xlrd, xlwt read and write excel combat

xlrd, xlwt read and write excel combat

Actual combat background

The requirement is given to an excel, and there are two columns (one is a major key and a small value) that need to be logically output. One of the major categories corresponds to multiple subcategories and involves the merge operation of excle. The processed target data is similar to json format: {'big category': {small category 1:, small category 2:}}. If the processed data is in a large category or a small category does not exist, mark the row corresponding to excel in red (the large category exists and the small category value is empty, etc.)

Code

import xlrd
import main
import xlwt
#返回合并excel信息
def merge_cell(sheet_info):
    '''
    #handle Merge transverse cells and handle Merge Vertical Cells, assign empty cells,
    :param rlow:row, include row exclusive of row_range
    :param rhigh:row_range
    :param clow:col, include col exclusive of col_range
    :param chigh:col_range
    :param sheet_info:object of sheet
    :return:dic contain all of empty cells value
    '''
    merge = {}
    merge_cells = sheet_info.merged_cells
    for (rlow, rhigh, clow, chigh) in merge_cells:#起始行，结束行，起始列，结束列
        value_mg_cell = sheet_info.cell_value(rlow, clow)
        if rhigh-rlow == 1:
            # Merge transverse cells
            for n in range(chigh-clow-1):
                merge[(rlow, clow+n+1)] = value_mg_cell
        elif chigh-clow == 1:
            # Merge Vertical Cells
            for n in range(rhigh-rlow-1):
                merge[(rlow+n+1, clow)] = value_mg_cell
    return merge

def list_dic(list1,list2):
    '''
    two lists merge a dict,a list as key,other list as value
    :param list1:key
    :param list2:value
    :return:dict
    '''
    dic = dict(map(lambda x,y:[x,y], list1,list2))
    return dic

def read_excle(filename):
    '''
    读excle
    :param filename: 文件所在路径
    :return: apply_dic;每一行作为一个字典形如：{'列名'：value}；结果形如：[[{}],[{}]]
    '''
    apply_dic = []
    with xlrd.open_workbook(filename,formatting_info=True) as workbook:
        name_sheets = workbook.sheet_names()  # 获取Excel的sheet表列表，存储是sheet表名
        for index in name_sheets:  # for 循环读取每一个sheet表的内容
            sheet_info = workbook.sheet_by_name(index)  # 根据表名获取表中的所有内容，sheet_info也是列表，列表中的值是每个单元格里值
            first_line = sheet_info.row_values(0)  # 获取首行，我这里的首行是表头，我打算用表头作为字典的key，每一行数据对应表头的value，每一行组成一个字典
            values_merge_cell = merge_cell(sheet_info)  # 这里是调用处理合并单元格的函数
            for i in range(1, sheet_info.nrows):  # 开始为组成字典准备数据
                other_line = sheet_info.row_values(i)
                for key in values_merge_cell.keys():
                    if key[0] == i:
                        other_line[key[1]] = values_merge_cell[key]
                # print(other_line)
                dic = list_dic(first_line, other_line)  # 调用组合字典的函数，传入key和value，字典生成
                apply_dic.append(dic)
            return apply_dic
def compare_dic(key,value,dic):
    #判断大类是否存在目标字典:0-大类不存在；1-小类不存在；2小类为空；3小类有值
    if key in dic.keys():
        #判断小类是否存在字典
        # if value in (dic.values())[key].keys():
        if value in dic[key]:
            #判断小类是否为：'',None
            if str(dic[key][value]).strip()=='' or dic[key][value]==None:
                #值为空
                return 2
            else:
                return 3#有值
        else:
            #小类不存在
            return 1
    else:
        #key不存在目标字典
        return 0

def write_excle(filename,filename1,dic):
    #8 through 63. 0 = Black, 1 = White, 2 = Red, 3 = Green, 4 = Blue, 5 = Yellow, 6 = Magenta, 7 = Cyan, 16 = Maroon, 17 = Dark Green, 18 = Dark Blue, 19 = Dark Yellow , almost brown), 20 = Dark Magenta, 21 = Teal, 22 = Light Gray, 23 = Dark Gray, the list goes on
    # 创建一个workbook 设置编码
    workbook = xlwt.Workbook(encoding='utf-8')
    # 创建一个worksheet# 创建一个workbook 设置编码
    worksheet = workbook.add_sheet('My Worksheet',cell_overwrite_ok=True)  # 表名
    # 写入excel
    # 参数对应 行, 列, 值
    pattern = xlwt.Pattern()  # Create the Pattern
    pattern.pattern = xlwt.Pattern.SOLID_PATTERN  # May be: NO_PATTERN, SOLID_PATTERN, or 0x00 through 0x12
    pattern.pattern_fore_colour = 2
    # May be: 8 through 63. 0 = Black, 1 = White, 2 = Red, 3 = Green, 4 = Blue, 5 = Yellow, 6 = Magenta, 7 = Cyan, 16 = Maroon, 17 = Dark Green, 18 = Dark Blue, 19 = Dark Yellow , almost brown), 20 = Dark Magenta, 21 = Teal, 22 = Light Gray, 23 = Dark Gray, the list goes on...
    style = xlwt.XFStyle()  # Create the Pattern
    style.pattern = pattern  # Add Pattern to Style
    apply_dic=read_excle(filename)
    for i in range(len(apply_dic)):
        for j in range(len(apply_dic[i])):
            worksheet.write(0, j, tuple(apply_dic[i].keys())[j])#写表头
            key=apply_dic[i]['英文分类'].strip()
            value=apply_dic[i]['字段key'].strip()
            comparedic=compare_dic(key,value,dic)
            print(key)
            print(value)
            print(comparedic)
            #大类存在，小类有值
            if comparedic ==3:
                worksheet.write(i + 1, j, tuple(apply_dic[i].values())[j])  # 表格内容
            #大类存在，小类不存在 或者大类不存在
            elif comparedic ==0 or comparedic==1:

                worksheet.write(i + 1, j, tuple(apply_dic[i].values())[j],style)
            else:
                worksheet.write(i + 1, j, tuple(apply_dic[i].values())[j])
            #判断大类是否存在目标字典:0-大类不存在；1-小类不存在；2小类为空；3小类有值


    workbook.save(filename1)
    # 保存

if __name__=='__main__':
    filename=f'{main.BASE_DIR}/dataCenter/IDFY对接新增输入项0424版.xls'
    filename1 = f'{main.BASE_DIR}/dataCenter/IDFY对接新增输入项0424版1.xls'
    from dataCenter.compare_data import comare_data#引入实际json格式数据
    write_excle(filename, filename1, comare_data)

effect

slightly