So i wrote a little program in python which allows me to take a .csv file, filter out the lines i need and then export these into a new .txt file.
This worked quite well, so i decided to make it more user friendly by allowing the user to select the file that should be converted by himself through the console (command line).
My problem: The file is imported as a .csv file but not exported as a .txt file which leads to my program overwriting the original file which will be emptied because of a step in my program which allows me to delete the first two lines of the output text.
Does anyone know a solution for this?
Thanks :)
import csv
import sys
userinput = raw_input('List:')
saveFile = open(userinput, 'w')
with open(userinput, 'r') as file:
reader = csv.reader(file)
count = 0
for row in reader:
print(row[2])
saveFile.write(row[2] + ' ""\n')
saveFile.close()
saveFile = open(userinput, 'r')
data_list = saveFile.readlines()
saveFile.close()
del data_list[1:2]
saveFile = open(userinput, 'w')
saveFile.writelines(data_list)
saveFile.close()
Try This:
userinput = raw_input('List:')
f_extns = userinput.split(".")
saveFile = open(f_extns[0]+'.txt', 'w')
I think you probably just want to save the file with a new name, this Extracting extension from filename in Python talks about splitting out the extension so then you can just add your own extension
you would end up with something like
name, ext = os.path.splitext(userinput)
saveFile = open(name + '.txt', 'w')
You probably just need to change the extension of the output file. Here is a solution that sets the output file extension to .txt; if the input file is also .txt then there will be a problem, but for all other extensions of the input file this should work.
import csv
import os
file_name = input('Name of file:')
# https://docs.python.org/3/library/os.path.html#os.path.splitext
# https://stackoverflow.com/questions/541390/extracting-extension-from-filename-in-python
file_name, file_ext_r = os.path.splitext(file_name)
file_ext_w = '.txt'
file_name_r = ''.format(file_name, file_ext_r)
file_name_w = ''.format(file_name, file_ext_w)
print('File to read:', file_name_r)
print('File to write:', file_name_w)
with open(file_name_r, 'r') as fr, open(file_name_w, 'w') as fw:
reader = csv.reader(fr)
for i, row in enumerate(reader):
print(row[2])
if i >= 2:
fw.write(row[2] + ' ""\n')
I also simplified your logic to avoid writting the first 2 lines to the output file; no need to read and write the output file again.
Does this work for you?
so I have a some code that opens a text file containing a list of paths to files like so:
C:/Users/User/Desktop/mini_mouse/1980
C:/Users/User/Desktop/mini_mouse/1982
C:/Users/User/Desktop/mini_mouse/1984
It then opens these files individually, line-by-line, and does some filtering to the files. I then want it to output the result to a completely different folder called:
output_location = 'C:/Users/User/Desktop/test2/'
As it stands, my code currently outputs the result to the place where the original file was opened i.e if it opens the file C:/Users/User/Desktop/mini_mouse/1980, the output will be in the same folder under the name '1980_filtered'. I, however, would like the output to go into the output_location. Could anyone see where I am going wrong currently? Any help would be greatly appreciated! Here is my code:
import os
def main():
stop_words_path = 'C:/Users/User/Desktop/NLTK-stop-word-list.txt'
stopwords = get_stop_words_list(stop_words_path)
output_location = 'C:/Users/User/Desktop/test2/'
list_file = 'C:/Users/User/Desktop/list_of_files.txt'
with open(list_file, 'r') as f:
for file_name in f:
#print(file_name)
if file_name.endswith('\n'):
file_name = file_name[:-1]
#print(file_name)
file_path = os.path.join(file_name) # joins the new path of the file to the current file in order to access the file
filestring = '' # file string which will take all the lines in the file and add them to itself
with open(file_path, 'r') as f2: # open the file
print('just opened ' + file_name)
print('\n')
for line in f2: # read file line by line
x = remove_stop_words(line, stopwords) # remove stop words from line
filestring += x # add newly filtered line to the file string
filestring += '\n' # Create new line
new_file_path = os.path.join(output_location, file_name) + '_filtered' # creates a new file of the file that is currenlty being filtered of stopwords
with open(new_file_path, 'a') as output_file: # opens output file
output_file.write(filestring)
if __name__ == "__main__":
main()
Assuming you're using Windows (because you have a normal Windows filesystem), you have to use backslashes in your pathnames. Note that this is only on Windows. I know it's annoying, so I changed it for you (you're welcome :)). You also have to use two backslashes, as it will try to use it as an escape char.
