Find Head&Rear

import time
try:
    from Tkinter import *  #python 2.x
    from tkFileDialog import *   #python 2.x
except importError as e:
    from tkinter import *
    from tkinter.filedialog import *

import binascii
import os
import os.path
import re

class TextToHex:
    def __init__(self):
        root = Tk()
        root.title("Find Head&Rear")
        # frame1 排版布局
        frame1 = frame(root,pady = 6)
        frame1.grid(row=1, column=1)

        # 文件夹路径 账单头标识符 头-文件总数 等项布局
        lablenames = ['文件夹路径:','账单头标识符:','头-文件总数:','账单尾标识符:','尾-文件总数:','尾-文件总数:','账单尾标识符:']
        self.var1 = StringVar()
        self.var2 = StringVar()
        self.var4 = StringVar()
        self.var3 = StringVar()
        self.var5 = StringVar()
        EntryVar = [self.var1, self.var2, self.var4,self.var5,self.var3]

        for colone in range(3):
            coloneLable = Label(frame1,text = lablenames[colone])
            coloneLable.grid(row=1+colone, column=1, sticky=W)
            coltoEntry = Entry(frame1, textvariable=EntryVar[colone])
            coltoEntry.grid(row=1+colone, column=2, padx=5, pady=2)

        for coltwo in range(2):
            coltwolable = Label(frame1, text=lablenames[-1-coltwo])
            coltwolable.grid(row=2+coltwo, column=3, sticky=W)
            coltwoentry = Entry(frame1,textvariable = EntryVar[-1-coltwo])
            coltwoentry.grid(row=2+coltwo, column=4, padx=5)

        # 三个按钮布局
        ButtonList = ['选择文件夹','查询','导出结果']
        deflist = [self.DirSelect,self.SearchHR,self.SaveFile]

        for butrowone in range(3):
            if butrowone == 0:
                buttons = Button(frame1, text=ButtonList[butrowone], command=deflist[butrowone],padx=20)
                buttons.grid(row=1, column=3,sticky=W)
            else:
                buttons = Button(frame1, text=ButtonList[butrowone], command=deflist[butrowone],padx=(20 if butrowone==1 else 0 ))
                buttons.grid(row=1, column=4,padx=5,sticky=('W' if butrowone==1 else 'E'))

        # frame2 排版布局
        frame2 = frame(root,pady = 5,padx = 5)
        frame2.grid(row=2, column=1)

        scrollbar = Scrollbar(frame2)
        scrollbar.pack(side=RIGHT, fill=Y)
        self.ListBox = Listbox(frame2, width=80, height=30, yscrollcommand=scrollbar.set)
        self.ListBox.pack()
        scrollbar.config(command=self.ListBox.yview)

        root.mainloop()
    # 选择账单文件夹路径
    def DirSelect(self):
        self.DirSelectPath = askdirectory()
        self.var1.set(self.DirSelectPath.replace("/","\"))

    # 在账单中查找头尾的数量，判断头尾的唯一性
    def SearchHR(self):
        # openread = open('11.spc.bak','rb') # 16进制字符串文件
        # readf = openread.read()
        # readf1 = readf.decode().replace(' ','') # 去空格，字符串简单的替换速度快于re.sub
        # #readf1 = re.sub(' ','',readf.decode())
        # #print(readf1)
        #
        # readf1_b2a = binascii.unhexlify(readf1.encode()) # bin to ascii
        # print(readf1_b2a)
        THFC = 0
        TRFC = 0
        m = 0
        self.list = []
        self.ListBox.delete(0,END)
        if os.path.isdir(self.var1.get()):
            for root,dirs,files in os.walk(self.var1.get()):
                for self.name in files:
                    ''' -- endswith(suffix,start,end),suffix(后缀)可以是一个字符/字符串/元组，判断文件后缀，筛选出符合条件的文件
                        添加时间 -- 2020/10/18
                    '''
                    if self.name.endswith(('.txt','.spc')):
                        i = 1
                        m += i
                        #print(self.name)
                        Fname = os.path.join(root,self.name)
                        self.list.append(Fname)
                        #print(Fname)
                        OpenFile = open(Fname,"rb") # 图片账单文件比较大，必须使用rb格式打开，否则会丢失数据
                        ReadFile = OpenFile.read()
                        # python3.x严格要求格式，必须转成字符串类型.decode()
                        # binascii.hexlify() 数据转换成16进制效率高
                        # ' '.join(re.findall('..')) 16进制数据转成字符串后，设置每两个字节中间加一个空格，防止查找时匹配有问题(30A10A0A0A0A,如不加空格会取到3 0A)
                        TxtToHex = ' '.join(re.findall('..',binascii.hexlify(ReadFile).decode()))
                        #print(TxtToHex)
                        if self.var2.get() != "":
                            HFC = len(re.findall(' '.join(re.findall('..',self.var2.get().replace(' ',''))),TxtToHex,flags = re.I))
                        else:
                            HFC = 0
                        if self.var3.get() != "":
                            RFC = len(re.findall(' '.join(re.findall('..',self.var3.get().replace(' ',''))),TxtToHex,flags = re.I))
                        else:
                            RFC = 0
                        if HFC == RFC:
                            self.ListBox.insert(END,"文件名:" + self.name + "|" + "头个数:" + str(HFC) + "|" + "尾个数:" + str(RFC) + "n")
                        else:
                            self.ListBox.insert(END, "文件名:" + self.name + "|" + "头个数:" + str(HFC) + "|" + "尾个数:" + str(RFC) + "n")
                            self.ListBox.itemconfig(m-1,fg="red") #设置当前行的字体颜色
                        if HFC > 0:
                            THFC += i
                        if RFC > 0:
                            TRFC += i
                        OpenFile.close()
            self.ListBox.insert(0,"文件总数:" + str(m) + "n")
            self.ListBox.itemconfig(0, fg="blue")
            self.var4.set(str(THFC))
            self.var5.set(str(TRFC))
        else:
            self.ListBox.insert(END,"请选择正确的文件夹路径！！！" + "n")
            self.ListBox.itemconfig(0,fg="red")
    # 下期准备做记录中打开选择的文件
    # def WatchFile(self):
    #     try:
    #         print(self.list)
    #     except:
    #         self.ListBox.insert(END,"无有效文件，打不开" + "n")
    # 导出所有的查找记录
    def SaveFile(self):
        SaveFileName = asksaveasfilename(title='导出',defaultextension = '.xls')
        if SaveFileName != "":
            OpenSaveFile = open(SaveFileName,'w')
            for i in range(len(self.ListBox.get(0,END))):
                OpenSaveFile.write(self.ListBox.get(0,END)[i])
            OpenSaveFile.close()
TextToHex()