使用Python快速打开一个百万行级别的超大Excel文件的方法

>>> from openpyxl import Workbook
>>> wb = Workbook()
>>> sh = wb.active
>>> sh.append(['id', '语文', '数学', '英语', '物理'])
>>> for i in range(1000000): # 写入100万行数据
	sh.append([i+1, 90, 100, 95, 99])

	
>>> wb.save(r'd:\bigxlsx.xlsx')
>>> import os
>>> os.path.getsize(r'd:\bigxlsx.xlsx') # 文件大小：20M字节
20230528

>>> from openpyxl import load_workbook
>>> import time
>>> def read_xlsx(read_only):
	t0 = time.time()
	wb = load_workbook(r'd:\bigxlsx.xlsx', read_only=read_only)
	t1 = time.time()
	print(wb.sheetnames)
	print(sh.cell(row=1, column=1).value)
	print(sh.cell(row=100, column=3).value)
	print('耗时%0.3f秒钟'%(t1-t0))

	
>>> read_xlsx(True)
['Sheet']
id
100
耗时0.404秒钟
>>> read_xlsx(False)
['Sheet']
id
100
耗时67.817秒钟

>>> import pandas as pd
>>> def read_excel_by_pandas():	
	with open(r'd:\bigxlsx.xlsx', 'rb') as fp:
		content = fp.read()
		t0 = time.time()
		df = pd.read_excel(content, engine='openpyxl')
		t1 = time.time()
	print(df.head())
	print(df.tail())
	print('耗时%0.3f秒钟'%(t1-t0))

	
>>> read_excel_by_pandas()
  id 语文  数学 英语 物理
0  1 90 100 95 99
1  2 90 100 95 99
2  3 90 100 95 99
3  4 90 100 95 99
4  5 90 100 95 99
       id 语文  数学 英语 物理
999995  999996 90 100 95 99
999996  999997 90 100 95 99
999997  999998 90 100 95 99
999998  999999 90 100 95 99
999999 1000000 90 100 95 99
耗时81.369秒钟