import os
def main():
stop_words_path = 'C:\\Users\\User\\Desktop\\NLTK-stop-word-list.txt'
stopwords = get_stop_words_list(stop_words_path)
output_location = 'C:\\Users\\User\\Desktop\\test2\\'
list_file = 'C:\\Users\\User\\Desktop\\list_of_files.txt'
with open(list_file, 'r') as f:
for file_name in f:
#print(file_name)
if file_name.endswith('\n'):
file_name = file_name[:-1]
#print(file_name)
file_path = os.path.join(file_name) # joins the new path of the file to the current file in order to access the file
filestring = '' # file string which will take all the lines in the file and add them to itself
with open(file_path, 'r') as f2: # open the file
print('just opened ' + file_name)
print('\n')
for line in f2: # read file line by line
x = remove_stop_words(line, stopwords) # remove stop words from line
filestring += x # add newly filtered line to the file string
filestring += '\n' # Create new line
new_file_path = os.path.join(output_location, file_name) + '_filtered' # creates a new file of the file that is currenlty being filtered of stopwords
with open(new_file_path, 'a') as output_file: # opens output file
output_file.write(filestring)
if __name__ == "__main__":
main()
Based your code it looks like an issue in the line:
new_file_path = os.path.join(output_location, file_name) + '_filtered'
In Python's os.path.join() any absolute path (or drive letter in Windows) in the inputs will discard everything before it and restart the join from the new absolute path (or drive letter). Since you're calling file_name directly from list_of_files.txt and you have each path formatted there relative to the C: drive, each call to os.path.join() is dropping output_location and being reset to the original file path.
See Why doesn't os.path.join() work in this case? for a better explanation of this behavior.
When building the output path you could strip the file name, "1980" for instance, from the path "C:/Users/User/Desktop/mini_mouse/1980" and join based on the output_location variable and the isolated file name.
I have a folder with multiple files like so:
1980
1981
1982
In each of these files is some text. I want to loop through each of these files and do some operation to each file then save the edited file to another folder and move onto the next file and so on. The result would be that I have the original folder and then another folder with the edited version of each file in it like so:
1980_filtered
1981_filtered
1982_filtered
Is it possible to do this?
Currently I have some code that loops through the files in a folder, does some filtering to each file and then saves all the edits of each file into one massive file. Here is my code:
import os
input_location = 'C:/Users/User/Desktop/mini_mouse'
output_location = 'C:/Users/User/Desktop/filter_mini_mouse/mouse'
for root, dir, files in os.walk(input_location):
for file in files:
os.chdir(input_location)
with open(file, 'r') as f, open('NLTK-stop-word-list', 'r') as f2:
mouse_file = f.read().split() # reads file and splits it into a list
stopwords = f2.read().split()
x = (' '.join(i for i in mouse_file if i.lower() not in (x.lower() for x in stopwords)))
with open(output_location, 'a') as output_file:
output_file.write(x)
Any help would be greatly appreciated!
