使用python脚本搜索多个文件并为每个文件输出一个单独的文件

Question

我正在尝试启动并运行一个程序，该程序使用具有扩展名的天文数据文件。将具有该扩展名的所有文件放入一个文件夹并搜索特定的标题信息，然后将其放入与每个文件对应的文本文件夹中。我正在使用while循环，如果这段代码格式不好，请原谅，这是我第一次使用python！我的主要问题是我只能让程序在关闭自己之前读取一个文件。在

#!/usr/bin/env python

#This code properly imports all '.fits' files in a specified directory and 
#outputs them into a .txt format that allows several headers and their contained
#data to be read.  

import copy
import sys
import pyfits
import string
import glob
import os.path
import fnmatch
import numpy as np

DIR = raw_input("Please input a valid directory : ") #-----> This prompts for input from the user to find the '.fits' files
os.chdir(DIR)

initialcheck = 0  #Initiates the global counter for the number of '.fits' files in the specified directory
targetcheck = 0   #Initiates the global counter for the amount of files that have been processed

def checkinitial(TD):
    #This counts the number of '.fits' files in your directory
    for files in glob.iglob('*.fits'):
        check = len(glob.glob1(TD,"*.fits"))
        global initialcheck
        initialcheck = check    
        if initialcheck == 0:
        print 'There are no .FITS files in this directory! Try Again...'
        sys.exit()
    return initialcheck
def sorter(TD, targcheck, inicheck):
    #This function will call the two counters and compare them until the number of processed files is greater than the files in the     #directory, thereby finishing the loop 
    global initialcheck
    inicheck = initialcheck
    global targetcheck
    targcheck = targetcheck
    while targcheck <= inicheck:
        os.walk(TD)
        for allfiles in glob.iglob('*.fits'):
        print allfiles #This prints out the filenames the porgram is currently processing
            with pyfits.open(allfiles) as HDU:
            #This block outlines all of the search terms in their respective headers, you will need to set the indices                  #below to search in the correct header for the specified term you are looking for, however no alterations to                    #the header definitions should be made.
            HDU_HD_0 = HDU[0].header
            HDU_HD_1 = HDU[1].header
            #HDU_HD_2 = HDU[2].header  -----> Not usually needed, can be activated if data from this header is required
            #HDU_HD_3 = HDU[3].header  -----> Use this if the '.fits' file contains a third header (unlikely but possible)
            KeplerIDIndex = HDU_HD_0.index('KEPLERID')
            ChannelIndex = HDU_HD_0.index('SKYGROUP')
            TTYPE1Index = HDU_HD_1.index('TTYPE1')
            TTYPE8Index = HDU_HD_1.index('TTYPE8')
            TTYPE9Index = HDU_HD_1.index('TTYPE9')
            TTYPE11Index = HDU_HD_1.index('TTYPE11')
            TTYPE12Index = HDU_HD_1.index('TTYPE12')
            TTYPE13Index = HDU_HD_1.index('TTYPE13')
            TTYPE14Index = HDU_HD_1.index('TTYPE14')
            TUNIT1Index = HDU_HD_1.index('TUNIT1')
            TUNIT8Index = HDU_HD_1.index('TUNIT8')
            TUNIT9Index = HDU_HD_1.index('TUNIT9')
            TUNIT11Index = HDU_HD_1.index('TUNIT11')
            TUNIT12Index = HDU_HD_1.index('TUNIT12')
            TUNIT13Index = HDU_HD_1.index('TUNIT13')
            TUNIT14Index = HDU_HD_1.index('TUNIT14')    
            #The below variables are an index search for the data found in the specified indices above, allowing the data                   #to be found in teh numpy array that '.fits' files use                      
