需求:根据列名提取整行数据并保存到excel表中(批量处理).
实现过程:用os.walk遍历目标文件夹,把文件路径与文件名以(.xls或.xlsx结尾)存储到数组中,而后遍历数组,筛选数据存储。
import pandas as pd
import os
dir_path = r'E:WorkTest360test'#excel所在文件夹路径
dir_path_save = r'E:WorkTest360test数据筛选\'#提取数据后excel存储文件夹路径
file_arr = []
for dirpath,dirnames,filenames in os.walk(dir_path):
for file in filenames:
temporary_arr = []
if file.endswith('.xls') or file.endswith('.xlsx'):
file_path = dirpath + '\' + file
temporary_arr.append(file_path)
temporary_arr.append(file)
file_arr.append(temporary_arr)
break
#循环遍历输出
for filedata in file_arr:
data = pd.read_excel(filedata[0])
pro_data = data.groupby('ACCESSPASS')
for i, j in pro_data:
new_file_path = (dir_path_save+filedata[1])
# j.to_excel(new_file_path,sheet_name=i,index=False)
if (i == '正确'):
j.to_excel(new_file_path)



