python，比較兩個xml

實作的功能是從兩個xml讀取多個子節點和屬性，比較相同子節點是否相同，将不同的内容儲存生成csv檔案。

# -*- coding: UTF-8 -*-
#作用：查詢表一表二的不同内容，表1相對于表2 ，表2相對于表1
#data1生成名字的list2
from __future__ import division
import csv
import re
import os
import math
import sys
from bs4 import BeautifulSoup
from tkinter.filedialog import askopenfilename
import pandas as pd
#定義進度條
def progressbar(cur, total):
    percent = '{:.2%}'.format(cur / total)
    sys.stdout.write('\r')
    sys.stdout.write("[%-50s] %s" % ('=' * int(math.floor(cur *  / total)),
    percent))
    sys.stdout.flush()

print('第一份xml檔案')
filename1 = askopenfilename(filetypes=( ("Text file", "*.xml*"),("HTML files", "*.html;*.htm")))
print('第二份xml檔案')
filename2 = askopenfilename(filetypes=( ("Text file", "*.xml*"),("HTML files", "*.html;*.htm")))
print('進行中，大約20來秒，處理結果在D盤diff檔案夾内')
print('處理進度')
progressbar(, )

#建立檔案夾目錄
if(os.path.exists('D:\diff')):
    pass
else:
    os.mkdir("D:\diff")
#xml2csv 把xml檔案轉換成csv


header = ['Name', 'InitialValue', 'BachmannAddress', 'CalibrationExpression', 'IOInitialValue']

def parse_channel(tag):
    name = tag.find("Name")
    initial_value = tag.find("InitialValue")
    bachmann_address = tag.find("BachmannAddress")
    calibration_expression = tag.find("CalibrationExpression")
    io_initial_value = tag.find("IOInitialValue")
    return {
        "Name": name.text if name else "",
        "InitialValue": initial_value.text if initial_value else "",
        "BachmannAddress": bachmann_address.text if bachmann_address else "",
        "CalibrationExpression": calibration_expression.text if calibration_expression else "",
        "IOInitialValue": io_initial_value.text if io_initial_value else "",
    }

def dump_file(data_list, file_name):
    df = pd.DataFrame(data_list)
    # 去除空行
    df.dropna()
    # 去重
    df.drop_duplicates()
    #df.to_csv(file_name, index=False, header=header)
    df.to_csv(file_name, index=False, columns=header)

def xml2csv(input_file, output_file):
    raw_text = open(input_file,'rb').read()
    soup = BeautifulSoup(raw_text, "xml")
    data_list = [parse_channel(i) for i in soup.find("Channels").find_all("Channel")]
    dump_file(data_list=data_list, file_name=output_file)

