This question already has answers here:
Create file but if name exists add number
(16 answers)
Closed 3 years ago.
i = 1
while i <=10:
f = open("txtfile.txt",+str(i) "a+")
f.write("111\n")
f.write("222\n")
i = i + 1
f.close()
I want to create txt in many times , But the top code is not in my mind.
I want to create a txt.file1 , and if it exist , the next time execute name is txt.file2.
Assuming, on every run new file (txtfileNN.txt) with incremented number need to be created ( NN is one or two digit number), try below code:
import os
import re
file_base_name = 'txtfile'
r = re.compile(file_base_name+'\d{0,2}.txt')
all_files_in_dir=sorted([i for i in os.listdir() if r.match(i)])
print('Existing files in directory: {}'.format(all_files_in_dir))
# Existing files in directory: ['txtfile.txt', 'txtfile1.txt', 'txtfile10.txt']
if not all_files_in_dir:
# File does not exist yet
out_file = file_base_name + '.txt'
else:
highest_file=all_files_in_dir[-1]
# 'txtfile10.txt'
int_portion = highest_file.replace('.txt', '').split(file_base_name)[-1]
if not int_portion:
# no integer in file, so it it txtfile.txt
next_int = 1
else:
next_int = int(int_portion) + 1
out_file = file_base_name + str(next_int) + '.txt'
print('Next file name : {}'.format(out_file))
# Next file name : txtfile11.txt
# Now write text in new file
f = open(out_file, 'a')
f.write("111\n")
f.write("222\n")
f.close()
Here is a simple way to create 10 files in Python 3.6+, named from file.txt01 to file.txt10:
from pathlib import Path
for i in range(1, 11):
f = Path(f'file.txt{i:02d}')
f.write_text('111\n222\n')
If you want to create a new file on every run, sequentially numbered ad infinitum, do this:
from pathlib import Path
i = 1
while True:
if Path(f'file.txt{i}').exists():
i += 1
else:
Path(f'file.txt{i}').write_text('111\n222\n')
break
But that is very inefficient though.
So maybe this is a better solution:
from pathlib import Path
source = Path('/home/accdias/temp')
prefix = 'file.txt'
slots = set([int(_.name.replace(prefix, '')) for _ in source.glob(f'{prefix}*')])
slot = min(set(range(1, max(slots, default=1) + 1)) - slots, default=max(slots, default=1) + 1)
filename = source / f'{prefix}{slot}'
filename.write_text('111\n222\n')
The solution above is nice because it take into account any gaps that may exist and pick the next lowest slot number available.
Related
I want to put proper sequence no in my file using python. Its working partially not fully. Suppose in a particular folder there is 3 files. The sequence should Num1_.doc,Num2_.pdf,Num3_.doc. It's working fine.
But suppose a new file is coming on that folder, how it maintain the proper sequence.
My code is -
import os
os.chdir('C:\\Users\\Project\\')
print(os.getcwd())
for count, f in enumerate(os.listdir()):
f_name, f_ext = os.path.splitext(f)
f_name = "Num" + str(count) + '_' + f_name
new_name = f'{f_name}{f_ext}'
os.rename(f, new_name)
Its generate Num1_.doc,Num2_.pdf,Num3_.doc etc.
Now new file is added on that folder. The sequence should Num4_.doc. How to do it in python.
Find what the maximum number is out of the current files, then rename any new files with a number 1 higher
import os
current_max = 0
for i in os.listdir():
# The number in this filename
num = int(i[3:-5])
if num > current_max:
current_max = num
# If the current_file has not been named yet
if "Num_" not in i:
#Rename by adding 1 to the current maximum number recorded
os.rename(i, f"Num_{current_max+1}")
Try to first get the maximum number already assigned from previous renamings, and then rename the remaining files starting from that number.
