python使用openpyxl操作excel表格

#!Linux path：/usr/bin/env python3
# -*- coding: utf-8 -*-
from openpyxl import Workbook
from openpyxl import load_workbook
from sys import argv
from urllib.request import urlopen
import os
import warnings
import sys

inputdir = argv[1] #argv[1] #r"D:\8to9" #argv[1]  输入路径
outputdir = argv[2] #r"F:\pythonDemo\8to9\test\output" #argv[2]  输出路径

def split_file():
# 判断版本是否匹配
html = urlopen('***********')
strl = str(html.read())
print(strl)
if not '20171103' in strl:
sys.exit(0)
print("校验正确")

# 获取映射文件和输出模版(和python文件同级)
path = os.path.abspath('.')
excel_files = os.listdir()
tempExcels = {}
map_excel = None
for excel in excel_files:

if not excel.startswith("input_8to9_") and not excel == "数据库列标题映射.xlsx":
continue

if excel == '数据库列标题映射.xlsx':
template = path + '/' + excel
print("映射文件路径：" + template)
map_excel = load_workbook(filename=template)
else:
excelpath = path + '/' + excel
# print("输出模版路径：" + excelpath)
excelwork = load_workbook(filename=path + "/" + excel)
tempExcels[excel] = excelwork

excel_files1 = os.listdir(inputdir)
for k in excel_files1:
print(k)
for excel in excel_files1:

if excel == 'input_step4_计算输入文件.xlsx':

print("loading file...")
warnings.simplefilter("ignore")
read_excel = load_workbook(filename = inputdir + "/" + excel)

sheets = read_excel.get_sheet_names()
sheet = read_excel.get_sheet_by_name(sheets[0])

mapsheet = map_excel.get_sheet_by_name("Sheet1")

sheetNames = ['电力','工业锅炉','钢铁','平板玻璃','石油化工','焦化','其他建材','冶金','食品轻纺及其他','堆场','储罐','装载','泄漏','喷涂']

sheetAndColumnIn = {} # 输入文件的sheet和列     #{'电力':83,'工业锅炉':84}
sheetAndColumnAll = {} # 输入文件的sheet和列 全部

sheetAndColumnMap = {} # 映射文件的sheet和列       #{"储罐": 3, "电力": 4}

sheetAndRowDict = {} # 模版文件的sheet和行映射

headerMap = {} # 映射文件的标题映射

# 初始化sheetAndColumnIn
for i in range(1,sheet.max_column+1):
s = sheet.cell(row= 2,column=i).value
if s in sheetNames:
sheetAndColumnIn[s] = i
# print(sheetAndColumnIn)

# 初始化sheetAndColumnAll
for i in range(1,sheet.max_column+1):
s = sheet.cell(row= 1,column=i).value
sheetAndColumnAll[s] = i
# print(sheetAndColumnAll)

# 初始化sheetAndRowDict
for i in sheetNames:
excel1 = tempExcels.get("input_8to9_"+ i + ".xlsx")
sheets = excel1.get_sheet_names()
sheet1 = excel1.get_sheet_by_name(sheets[0])
row = sheet1.max_row
sheetAndRowDict[i] = row

# # 初始化映射文件标题字典（中文为健）
for i in range(1,mapsheet.max_column+1):
s = mapsheet.cell(row= 1,column=i).value
if s in sheetNames:
sheetAndColumnMap[s] = i
# print(sheetAndColumnMap)
for i in sheetNames:
temp = {}
for j in range(2, mapsheet.max_row + 1):
c = sheetAndColumnMap[i]
k = mapsheet.cell(row=j,column=1).value
v = mapsheet.cell(row=j, column=c).value
if v :
if k:
temp[k]= v
headerMap[i] = temp

# 输出文件映射列
outWorkMap = {}
for index in sheetNames:
temp = {}
excel2 = tempExcels.get("input_8to9_"+ index +".xlsx")

sheets = excel2.get_sheet_names()
sheet2 = excel2.get_sheet_by_name(sheets[0])

for i in range(1, sheet2.max_column+1):
v = sheet2.cell(row=1,column=i).value
if v:
temp[v] = i
outWorkMap[index] = temp

# 遍历全部数据len(sheetNames)次，重复分配
print("insert data...")
print(sheet.max_row)
for i in sheetNames:
temp = headerMap.get(i) # 原值：新值
list = temp.keys() # 原值
outMap = outWorkMap.get(i) # 新值：列
for l in range(3,sheet.max_row+1):
colnum = sheetAndColumnIn.get(i)
v = sheet.cell(row=l, column=colnum).value
if v == '1' or v == 1:

index = sheetAndRowDict[i] + 1
sheetAndRowDict[i] = index
wb = tempExcels["input_8to9_"+ i +".xlsx"]

sheets = wb.get_sheet_names()
temp_sheet = wb.get_sheet_by_name(sheets[0])

#   插入一条数据
for m in list:
colnum1 = sheetAndColumnAll.get(m)
if colnum1 == None:
# print("映射文件和input文件"+ i + m + "字段不匹配")
continue
v = sheet.cell(row = l,column= colnum1).value
row = sheetAndRowDict.get(i)
# 通过m获取模版表中的标题，通过标题获取列号
colnum2 = outMap.get(temp.get(m))
if colnum2 == None:
# print( "映射文件和模版文件"+ i + m + "字段不匹配")
continue
temp_sheet.cell(row = row,column = colnum2,value = v)

print(i + " 数据插入成功")

print("save file...")
for index in sheetNames:
tempExcels["input_8to9_"+ index +".xlsx"].save(outputdir + "/" + "output_8to9" + '_' + index + '.xlsx')

print("succefully!")
return 0

if __name__ == "__main__":
split_file()