You need to specify what each new file is called. To do so, Python has some good string formatting methods. Fortunately, your new desired file names are easy to do in a loop
import os
input_location = 'C:/Users/User/Desktop/mini_mouse'
output_location = 'C:/Users/User/Desktop/filter_mini_mouse/mouse'
for root, dir, files in os.walk(input_location):
for file in files:
new_file = "{}_filtered.txt".format(file)
os.chdir(input_location)
with open(file, 'r') as f, open('NLTK-stop-word-list', 'r') as f2:
mouse_file = f.read().split()
stopwords = f2.read().split()
x = (' '.join(i for i in mouse_file if i.lower() not in (x.lower() for x in stopwords)))
with open(output_location+'/'+new_file, 'w') as output_file: # Changed 'append' to 'write'
output_file.write(x)
If you're in Python 3.7, you can do
new_file = f"{file}_filtered.txt"
and
with open(f"{output_location}/{new_file}", 'w') as output_file:
output_file.write(x)
First of all you should start by opening the NLTK-stop-word-list only once, so I moved it outside of your loops. Second, os.chdir() is redundant, you can use os.path.join() to get your current file path (and to construct your new file path):
import os
input_location = 'C:/Users/User/Desktop/mini_mouse'
output_location = 'C:/Users/User/Desktop/filter_mini_mouse/'
stop_words_path = 'C:/Users/User/Desktop/NLTK-stop-word-list.txt'
with open(stop_words_path, 'r') as stop_words:
for root, dirs, files in os.walk(input_location):
for name in files:
file_path = os.path.join(root, name)
with open(file_path, 'r') as f:
mouse_file = f.read().split() # reads file and splits it into a list
stopwords = stop_words.read().split()
x = (' '.join(i for i in mouse_file if i.lower() not in (x.lower() for x in stopwords)))
new_file_path = os.path.join(output_location, name) + '_filtered'
with open(new_file_path, 'a') as output_file:
output_file.write(x)
P.S: I took the liberty to change some of your variable names as they were part of python's built in words ('file' and 'dir'). If you'll run __builtins__.__dict__.keys() you'll see them there.
I am trying to process several files into a single, merged csv file using python. So far, I have
files = ["file1.txt", "file2.txt", "file3.txt"]
def doSomething(oldfile):
content = []
with open oldfile as file:
content = file.read().splitlines()
file.close()
return content.reverse()
with open("newfile.txt", "w") as file:
w = csv.writer(file, dialect = "excel-tab")
for i in range(0, len(files)):
w. writerows(doSomething(files[i])
file.close()
The new file is being created, but there is nothing in it. I am curious about what is going on.
Thanks!
For starters, list.reverse() reverses the list in place and doesn't return anything so you're essentially returning None from your doSomething() function. You'll actually want to split that into two lines:
content.reverse()
return content
If you want to streamline your code, here's a suggestion:
def doSomething(oldfile):
with open(oldfile, "r") as f:
return reversed(f.read().splitlines())
files = ["file1.txt", "file2.txt", "file3.txt"]
with open("newfile.txt", "wb") as file:
w = csv.writer(file, dialect = "excel-tab")
for current_file in files:
w.writerows(doSomething(current_file))
I think your program crashes for several reasons:
open(..) is a function, so you cannot write:
with open oldfile as file:
a with statement for files is used to enforce closing of a file, so file.close() is actually not necessary.
.reverse() works inplace: it returns None, you can use reversed(..) for that.
You can fix it with:
files = ["file1.txt", "file2.txt", "file3.txt"]
def doSomething(oldfile):
content = []
with open(oldfile,'r') as file:
return list(reversed(file))
with open("newfile.txt", "w") as file:
w = csv.writer(file, dialect = "excel-tab")
for oldfile in files:
w.writerows(doSomething(oldfile))
I also used a for loop over the list, instead of the indices, since that is more "pythonic". Furthermore a file is iterable over its rows. So one can use reversed(file) to obtain the lines of the file in reverse.
How do I search and replace text in a file using Python 3?
Here is my code:
import os
import sys
import fileinput
print ("Text to search for:")
textToSearch = input( "> " )
print ("Text to replace it with:")
textToReplace = input( "> " )
print ("File to perform Search-Replace on:")
fileToSearch = input( "> " )
#fileToSearch = 'D:\dummy1.txt'
tempFile = open( fileToSearch, 'r+' )
for line in fileinput.input( fileToSearch ):
if textToSearch in line :
print('Match Found')
else:
print('Match Not Found!!')
tempFile.write( line.replace( textToSearch, textToReplace ) )
tempFile.close()
input( '\n\n Press Enter to exit...' )
Input file:
hi this is abcd hi this is abcd
This is dummy text file.
This is how search and replace works abcd
When I search and replace 'ram' by 'abcd' in above input file, it works as a charm. But when I do it vice-versa i.e. replacing 'abcd' by 'ram', some junk characters are left at the end.
