试了pandas,to_csvd的时候只有最后一个excel的内容,应该是被覆盖掉了,只有最后一个读取文件的内容
代码如下,求大佬帮忙修改一下
import pandas as pd
import os
#判断后缀名
def endwith(s,*endstring):
array=map(s.endswith,endstring)
if True in array:
return True
else:
return False
#分析文件夹C:\\Users\\JacyJam\\Desktop\\中标企业信息\\
log_directory='C:\\Users\\JacyJam\\Desktop\\企业供应商清洗名单\\Data\\DATA\\结构统一'
logFiles=os.listdir(log_directory)
milligram_df2=pd.DataFrame()
#在文件夹C:\\Users\\JacyJam\\Desktop\\中标企业信息\\遍历
for filename in logFiles:
if endwith(filename, '.xlsx') or \
endwith(filename, '.xls'):
filePath = log_directory + '/' + filename
data = pd.read_excel(filePath)
pd.set_option('max_rows', None)
pd.set_option('max_colwidth', 10000)
# 获取以 "_num" 结尾的各列数据
col_names = data.columns.tolist()
milligram_columns = []
for items in col_names:
if items.endswith("供应商名称") :
milligram_columns.append(items)
milligram_df2=data[milligram_columns]
milligram_df2.to_csv('out.csv',encoding='utf_8_sig',header=0)
print(milligram_df2)
print(filename)
代码如下,求大佬帮忙修改一下
import pandas as pd
import os
#判断后缀名
def endwith(s,*endstring):
array=map(s.endswith,endstring)
if True in array:
return True
else:
return False
#分析文件夹C:\\Users\\JacyJam\\Desktop\\中标企业信息\\
log_directory='C:\\Users\\JacyJam\\Desktop\\企业供应商清洗名单\\Data\\DATA\\结构统一'
logFiles=os.listdir(log_directory)
milligram_df2=pd.DataFrame()
#在文件夹C:\\Users\\JacyJam\\Desktop\\中标企业信息\\遍历
for filename in logFiles:
if endwith(filename, '.xlsx') or \
endwith(filename, '.xls'):
filePath = log_directory + '/' + filename
data = pd.read_excel(filePath)
pd.set_option('max_rows', None)
pd.set_option('max_colwidth', 10000)
# 获取以 "_num" 结尾的各列数据
col_names = data.columns.tolist()
milligram_columns = []
for items in col_names:
if items.endswith("供应商名称") :
milligram_columns.append(items)
milligram_df2=data[milligram_columns]
milligram_df2.to_csv('out.csv',encoding='utf_8_sig',header=0)
print(milligram_df2)
print(filename)