W_hFR6T...
提取码：xojo
原文里的 非典 两个词不知道为什么 过滤不掉