1
我需要在Excel工作表中搜索包含某些模式的单元格。这需要比我能处理更多的时间。下面是我可以编写的最优化的代码。由于数据模式通常是一排一排,所以我使用iter_rows(row_offset = x)。不幸的是,下面的代码在循环的每个循环中发现给定模式的次数越来越多(从毫秒开始并快到几分钟)。我究竟做错了什么?Openpyxl优化单元搜索速度
import openpyxl
import datetime
from openpyxl import Workbook
wb = Workbook()
ws = wb.active
ws.title = "test_sheet"
print("Generating quite big excel file")
for i in range(1,10000):
for j in range(1,20):
ws.cell(row = i, column = j).value = "Cell[{},{}]".format(i,j)
print("Saving test excel file")
wb.save('test.xlsx')
def FindXlCell(search_str, last_r):
t = datetime.datetime.utcnow()
for row in ws.iter_rows(row_offset=last_r):
for cell in row:
if (search_str == cell.value):
print(search_str, last_r, cell.row, datetime.datetime.utcnow() - t)
last_r = cell.row
return last_r
print("record not found ",search_str, datetime.datetime.utcnow() - t)
return 1
wb = openpyxl.load_workbook("test.xlsx", data_only=True)
t = datetime.datetime.utcnow()
ws = wb["test_sheet"]
last_row = 1
print("Parsing excel file in a loop for 3 cells")
for i in range(1,100,1):
last_row = FindXlCell("Cell[0,0]", last_row)
last_row = FindXlCell("Cell[1000,6]", last_row)
last_row = FindXlCell("Cell[6000,6]", last_row)