Replacing 'abcd' by 'ram'
hi this is ram hi this is ram
This is dummy text file.
This is how search and replace works rambcd
As pointed out by michaelb958, you cannot replace in place with data of a different length because this will put the rest of the sections out of place. I disagree with the other posters suggesting you read from one file and write to another. Instead, I would read the file into memory, fix the data up, and then write it out to the same file in a separate step.
# Read in the file
with open('file.txt', 'r') as file :
filedata = file.read()
# Replace the target string
filedata = filedata.replace('abcd', 'ram')
# Write the file out again
with open('file.txt', 'w') as file:
file.write(filedata)
Unless you've got a massive file to work with which is too big to load into memory in one go, or you are concerned about potential data loss if the process is interrupted during the second step in which you write data to the file.
fileinput already supports inplace editing. It redirects stdout to the file in this case:
#!/usr/bin/env python3
import fileinput
with fileinput.FileInput(filename, inplace=True, backup='.bak') as file:
for line in file:
print(line.replace(text_to_search, replacement_text), end='')
As Jack Aidley had posted and J.F. Sebastian pointed out, this code will not work:
# Read in the file
filedata = None
with file = open('file.txt', 'r') :
filedata = file.read()
# Replace the target string
filedata.replace('ram', 'abcd')
# Write the file out again
with file = open('file.txt', 'w') :
file.write(filedata)`
But this code WILL work (I've tested it):
f = open(filein,'r')
filedata = f.read()
f.close()
newdata = filedata.replace("old data","new data")
f = open(fileout,'w')
f.write(newdata)
f.close()
Using this method, filein and fileout can be the same file, because Python 3.3 will overwrite the file upon opening for write.
You can do the replacement like this
f1 = open('file1.txt', 'r')
f2 = open('file2.txt', 'w')
for line in f1:
f2.write(line.replace('old_text', 'new_text'))
f1.close()
f2.close()
You can also use pathlib.
from pathlib2 import Path
path = Path(file_to_search)
text = path.read_text()
text = text.replace(text_to_search, replacement_text)
path.write_text(text)
(pip install python-util)
from pyutil import filereplace
filereplace("somefile.txt","abcd","ram")
Will replace all occurences of "abcd" with "ram".
The function also supports regex by specifying regex=True
from pyutil import filereplace
filereplace("somefile.txt","\\w+","ram",regex=True)
Disclaimer: I'm the author (https://github.com/MisterL2/python-util)
Open the file in read mode. Read the file in string format. Replace the text as intended. Close the file. Again open the file in write mode. Finally, write the replaced text to the same file.
try:
with open("file_name", "r+") as text_file:
texts = text_file.read()
texts = texts.replace("to_replace", "replace_string")
with open(file_name, "w") as text_file:
text_file.write(texts)
except FileNotFoundError as f:
print("Could not find the file you are trying to read.")
Late answer, but this is what I use to find and replace inside a text file:
with open("test.txt") as r:
text = r.read().replace("THIS", "THAT")
with open("test.txt", "w") as w:
w.write(text)
DEMO
With a single with block, you can search and replace your text:
with open('file.txt','r+') as f:
filedata = f.read()
filedata = filedata.replace('abc','xyz')
f.truncate(0)
f.write(filedata)
Your problem stems from reading from and writing to the same file. Rather than opening fileToSearch for writing, open an actual temporary file and then after you're done and have closed tempFile, use os.rename to move the new file over fileToSearch.
My variant, one word at a time on the entire file.
I read it into memory.
def replace_word(infile,old_word,new_word):
if not os.path.isfile(infile):
print ("Error on replace_word, not a regular file: "+infile)
sys.exit(1)
f1=open(infile,'r').read()
f2=open(infile,'w')
m=f1.replace(old_word,new_word)
f2.write(m)
Using re.subn it is possible to have more control on the substitution process, such as word splitted over two lines, case-(in)sensitive match. Further, it returns the amount of matches which can be used to avoid waste of resources if the string is not found.
import re
file = # path to file
# they can be also raw string and regex
textToSearch = r'Ha.*O' # here an example with a regex
textToReplace = 'hallo'
# read and replace
with open(file, 'r') as fd:
# sample case-insensitive find-and-replace
text, counter = re.subn(textToSearch, textToReplace, fd.read(), re.I)
# check if there is at least a match
if counter > 0:
# edit the file
with open(file, 'w') as fd:
fd.write(text)
# summary result
print(f'{counter} occurence of "{textToSearch}" were replaced with "{textToReplace}".')