import os
import re
os.chdir('C:\\Users\\Project\\')
print(os.getcwd())
# find max number in filenames, if already named
filenames = [os.path.splitext(f)[0] for f in os.listdir()]
filenames = filter(lambda f: f[:3] == "Num" and len(f) >= 4, filenames)
max_n_file = max(map(lambda f: int(re.search('^[0-9]*', f[3:]).group(0)), filenames), default=0) + 1
# apply same algorithm but rename only not-"Num_" files
for _, f in enumerate(os.listdir()):
f_name, f_ext = os.path.splitext(f)
if f_name[:3] != "Num":
f_name = "Num" + str(max_n_file) + '_' + f_name
new_name = f'{f_name}{f_ext}'
os.rename(f, new_name)
max_n_file += 1
I want to change csv name (in this case Example.csv) to a specific name: date time name. I have a library called from datetime import datetime
This is my sentence to create a cvsFile:
with open('Example.csv', 'w') as csvFile:
I want that my output to be:
20180820.csv
20180821.csv
20180822.csv ... etc
And if I run more that one time in the same day, I want that my output to be:
20180820.csv (First time that I run the script)
20180821(2).csv (Second time run)
... etc
Something like this:
import pandas as pd
import datetime
current_date = datetime.datetime.now()
filename = str(current_date.day)+str(current_date.month)+str(current_date.year)
df.to_csv(str(filename + '.csv'))
Since you know how to create the file name you just have to check whether it already exists or not :
def exists(filename):
try:
with open(filename) as f:
file_exists = True
except FileNotFoundError:
file_exists = False
return file_exists
name = 'some_date.csv'
c = 0
while exists(filename):
c += 1
name = 'some_date({}).csv'.format(c)
# do stuff with name
Please find a solution if you can manage a 'progressive' variable taking track of the files. Otherwise you need to check the disk content and it might be rather more complex.
import datetime
progressive = 0
today = datetime.date.today()
todaystr = str(today)
rootname = todaystr
progressive += 1
if progressive > 1:
rootname = todaystr + '_' + str(progressive)
filename = rootname + '.csv'
Count the number of files in the directory with the same date in its name and use that information to create the file name. Here is a solution for both your problems.
import datetime
import os
now = datetime.datetime.now().strftime("%y%m%d")
# count the number of files already in the output dir with date (now)
count = len([name for name in os.listdir('./output/') if (os.path.isfile(name) and now in name)])
csv_name = './output/' + now
if count > 0:
csv_name = csv_name + "(" + str(count+1) +")"
csv_name = csv_name + ".csv"
with open(csv_name, 'w') as csvFile:
pass
Good Luck.
I found the solution:
Only take the real time in a variable, and then concatenate with .csv (and also I put this csv output in a specific folder called output). Finally I open the csvFile with the variable name.
> now = datetime.now().strftime('%Y%m%d-%Hh%M')
> csvname = './output/' + now + '.csv'
> with open(csvname, 'w') as csvFile:
I can not do the second part of my problem. I want that if I run more than one time the code the date time name change or add (2), (3)... etc.
I have this where it reads a file called source1.html, source2.html, source3.html, but when it cant find the next file (because it doesnt exist) it gives me a error. there can be an x amount of sourceX.html, so i need something to say if the next sourcex.html file can not be found, stop the loop.
Traceback (most recent call last): File "main.py", line 14, in
file = open(filename, "r") IOError: [Errno 2] No such file or
directory: 'source4.html
how can i stop the script looking for the next source file?
from bs4 import BeautifulSoup
import re
import os.path
n = 1
filename = "source" + str(n) + ".html"
savefile = open('OUTPUT.csv', 'w')
while os.path.isfile(filename):
strjpgs = "Extracted Layers: \n \n"
filename = "source" + str(n) + ".html"
n = n + 1
file = open(filename, "r")
soup = BeautifulSoup(file, "html.parser")
thedata = soup.find("div", class_="cplayer")
strdata = str(thedata)
DoRegEx = re.compile('/([^/]+)\.jpg')
jpgs = DoRegEx.findall(strdata)
strjpgs = strjpgs + "\n".join(jpgs) + "\n \n"
savefile.write(filename + '\n')
savefile.write(strjpgs)
print(filename)
print(strjpgs)
savefile.close()
print "done"
use a try / except and break
while os.path.isfile(filename):
try: # try to do this
# <your code>
except FileNotFoundError: # if this error occurs
break # exit the loop
The reason your code doesn't currently work is you're checking the previous file exists in your while loop. Not the next one. Hence you could also do
while True:
strjpgs = "Extracted Layers: \n \n"
filename = "source" + str(n) + ".html"
if not os.path.isfile(filename):
break
# <rest of your code>
you can try opening file, and break out of while loop once you catch an IOError exception.
