工具: jupyter
代码:
#合并csv文件并保存为xlsx格式文件
import pandas as pd
import glob
csv_list = glob.glob(‘C:\Users\dell\Desktop\月销\*.csv’)#读取csv文件路径
print(u’共发现%s个CSV文件’% len(csv_list))
print(u’正在处理…’)
out_file = ‘C:\Users\dell\Desktop\月销\hebing2.xlsx’#设置保存文件路径和名称,可以保存为xlsx和csv格式
for i in csv_list:
fr = open(i,‘r’,encoding=‘utf-8’).read()
with open(out_file,‘a’,encoding=‘utf-8’) as f:
f.write(fr)
print(u’合并完毕!’)
#去重
df = pd.read_csv(out_file,header=0,encoding = ‘utf-8’)
datalist = df.drop_duplicates()
datalist.to_excel(out_file)
print(u’完成去重’)