Python之拼音拆分

经常会需要用到将zhangwei转化为ZhangWei、Zw、Zhangw之类的，就涉及到一个拼音拆分算法，这里写了一个demo分享给大家

我的思路是先将声母转换为大写，然后就可以根据大写字母来分割单个拼音

学的拼音早忘差不多了，百度了一下，声母有bpmfdtnlgkhjqxrzczyw

转化代码

def sm(strs):
    smlist = 'bpmfdtnlgkhjqxrzcsyw'

    for s in smlist:
        strs = strs.replace(s,s.upper())

    return strs

然后发现有个问题，韵母中也包含了声母的元素，zhangwei就会变成ZHaNGWei

发现两个问题，一个是Zh、Ch、Sh这类的包含了声母h，一个是er、an、en、in、un、vn、ang、eng、ing、ong这类的包含了声母r、n、g

于是再加一个转换

def sm(strs):
    smlist = 'bpmfdtnlgkhjqxrzcsyw'
    nosm = ['eR','aN','eN','iN','uN','vN','nG','NG']
    rep = {'ZH':'Zh','CH':'Ch','SH':'Sh'}

    for s in smlist:
        strs = strs.replace(s,s.upper())

    for s in nosm:
        strs = strs.replace(s,s.lower())

    for s in rep.keys():
        strs = strs.replace(s,rep[s])

    return strs

这时候zhangwei已经可以转为ZhangWei了

在进行批量转换的时候又遇到一个问题，碰到chenguiying(陈桂英)这种拼音的时候，会转化为ChenguiYing，这是因为r、n、g既可以做结尾，也可以做声母，于是又对nosm这个list进行一次判断，发现这类后，再往后判断一个字符，判断是否在声母表中

def sm(strs):
    smlist = 'bpmfdtnlgkhjqxrzcsyw'
    nosm = ['eR','aN','eN','iN','uN','vN','nG','NG']
    rep = {'ZH':'Zh','CH':'Ch','SH':'Sh'}

    for s in smlist:
        strs = strs.replace(s,s.upper())

    for s in nosm:
        strs = strs.replace(s,s.lower())

    for s in rep.keys():
        strs = strs.replace(s,rep[s])

    for s in nosm:
        tmp_num = 0
        isOk = False
        while (tmp_num < len(strs)) and (isOk==False):
            try:
                tmp_num = strs.index(s.lower(),tmp_num)
            except:
                isOk = True
            else:
                tmp_num = tmp_num + len(s)
                if strs[tmp_num:tmp_num+1].lower() not in smlist:
                    strs = strs[:tmp_num-1]+strs[tmp_num-1:tmp_num].upper()+strs[tmp_num:]

    return strs

这时候已经可以提取声母了，剩下就简单了，碰到大写字母后就是一个拼音的开始，提取简拼就只找大写字母

拆分

def onep(strs):
    restr = ''
    strs = sm(strs)
    for s in strs:
        if 'A' <= s and s <= 'Z':
            restr = restr + ' ' + s
        else:
            restr = restr + s

    restr = restr[1:]
    restr = restr.lower()
    return restr.split(' ')

返回

['chen','gui','ying']

简拼提取

def simplep(strs):
    restr = ''
    strs = sm(strs)
    for s in strs:
        if 'A' <= s and s <= 'Z':
            restr = restr + s

    restr = restr.lower()

    return restr

返回

cgy

然后就可以玩很多了

附一个通过拼音生成弱口令字典的脚本

#!/usr/bin/python
# Author : wkong
# Crack

def clearChar(chars):
    reStr = ['\n','\r','\t',' ']

    for reS in reStr:
        chars = chars.replace(reS, '')

    return chars


def sm(strs):
    smlist = 'bpmfdtnlgkhjqxrzcsyw'
    nosm = ['eR','aN','eN','iN','uN','vN','nG','NG']
    rep = {'ZH':'Zh','CH':'Ch','SH':'Sh'}

    for s in smlist:
        strs = strs.replace(s,s.upper())

    for s in nosm:
        strs = strs.replace(s,s.lower())

    for s in rep.keys():
        strs = strs.replace(s,rep[s])

    for s in nosm:
        tmp_num = 0
        isOk = False
        while (tmp_num < len(strs)) and (isOk==False):
            try:
                tmp_num = strs.index(s.lower(),tmp_num)
            except:
                isOk = True
            else:
                tmp_num = tmp_num + len(s)
                if strs[tmp_num:tmp_num+1].lower() not in smlist:
                    strs = strs[:tmp_num-1]+strs[tmp_num-1:tmp_num].upper()+strs[tmp_num:]

    return strs

def simplep(strs):
    restr = ''
    strs = sm(strs)
    for s in strs:
        if 'A' <= s and s <= 'Z':
            restr = restr + s

    restr = restr.lower()
    restr = restr.capitalize()

    return restr

def rePass(name):
    uList = []
    uList.append(user.capitalize())
    uList.append(sm(user))
    uList.append(simplep(user))

    pwdList = []

    ce = ['!@#123','123!@#','@123','@1234','@12345','@123456','123','1234','12345','123456','123.','1234.','12345.','123456.','123123','abc','abc@123','qwer!@#','!@#qwer','qwe!@#','!@#qwe','!QAZ2wsx','1q2w3e']

    for s in ce:
        for u in uList:
            pwdList.append(u+s)

    return pwdList

def autoCrack(username, password):
    print(username+':'+password)


if __name__ == '__main__':
    userFile = 'zhangwei.txt'

    pUserFile = open(userFile, 'r')

    userList = pUserFile.readlines()

    pUserFile.close()

    for user in userList:
        user = clearChar(user) 
        pwd = rePass(user)
        for pw in pwd:
            autoCrack(user, pw)