from bs4 import BeautifulSoup
import re
import os.path
n = 1
filename = "source" + str(n) + ".html"
savefile = open('OUTPUT.csv', 'w')
while os.path.isfile(filename):
try:
strjpgs = "Extracted Layers: \n \n"
filename = "source" + str(n) + ".html"
n = n + 1
file = open(filename, "r")
except IOError:
print("file not found! breaking out of loop.")
break
soup = BeautifulSoup(file, "html.parser")
thedata = soup.find("div", class_="cplayer")
strdata = str(thedata)
DoRegEx = re.compile('/([^/]+)\.jpg')
jpgs = DoRegEx.findall(strdata)
strjpgs = strjpgs + "\n".join(jpgs) + "\n \n"
savefile.write(filename + '\n')
savefile.write(strjpgs)
print(filename)
print(strjpgs)
savefile.close()
print "done"
I'll suggest you to use os.path.exists() (which returns True/False) and os.path.isfile() both.
Use with statement to open file. It is Pythonic way to open files.
with statement is best preferred among the professional coders.
These are the contents of my current working directory.
H:\RishikeshAgrawani\Projects\Stk\ReadHtmlFiles>dir
Volume in drive H is New Volume
Volume Serial Number is C867-828E
Directory of H:\RishikeshAgrawani\Projects\Stk\ReadHtmlFiles
11/05/2018 16:12 <DIR> .
11/05/2018 16:12 <DIR> ..
11/05/2018 15:54 106 source1.html
11/05/2018 15:54 106 source2.html
11/05/2018 15:54 106 source3.html
11/05/2018 16:12 0 stopReadingIfNot.md
11/05/2018 16:11 521 stopReadingIfNot.py
5 File(s) 839 bytes
2 Dir(s) 196,260,925,440 bytes free
The below Python code shows how will you read files source1.html, source2.html, source.3.html and stop if there is no more files of the form sourceX.html (where X is 1, 2, 3, 4, ... etc.).
Sample code:
import os
n = 1;
html_file_name = 'source%d.html'
# It is necessary to check if sourceX.html is file or directory.
# If it is directory the check it if it exists or not.
# It it exists then perform operation (read/write etc.) on file.
while os.path.isfile(html_file_name % (n)) and os.path.exists(html_file_name % (n)):
print "Reading ", html_file_name % (n)
# The best way (Pythonic way) to open file
# You don't need to bother about closing the file
# It will be taken care by with statement
with open(html_file_name % (n), "r") as file:
# Make sure it works
print html_file_name % (n), " exists\n";
n += 1;
Output:
H:\RishikeshAgrawani\Projects\Stk\ReadHtmlFiles>python stopReadingIfNot.py
Reading source1.html
source1.html exists
Reading source2.html
source2.html exists
Reading source3.html
source3.html exists
So based on the above logic. you can modify your code. It will work.
Thanks.
This appears to be a sequence error. Let's look at a small fragment of your code, specifically lines dealing with filename:
filename = "source" + str(n) + ".html"
while os.path.isfile(filename):
filename = "source" + str(n) + ".html"
n = n + 1
file = open(filename, "r")
You're generating the next filename before you open the file (or really, checking the old filename then opening a new one). It's a little hard to see because you're really updating n while filename holds the previous number, but if we look at them in sequence it pops out:
n = 1
filename = "source1.html" # before loop
while os.path.isfile(filename):
filename = "source1.html" # first time inside loop
n = 2
open(filename)
while os.path.isfile(filename): # second time in loop - still source1
filename = "source2.html"
n = 3
open(filename) # We haven't checked if this file exists!
We can fix this a few ways. One is to move the entire updating, n before filename, to the end of the loop. Another is to let the loop mechanism update n, which is a sight easier (the real fix here is that we only use one filename value in each iteration of the loop):
for n in itertools.count(1):
filename = "source{}.html".format(n)
if not os.path.isfile(filename):
break
file = open(filename, "r")
#...