            File_Data_KID = list( HDU_HD_0[i] for i in [KeplerIDIndex])
            File_Data_CHAN = list( HDU_HD_0[i] for i in [ChannelIndex])
            Astro_Data_1 = list( HDU_HD_1[i] for i in [TTYPE1Index])
            Astro_Data_8 = list( HDU_HD_1[i] for i in [TTYPE8Index])
            Astro_Data_9 = list( HDU_HD_1[i] for i in [TTYPE9Index])
            Astro_Data_11 = list( HDU_HD_1[i] for i in [TTYPE11Index])  
            Astro_Data_12 = list( HDU_HD_1[i] for i in [TTYPE12Index])
            Astro_Data_13 = list( HDU_HD_1[i] for i in [TTYPE13Index])
            Astro_Data_14 = list( HDU_HD_1[i] for i in [TTYPE14Index])
            Astro_Data_Unit_1 = list( HDU_HD_1[i] for i in [TUNIT1Index])
            Astro_Data_Unit_8 = list( HDU_HD_1[i] for i in [TUNIT8Index])
            Astro_Data_Unit_9 = list( HDU_HD_1[i] for i in [TUNIT9Index])
            Astro_Data_Unit_11 = list( HDU_HD_1[i] for i in [TUNIT11Index]) 
            Astro_Data_Unit_12 = list( HDU_HD_1[i] for i in [TUNIT12Index])
            Astro_Data_Unit_13 = list( HDU_HD_1[i] for i in [TUNIT13Index])
            Astro_Data_Unit_14 = list( HDU_HD_1[i] for i in [TUNIT14Index])
            HDU.close()
            with open('Processed ' + allfiles + ".txt", "w") as copy:
                targetcheck += 1
                Title1_Format = '{0}-----{1}'.format('Kepler I.D.','Channel')
                Title2_Format = '-{0}--------{1}------------{2}------------{3}------------{4}------------{5}-------------{6}-'.format('TTYPE1','TTYPE8','TTYPE9','TTYPE11','TTYPE12','TTYPE13','TTYPE14')
                File_Format = '{0}--------{1}'.format(File_Data_KID, File_Data_CHAN)
                Astro_Format = '{0}---{1}---{2}---{3}---{4}---{5}---{6}'.format(Astro_Data_1, Astro_Data_8, Astro_Data_9, Astro_Data_11, Astro_Data_12, Astro_Data_13, Astro_Data_14)
                Astro_Format_Units = '{0}  {1}  {2}  {3}  {4}   {5}   {6}'.format(Astro_Data_Unit_1, Astro_Data_Unit_8, Astro_Data_Unit_9, Astro_Data_Unit_11, Astro_Data_Unit_12, Astro_Data_Unit_13, Astro_Data_Unit_14)
                copy.writelines("%s\n" % Title1_Format)
                    copy.writelines( "%s\n" % File_Format)
                copy.writelines('\n')
                copy.writelines("%s\n" % Title2_Format)
                    copy.writelines( "%s\n" % Astro_Format)
                copy.writelines('\n')
                    copy.writelines( "%s\n" % Astro_Format_Units)   
                Results = copy          
            return Results

checkinitial(DIR)
sorter(DIR, targetcheck, initialcheck)

Answer 1

我想你总是混淆一个文件和一个文件列表。试试这样的方法：

def checkinitial(TD):
    #This counts the number of '.fits' files in your directory
    check = len(glob.glob1(TD,"*.fits"))
    if not check:
        print 'There are no .FITS files in this directory! Try Again...'
        sys.exit()
return check

def sorter(TD, targcheck, inicheck):
    """This function will call the two counters and compare them until the number of processed
       files is greater than the files in the directory, thereby finishing the loop
    """ 
    for in_file in glob.iglob(os.path.join(TD,'*.fits')):
        print in_file  # This prints out the filenames the program is currently processing
        with pyfits.open(in_file) as HDU:
            # <Process input file HDU here>
        out_file_name = 'Processed_' + os.path.basename(in_file) + ".txt"
        with open(os.path.join(TD, out_file_name), "w") as copy:
            # <Write stuff to your output file copy here>