Python 导入分部分项前的 数据处理2

改进的地方：
以前是固定删除某几列，由于excel经常更换格式，现改为按照单元格是否含有中文来判断，因为编码那列是不含有中文的，
列的宽度自适应，方便查看数据，
参考的文章代码里面都有标注原文

import os
import openpyxl
from openpyxl import Workbook
from copy import deepcopy
from openpyxl.utils import get_column_letter


# 原文：
# https://www.cnblogs.com/liuda9495/p/9039732.html
# https://blog.csdn.net/gaifuxi9518/article/details/80575880
# https://blog.csdn.net/COCO56/article/details/84590544
# http://www.voidcn.com/article/p-aadcasvw-bst.html



fenBuName = '五分部'
dirName = './所有分部/' + fenBuName+ '/'


#workbook2 = Workbook()
workbook2 = openpyxl.load_workbook(fenBuName + '.xlsx')# 加载excel
workbook = None
worksheet = None
unit_name = None




def is_chinese(string):
    """
    检查整个字符串是否包含中文
    :param string: 需要检查的字符串
    :return: bool
    """
    if string is None:
        return False
    for ch in string:
        if u'u4e00' <= ch <= u'u9fff':
            return True
    return False
    
    


def each_files():    
    pathDir =  os.listdir(dirName)
    for index, value in enumerate(pathDir):
        filepath2 = dirName + value
        print(filepath2)
        each_sheet(filepath2)




def each_sheet(path):
    global workbook
    global worksheet
    
    workbook = openpyxl.load_workbook(path)# 加载excel
    name_list = workbook.sheetnames# 所有sheet的名字    
    for sheetname in name_list:
        print(sheetname)
        worksheet = workbook[sheetname]# 读取第一个工作表
        CellSplit()
        Business()




def CellSplit():
    
    # 获取所有 合并单元格的 位置信息
    # 是个可迭代对象，单个对象类型：openpyxl.worksheet.cell_range.CellRange
    # print后就是excel坐标信息
    m_list = worksheet.merged_cells

    l = deepcopy(m_list)# 深拷贝

    # 拆分合并的单元格 并填充内容
    for m_area in l:
        
        # 这里的行和列的起始值（索引），和Excel的一样，从1开始，并不是从0开始（注意）
        r1, r2, c1, c2 = m_area.min_row, m_area.max_row, m_area.min_col, m_area.max_col
            
        worksheet.unmerge_cells(start_row=r1, end_row=r2, start_column=c1, end_column=c2)
        # print('区域:', m_area, '  坐标:', r1, r2, c1, c2)
        
        # 获取一个单元格的内容
        first_value = worksheet.cell(r1, c1).value

        # 数据填充
        for r in range(r1, r2+1):# 遍历行        
            if c2 - c1 > 0:# 多个列，遍历列
                for c in range(c1, c2+1):
                    worksheet.cell(r, c).value = first_value
            else:# 一个列
                worksheet.cell(r, c1).value = first_value
    




def Business():# 特定的业务逻辑
    global worksheet2
    global workbook2
    global unit_name
    
    # 获取单位工程的名字
    unit_name = worksheet.cell(5, 1).value
    '''
    unit_name = worksheet.cell(2, 1).value
    nPos = unit_name.find('：')
    unit_name = unit_name[nPos+1:]
    '''    
    worksheet.title = unit_name# 改sheet的名字

    
    '''
    # 针对无单位工程的excel，这种情况先不考虑
    worksheet.insert_cols(1)# 插入列
    for index in range(worksheet.max_row):# 首列批量填充数据
        r = index+1
        worksheet.cell(r, 1).value = unit_name
    worksheet.cell(3, 1).value = '单位工程'# 单元格赋值
    '''

    # 删除行，根据不同的版本，删除不同的行
    # worksheet.delete_rows(4)
    # worksheet.delete_rows(2)
    # worksheet.delete_rows(1)

    cellValue_r2_c1 = worksheet.cell(2, 1).value
    if cellValue_r2_c1 == '单位工程':
        worksheet.delete_rows(3)
        worksheet.delete_rows(1)
        print('版本1')
    else:
        worksheet.delete_rows(4)
        worksheet.delete_rows(2)
        worksheet.delete_rows(1)
        print('版本2')


    # 删除列
    # worksheet.delete_cols(5)
    # worksheet.delete_cols(3)
    
    # 自动删除列
    max_column = worksheet.max_column# 提前把列的数量确定好，不然删除一个列后，数量就会变
    for i in range(max_column):
        cellValue = worksheet.cell(2, max_column-i).value # 2：代表第二行，10：代表总列数
        ret = is_chinese(cellValue)
        if ret == False:
            worksheet.delete_cols(max_column-i)


    worksheet2 = workbook2.create_sheet(unit_name)
    
    
    # excel赋值
    for x in range(worksheet.max_row):
        r = x+1
        for y in range(worksheet.max_column):
            c = y+1
            worksheet2.cell(r, c).value = worksheet.cell(r, c).value


    # 列宽度自适应
    for y in range(worksheet.max_column):
        column_width = 10
        for x in range(worksheet.max_row):
            c = y+1
            r = x+1
            cellLength = 10
            cellValue = worksheet.cell(r, c).value
            if cellValue is not None:
                cellLength = len(cellValue)
            if cellLength > column_
                column_width = cellLength
        column_NameEn = get_column_letter(y + 1)
        worksheet2.column_dimensions[column_NameEn].width = column_width * 2





each_files()
workbook2.save('./新的分部/'+fenBuName+'.xlsx')

目录结构