请大神帮忙调一下程序 DEBUG没走通 请反馈源代码非常感谢 代码如下:
#载入需要的库
import os
import pandas as pd
import glob
#excel转化为csv
def xlsx_to_csv_pd():
c=os.getcwd()
excel_list1=glob.glob('*.xls')
excel_list2=glob.glob('*.xlsx')
for a in excel_list1:
data_xls = pd.read_excel(a, index_col=0)
outfile=c+"/"+a
data_xls.to_csv(outfile, encoding='utf-8')
for b in excel_list2:
data_xls = pd.read_excel(b, index_col=0)
outfile=c+"/"+b
data_xls.to_csv(outfile, encoding='utf-8')
定义函数hebing
def hebing():
csv_list = glob.glob('*.csv') # 查看同文件夹下的csv文件数
print(u'共发现%s个CSV文件' % len(csv_list))
print(u'正在处理............')
for i in csv_list: # 循环读取同文件夹下的csv文件
fr = open(i, 'r').read()
with open('result.csv', 'rb') as f: # 将结果保存为result.csv
f.write(fr)
print(u'合并完毕!')
定义函数quchong(file),将重复的内容去掉,主要是去表头
def quchong(file):
df = pd.read_csv(file, header=0)
datalist = df.drop_duplicates()
datalist.to_csv(file)
#运行函数
if name == '__main__':
xlsx_to_csv_pd()
print("转化完成!!!" )
hebing()
quchong("result.csv")
print("已完成数据文件合并清单所处位置:"+str(file))