At the risk of looking rather obscure, we can also express the steps functionally (I'm using six here to avoid a difference between Python 2 and 3; Python 2's map wouldn't finish):
from six.moves import map
from itertools import count, takewhile
numbers = count(1)
filenames = map('source{}.html'.format, numbers)
existingfiles = takewhile(os.path.isfile, filenames)
for filename in existingfiles:
file = open(filename, "r")
#...
Other options include iterating over the numbers alone and using break when isfile returns False, or simply catching the exception when open fails (eliminating the need for isfile entirely).
I have a folder that contains several log file that I will parse with python.
I would show the list of file contained into a folder like:
[1] FileName1.log
[2] FileName2.log
And then the user can choose the right file writing the file list number.
For instance, to parse the file "FileName2.log" the user press 2.
In my script I can show the list of file but I don't now how to pick up a file from a list by index.
This is my script
import os
import sys
items = os.listdir("D:/Logs")
fileList = []
for names in items:
if names.endswith(".log"):
fileList.append(names)
cnt = 0
for fileName in fileList:
sys.stdout.write( "[%d] %s\n\r" %(cnt, fileName) )
cnt = cnt + 1
fileName = raw_input("\n\rSelect log file [0 -" + str(cnt) + " ]: ")
Thanks for the help!
import os
import sys
items = os.listdir("D:/Logs")
fileList = [name for name in items if name.endswith(".log")]
for cnt, fileName in enumerate(fileList, 1):
sys.stdout.write("[%d] %s\n\r" % (cnt, fileName))
choice = int(input("Select log file[1-%s]: " % cnt))
print(fileList[choice])
you own version of code with few modifications, hope this solves your purpose
If you have the names in an array like this:
fileList = ['FileName1.log','FileName2.log']
you can pull them out by using their index (remember that arrarys are 0-indexed) so fileList[0] would be 'FileName1.log'
when you ask for the user to input a number (eg 0, 1, 2) you would then use that number to get the file you want. like this:
fileToRead=fileList[userInput]
if you asked for 1,2,3 you would need to use userInput-1 to make sure it is correctly 0-indexed.
then you open the file you now have:
f=open(fileToRead, 'r')
you can read more about open here
If fileList is a list of files, and fileName is the user input, you can reference the file the user chose by using the following:
fileList[fileName]
import glob
import os
dirpath = r"D:\Logs" # the directory that contains the log files
prefix = "FileName"
fpaths = glob.glob(os.path.join(dirpath, "{}*.log".format(prefix))) # get all the log files
fpaths.sort(key=lambda fname: int(fname.split('.',1)[0][len(prefix):])) # sort the log files by number
print("Select a file to view:")
for i,fpath in enumerate(fpaths, 1):
print("[{}]: {}".format(i, os.path.basename(fpath)))
choice = int(input("Enter a selection number: ")) # assuming valid inputs
choice -= 1 # correcting for python's 0-indexing
print("You have chosen", os.path.basename(fpaths[choice]))
Just add in the end something like this...
sys.stdout.write(fileList[int(fileName)])
Indexing in python as in many other languages starts from 0. Try this:
import os
import sys
items = os.listdir("D:/Logs")
fileList = []
for names in items:
if names.endswith(".log"):
fileList.append(names)
cnt = 0
for fileName in fileList:
sys.stdout.write( "[%d] %s\n\r" %(cnt, fileName) )
cnt = cnt + 1
fileName = int(raw_input("\n\rSelect log file [0 - " + str(cnt - 1) + "]: "))
print(fileList[fileName])
You need to cast input from raw_input() to int. And then you can use the obtained number as index for your list. 0 is the first file, 1 is the second file etc.
I am trying to get a program up and running that takes astronomical data files with the extension .fits and takes all of the files with that extension in a folder and searches for specific header information, and subsequently places it into a text folder corresponding to each file. I am using a while loop, and please forgive me if this code is badly formatted, it is my first time using python! My main problem is that I can only get the program to read one file before it closes itself.
#!/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)
I think you keep getting confused between a single file and a list of files. Try something like this:
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>