load_workbook(data_file_path, data_only=True)

"""
 pip install openpyxl
"""
from openpyxl import load_workbook
from openpyxl import Workbook
import os
import re

# 模板文件
TEMPLATE_FILE = r'H:\合并\合并模板.xlsx'
# 合并結(jié)果文件
RESULT_FILE = r'H:\合并\結(jié)果.xlsx'
# 數(shù)據(jù)文件目錄
DATA_ROOT_DIR = r"H:\合并"

# 文件名稱正則
DATA_FILE_REG = r"(.*?)-合同導(dǎo)入臺(tái)賬\d{8}.xlsx"


# 獲取要處理的文件
def get_deal_file_map():
    file_sn_map = {}
    fs = os.listdir(DATA_ROOT_DIR)
    for f in fs:
        match = re.match(DATA_FILE_REG, f)
        if match:
            city = match.group(1)
            sn = 2
            if city == '成都':
                sn = 4
            elif city == '杭州':
                sn = 3
            file_sn_map[os.path.join(DATA_ROOT_DIR, f)] = sn
    return file_sn_map


# 規(guī)范化列名
def get_normal_column_name(origin_col_name):
    if origin_col_name:
        start = origin_col_name.find("（")
        if start == -1:
            return origin_col_name.strip()
        else:
            return origin_col_name[0:start].strip()


# 獲取列名與列坐標(biāo)的映射
def get_col_name_coordinate_map(sheet_row):
    name_coor_map = {}
    for cell in sheet_row:
        # name_coor_map[get_normal_column_name(cell.value)] = cell.column_letter
        name_coor_map[get_normal_column_name(cell.value)] = cell.column
    return name_coor_map


# 獲取模板文件的列名與列坐標(biāo)映射
def get_template_name_coordinate_map(template_file_path):
    template_wbook = load_workbook(template_file_path)
    table = template_wbook[template_wbook.sheetnames[0]]
    row = table[1:1]
    return get_col_name_coordinate_map(row)


def deal_data_content():
    """
        合并文件內(nèi)容
    """
    dfile_sn_map = get_deal_file_map()
    save_book = Workbook()
    wsheet = save_book.active
    wsheet.title = 'merge-data'
    tmp_col_coor_map = get_template_name_coordinate_map(TEMPLATE_FILE)
    wsheet.append(list(tmp_col_coor_map.keys()))
    line = 2
    for data_file_path in dfile_sn_map.keys():
        sheet_num = dfile_sn_map[data_file_path]
        wbook = load_workbook(data_file_path, data_only=True)

        names = wbook.sheetnames

        for i in range(0, sheet_num):
            table = wbook[names[i]]
            row = table[1:1]
            data_col_coor_map = get_col_name_coordinate_map(row)
            use_col = data_col_coor_map.keys() & tmp_col_coor_map.keys()
            for row in table.iter_rows(min_row=2, values_only=True):
                rcol_index = data_col_coor_map['城市']
                city = row[rcol_index - 1]
                if (city is None) or len(city.strip()) == 0:
                    continue
                for col_name in use_col:
                    rcol_index = data_col_coor_map[col_name]
                    wcol_index = tmp_col_coor_map[col_name]
                    wsheet.cell(line, wcol_index, row[rcol_index - 1])
                line += 1
    save_book.save(RESULT_FILE)


if __name__ == '__main__':
    deal_data_content()

pd.concat(objs, axis=0, join='outer', join_axes=None, ignore_index=False,keys=None, levels=None, names=None,verify_integrity=False,copy=True)

# coding:utf-8
import pandas as pd

# 讀取指定文件的指定sheet
df1 = pd.read_excel(r'H:\merge\cd-contract-charge-1-20200807.xlsx', header=0, sheet_name=0)
df2 = pd.read_excel(r'H:\merge\cd-contract-charge-2-20200807.xlsx', header=0, sheet_name=1)
df3 = pd.read_excel(r'H:\merge\cd-contract-charge-3-20200807.xlsx', header=0, sheet_name=2)
df4 = pd.read_excel(r'H:\merge\hz-contract-charge-1-20200807.xlsx', header=0, sheet_name=0)
df5 = pd.read_excel(r'H:\merge\hz-contract-charge-2-20200807.xlsx', header=0, sheet_name=1)

# 按行拼接
data = pd.concat([df1, df2, df3, df4, df5], sort=False, ignore_index=True)

# 選擇需要的列
header = ['日期', '合同號(hào)', '城市', '姓名', 'charge']
data = data.loc[:, header]

# 將結(jié)果寫到值得excel文件
data.to_excel(r'H:\merge\result.xlsx', index=False)