python xlsx 大文件_用python处理大型XLSX文件

就这样，我找到了解决办法。最快的方法来读取xlsx表。

56mb文件，超过500k行和4张纸，用了6s才继续。import zipfile

from bs4 import BeautifulSoup

paths = []

mySheet = 'Sheet Name'

filename = 'xlfile.xlsx'

file = zipfile.ZipFile(filename, "r")

for name in file.namelist():

if name == 'xl/workbook.xml':

data = BeautifulSoup(file.read(name), 'html.parser')

sheets = data.find_all('sheet')

for sheet in sheets:

paths.append([sheet.get('name'), 'xl/worksheets/sheet' + str(sheet.get('sheetid')) + '.xml'])

for path in paths:

if path[0] == mySheet:

with file.open(path[1]) as reader:

for row in reader:

print(row) ## do what ever you want with your data

reader.close()

享受和快乐的编码。