python_合并列名不完全相同的Excel文件
意思就是两个文件有相同的列名，但是列数不同

from openpyxl import *
import xlrd
import xlwt
import pandas as pd
import csv
import os
# 合并表
from utils.read_write import eachFile, writeOneCSV, writeCSV, readCsv

# 子表

# wb2=load_workbook(fileName)
# #获取sheet
# table=wb2.get_sheet_by_name('Sheet1')
# #获取行列数
# rows=table.max_row
# cols=table.max_column
# #获取第一行单元格的值
# rowdata=[]
# for i in range(1,cols+1):
#     cellvalue=table.cell(row=rows,column=i).value
#     rowdata.append(cellvalue)

class excel():
    def __init__(self, file):
        self.file = file
        self.wb = load_workbook(self.file)
        sheets = self.wb.get_sheet_names()
        self.sheet = sheets[0]
        self.ws = self.wb[self.sheet]

    # 获取表格的总行数和总列数
    def getRowsClosNum(self):
        rows = self.ws.max_row
        columns = self.ws.max_column
        return rows, columns
        # 获取某个单元格的值

    def getCellValue(self, row, column):
        cellvalue = self.ws.cell(row=row, column=column).value
        return cellvalue

        # 获取某列的所有值

    def getColValues(self, column):
        rows = self.ws.max_row
        columndata = []
        for i in range(1, rows + 1):
            cellvalue = self.ws.cell(row=i, column=column).value
            columndata.append(cellvalue)
        return columndata
        # 获取某行所有值

    def getRowValues(self, row):
        columns = self.ws.max_column
        rowdata = []
        for i in range(1, columns + 1):
            cellvalue = self.ws.cell(row=row, column=i).value
            rowdata.append(cellvalue)
        return rowdata

    # 写入值
    def writeCellValue(self, readCellvalue):
        sheetActive = self.wb.active
        rows = sheetActive.max_row + 1
        column = sheetActive.max_column + 1
        # for data_cell in range(1,rows):
        #             # sheetActive.cell(rows=rows,column=data_cell,value=readCellvalue)
        #             sheetActive.cell(row=rows,column=data_cell,value=readCellvalue)
        #             self.wb.save(fileName)
        sheetActive.cell(row=rows, column=column, value=readCellvalue)
        self.wb.save(fileName)

    # def writeCellValue2(self,readCellvalue,cloumn_k):
    #     sheetActive=self.wb.active
    #     rows = sheetActive.max_row+1
    #     column=sheetActive.max_column+1
    #     # for data_cell in range(1,rows):
    #     #             # sheetActive.cell(rows=rows,column=data_cell,value=readCellvalue)
    #     #             sheetActive.cell(row=rows,column=data_cell,value=readCellvalue)
    #     #             self.wb.save(fileName)
    #     sheetActive.cell(row=1,column=cloumn_k+1,value=readCellvalue)
    #     self.wb.save(fileName)
    #     return cloumn_k


class subexcel():
    def __init__(self, subfile):
        self.subfile = subfile
        self.book = xlrd.open_workbook(self.subfile)
        sheets = self.book.sheet_by_index(0)
        self.sheets = sheets

    # 获取总行数和总列数
    def getRowsClosNum(self):
        rows = self.sheets.nrows
        colums = self.sheets.ncols
        return rows

    # 获取单元格的值
    def getCellValue(self, row, column):
        cellvalue = self.sheets.cell_value(rowx=row, colx=column)
        return cellvalue

    # 获取某行的值
    def getRowValues(self, row):
        row_value = self.sheets.row_values(row)
        return row_value

    # 获取某列的值
    def getColValues(self, column):
        col_value = self.sheets.col_values(column, 2)
        return col_value


def mergeCsv(src,writeFile):
    files = eachFile(src)
    for file in files:
        subfileName = src + file
        excelOne = readCsv(subfileName)
        rows = len(excelOne)
        # 遍历89列
        listTwo =[]
        for n in range(1,rows):
            listTwo.append(excelOne[n])
        writeCSV(listTwo,writeFile)


def merge(src,writeFile):
    files = eachFile(src)
    for file in files:
        subfileName = src + file
        excelOne = subexcel(subfileName)
        sub_title = excelOne.getRowValues(2)
        rows = excelOne.getRowsClosNum()
        # 遍历89列
        listTwo =[]
        combine = []
        # ！！！关键在此，记录在1文件中和2文件相同的列序数
        for i in range(0, len(sub_title)):
            for k in range(0, len(combine_title)):
                if combine_title[k] == sub_title[i]:
                    combine.append(k)
        for n in range(3,rows):
            list = []
            for m in range(0,61):
                if m in combine:
                    col_value = excelOne.getCellValue(n,combine.index(m))
                    if isinstance(col_value,str):
                        col_value = col_value.replace('\n','').replace('\ue5e5','').replace('\ue2e8','').replace('\ue134','').replace('\ue128','').replace('\ue3b8','').replace('\ue370','')
                        list.append(col_value)
                    else:
                        list.append(col_value)
                else:
                    list.append(0)
            listTwo.append(list)
        writeCSV(listTwo,writeFile)

def mergeSame(src,writeFile):
    files = eachFile(src)
    for file in files:
        subfileName = src + file
        excelOne = subexcel(subfileName)
        # sub_title = excelOne.getRowValues(2)
        rows = excelOne.getRowsClosNum()
        # 遍历89列
        listTwo =[]
        for n in range(3,rows):
            list = []
            for m in range(0,61):
                col_value = excelOne.getCellValue(n,m)
                if isinstance(col_value,str):
                    col_value = col_value.replace('\n','').replace('\ue5e5','').replace('\ue2e8','').replace('\ue134','').replace('\ue128','').replace('\ue3b8','').replace('\ue370','')
                    list.append(col_value)
                else:
                    list.append(col_value)
            listTwo.append(list)
        writeCSV(listTwo,writeFile)

def getAllFile():

    src = 'C:\\Users\2019年\\all\\'

    mergeSame(src,'数据.csv')

def writeWrong():
    fileDir =  'D'
    data = readCsv(fileDir)
    writeCSV(data,'luanma.csv')

if __name__ == "__main__":
    # writeWrong()
    fileName = r'D:\projec.xlsx'
    # 89列
    list1 = excel(fileName).getRowValues(2)
    combine_title = list(filter(None, list1))
    writeOneCSV(combine_title, '人口数据.csv')
    # writeOneCSV(combine_title, 'wrong.csv')
    getAllFile()