# xml2csv(input_file="raw.xml", output_file="post.csv")

def zhaozuzhi(a,b): #a是多的那一個，b是少的
    t=[]
    for i in range(len(a)):
        for j in b:
            if a[i][]==j:
                t.append([a[i]])
    return t
#從三個清單中依次讀取第一個存入一行存入一個list  形成name，data1，data2的模樣
def walk_list(a,b,c):
    list=[]
    for i in range(len(a)):
        list.append([a[i],b[i],c[i]])
    return list
#将xml轉換成csv
xml2csv(input_file=filename1, output_file="D:/data1.csv")
xml2csv(input_file=filename2, output_file="D:/data2.csv")
#讀取第一個csv，生成以name名字為元素的list2
progressbar(, )
with open('D:\data1.csv','r') as f:
    readers1=csv.reader(f)
    list1=[row for row in readers1]
    list2=[]
    for i in range(len(list1)):
        list2.append(list1[i][])
#讀取第二個csv，生成以name名字為元素的list4
progressbar(, )
with open('D:\data2.csv','r') as f1:
    readers1=csv.reader(f1)
    list3=[row for row in readers1]
    list4=[]
    for j in range(len(list3)):
        list4.append(list3[j][])
progressbar(, )
# list2有，list4沒有，即為，data1有，data2沒有的 減少的
ret1 = [i for i in list2 if i not in list4]
# list4沒有，list2有，即為，data1沒有，data2有，增加的
ret2 = [i for i in list4 if i not in list2]
#list2有，list4也有，即為相同的部分
ret3=[i for i in list2 if i in list4]
#a11 是list1相同部分大list，b11是相同部分大list
file = open('D:\diff/ret1.txt', 'w')
for i in  ret1:
    file.write(str(i) +','+ '\n')
file.close()
file = open('D:\diff/ret2.txt', 'w')
for i in  ret2:
    file.write(str(i) +','+ '\n')
file.close()
a11=zhaozuzhi(list1,ret3)
b11=zhaozuzhi(list3,ret3)
file = open('D:\diff/temp1.txt', 'w')
for i in  a11:
    file.write(str(i) +','+ '\n')
file.close()
file = open('D:\diff/temp2.txt', 'w')
for i in  b11:
    file.write(str(i) +','+ '\n')
file.close()
lines=open('D:\diff/temp1.txt').readlines()
fp=open('D:\diff/temp1.csv', 'w')
for s in lines:
       fp.write( s.replace('[[','').replace(']]',''))   # replace是替換，write是寫入
fp.close()  # 關閉檔案
progressbar(, )
lines=open('D:\diff/temp2.txt').readlines()
fp=open('D:\diff/temp2.csv', 'w')
for s in lines:
       fp.write( s.replace('[[','').replace(']]',''))   # replace是替換，write是寫入
fp.close()  # 關閉檔案
with open('D:\diff/temp1.csv','r') as f:
    readers1=csv.reader(f)
    a11=[row for row in readers1]
    #print(list1)
    # list2=[]
    # for i in range(len(list1)):
    #     list2.append(list1[i][0])
with open('D:\diff/temp2.csv','r') as f:
    readers1=csv.reader(f)
    b11=[row for row in readers1]
    #print(list2)
# print(len(a11))
# print(len(b11))
#四個name,空清單,用來放找出不同的name
name1=[]
name2=[]
name3=[]
name4=[]
#寫initiavalue，形成一個txt，讀的内容不對，讀的内容應該是表以表2的相同部分
progressbar(, )
initiavalue1=[]
initiavalue2=[]
for z in range(len(a11)):
        if a11[z][]!=b11[z][]:
            name1.append(a11[z][])
            initiavalue1.append(a11[z][])
            initiavalue2.append(b11[z][])
a=walk_list(name1,initiavalue1,initiavalue2)
file = open('D:\diff/initiavalue.txt', 'w')
for i in  a:
    file.write(str(i) +','+ '\n')
file.close()
lines=open('D:\diff/initiavalue.txt').readlines()
fp=open('D:\diff/initiavalue.csv', 'w')
for s in lines:
       fp.write( s.replace('[','').replace(']',''))   # replace是替換，write是寫入
fp.close()  # 關閉檔案
##寫BachmannAddress，形成一個txt
BachmannAddress1=[]
BachmannAddress2=[]
for i in range(len(a11)):
        if a11[i][]!=b11[i][]:
            name2.append(str(a11[i][]))
            BachmannAddress1.append(str(a11[i][]))
            BachmannAddress2.append(str(b11[i][]))
b=walk_list(name2,BachmannAddress1,BachmannAddress2)
file = open('D:\diff/BachmannAddress.txt', 'w')
for i in  b:
    file.write(str(i) +','+ '\n')
file.close()
lines=open('D:\diff/BachmannAddress.txt').readlines()
fp=open('D:\diff/BachmannAddress.csv', 'w')
for s in lines:
       fp.write( s.replace('[','').replace(']',''))   # replace是替換，write是寫入
fp.close()  # 關閉檔案
# #寫CalibrationExpression，形成一個txt
CalibrationExpression1=[]
CalibrationExpression2=[]
for i in range(len(a11)):
        if a11[i][]!=b11[i][]:
            name3.append(str(a11[i][]))
            CalibrationExpression1.append(str(a11[i][]))
            CalibrationExpression2.append(str(b11[i][]))
c=walk_list(name3,CalibrationExpression1,CalibrationExpression2)
file = open('D:\diff/CalibrationExpression.txt', 'w')
for i in  c:
    file.write(str(i) +','+ '\n')
file.close()
lines=open('D:\diff/CalibrationExpression.txt').readlines()
fp=open('D:\diff/CalibrationExpression.csv', 'w')
for s in lines:
       fp.write( s.replace('[','').replace(']',''))   # replace是替換，write是寫入
fp.close()  # 關閉檔案
#寫IOInitialValue，形成一個txt
try:
    IOInitialValue1=[]
    IOInitialValue2=[]
    for i in range(len(a11)):
            if a11[i][]!=b11[i][]:
                name4.append(a11[i][])
                IOInitialValue1.append(str(a11[i][]))
                IOInitialValue2.append(str(b11[i][]))
    d=walk_list(name4,IOInitialValue1,IOInitialValue2)
    file = open('D:\diff/IOInitialValue.txt', 'w')
    for i in  d:
        file.write(str(i) +','+ '\n')
    file.close()
    lines=open('D:\diff/IOInitialValue.txt').readlines()
    fp=open('D:\diff/IOInitialValue.csv', 'w')
    for s in lines:
           fp.write( s.replace('[','').replace(']',''))   # replace是替換，write是寫入
    fp.close()  # 關閉檔案
except IndexError as e:
    pass
os.remove('D:\diff/temp1.txt')
os.remove('D:\diff/temp1.csv')
os.remove('D:\diff/temp2.txt')
os.remove('D:\diff/temp2.csv')
os.remove('D:\diff/initiavalue.txt')
os.remove('D:\diff/BachmannAddress.txt')
os.remove('D:\diff/CalibrationExpression.txt')
os.remove('D:\diff/IOInitialValue.txt')
os.remove('D:/data1.csv')
os.remove('D:/data2.csv')
progressbar(,)