汇总zip文件,压缩包的每个文件格式一模一样
from zipfile import ZipFile
import pandas as pd
import os
# 打开文件
path = r"C:UsersAdministratorDesktopdownloadoutput" # 对应文件夹的路径
dirs = os.listdir(path)
# 输出所有文件名字
df_list = []
for file in dirs:
myzip = ZipFile(r'C:UsersAdministratorDesktopdownloadoutput{}'.format(file))
# print(myzip.filename) # 返回该目录下的zip的文件名
for ii in myzip.namelist(): # 返回对应解压后的文件名
f = myzip.open(r'{}'.format(ii))
df = pd.read_table(f, sep='t',header=None)
df_list.append(df)
df_all = pd.concat(df_list,axis=0)
df_all.columns = ["日期","类型","网址","pv","uv"] # 设置列名
# pandas在写入excel是会对链接形式的数据(http或者https类型)有一个检测和长度的限制,一般是255
writer = pd.ExcelWriter(r'C:UsersAdministratorDesktop汇总.xlsx', engine='xlsxwriter', options={'strings_to_urls': False})
df_all.to_excel(writer,index = False)
writer.save()
writer.close()