筛选kepler.csv中未下载到的kepid

In [1]

#判断输入字符串是否在路径中函数
import os
def findfile2(keyword):
    keyword="%.9d" % int(keyword)
    judgeExist=False
    root=os.path.join('C:\\Users\\96502\\kepler', keyword[0:4])
    if os.path.exists(root):
        filelist=[]
        for root,dirs,files in os.walk(root):
            for name in files:
                fitfile=filelist.append(os.path.join(root, name))
        for i in filelist:            
            if os.path.isfile(i):
                 #print(i)
                if keyword in os.path.split(i)[1]:
                     judgeExist=True    
                    #else:
                        #print('......no keyword!')
    return judgeExist

In [2]

#从csv中读取kepid调用findfile2函数
import pandas as pd
import numpy as np
df = pd.DataFrame(pd.read_csv("C:\\Users\\96502\\kepler\\dr24_tce_500.csv"),columns=['kepid'])
print(df)
kep_id=df.to_numpy()
print(kep_id[0])
my_array=np.empty([kep_id.size,1],dtype = str)
filelist=[]
for i in range(kep_id.size):
    temp=findfile2(kep_id[i])
    my_array[i]=temp
    print("处理第:"+str(i)+"个kepid:  "+str(temp))
# print(my_array)

In [3]

#输出
df2=pd.DataFrame(pd.read_csv("C:\\Users\\96502\\kepler\\dr24_tce_500.csv"))
df2.insert(0, 'flag', my_array)
filterDf=df2.flag[df2['flag']=='F']
df2=df2.drop(filterDf.index)
df2 = df2.reset_index()
df2.index=df2.index+1
df2['rowid'] = df2.index
del df2['flag']
del df2['index']
print(df2)
df2.to_csv('outputkepler24.csv',index=False)

reference:https://blog.csdn.net/lilong117194/article/details/74537595