Some regex:
add the re.I flag, short form of re.IGNORECASE, for a case-insensitive match
for multi-line replacement re.subn(r'\n*'.join(textToSearch), textToReplace, fd.read()), depending on the data also '\n{,1}'. Notice that for this case textToSearch must be a pure string, not a regex!
Besides the answers already mentioned, here is an explanation of why you have some random characters at the end:
You are opening the file in r+ mode, not w mode. The key difference is that w mode clears the contents of the file as soon as you open it, whereas r+ doesn't.
This means that if your file content is "123456789" and you write "www" to it, you get "www456789". It overwrites the characters with the new input, but leaves any remaining input untouched.
You can clear a section of the file contents by using truncate(<startPosition>), but you are probably best off saving the updated file content to a string first, then doing truncate(0) and writing it all at once.
Or you can use my library :D
I got the same issue. The problem is that when you load a .txt in a variable you use it like an array of string while it's an array of character.
swapString = []
with open(filepath) as f:
s = f.read()
for each in s:
swapString.append(str(each).replace('this','that'))
s = swapString
print(s)
I tried this and used readlines instead of read
with open('dummy.txt','r') as file:
list = file.readlines()
print(f'before removal {list}')
for i in list[:]:
list.remove(i)
print(f'After removal {list}')
with open('dummy.txt','w+') as f:
for i in list:
f.write(i)
you can use sed or awk or grep in python (with some restrictions). Here is a very simple example. It changes banana to bananatoothpaste in the file. You can edit and use it. ( I tested it worked...note: if you are testing under windows you should install "sed" command and set the path first)
import os
file="a.txt"
oldtext="Banana"
newtext=" BananaToothpaste"
os.system('sed -i "s/{}/{}/g" {}'.format(oldtext,newtext,file))
#print(f'sed -i "s/{oldtext}/{newtext}/g" {file}')
print('This command was applied: sed -i "s/{}/{}/g" {}'.format(oldtext,newtext,file))
if you want to see results on the file directly apply: "type" for windows/ "cat" for linux:
####FOR WINDOWS:
os.popen("type " + file).read()
####FOR LINUX:
os.popen("cat " + file).read()
I have done this:
#!/usr/bin/env python3
import fileinput
import os
Dir = input ("Source directory: ")
os.chdir(Dir)
Filelist = os.listdir()
print('File list: ',Filelist)
NomeFile = input ("Insert file name: ")
CarOr = input ("Text to search: ")
CarNew = input ("New text: ")
with fileinput.FileInput(NomeFile, inplace=True, backup='.bak') as file:
for line in file:
print(line.replace(CarOr, CarNew), end='')
file.close ()
I modified Jayram Singh's post slightly in order to replace every instance of a '!' character to a number which I wanted to increment with each instance. Thought it might be helpful to someone who wanted to modify a character that occurred more than once per line and wanted to iterate. Hope that helps someone. PS- I'm very new at coding so apologies if my post is inappropriate in any way, but this worked for me.
f1 = open('file1.txt', 'r')
f2 = open('file2.txt', 'w')
n = 1
# if word=='!'replace w/ [n] & increment n; else append same word to
# file2
for line in f1:
for word in line:
if word == '!':
f2.write(word.replace('!', f'[{n}]'))
n += 1
else:
f2.write(word)
f1.close()
f2.close()
def word_replace(filename,old,new):
c=0
with open(filename,'r+',encoding ='utf-8') as f:
a=f.read()
b=a.split()
for i in range(0,len(b)):
if b[i]==old:
c=c+1
old=old.center(len(old)+2)
new=new.center(len(new)+2)
d=a.replace(old,new,c)
f.truncate(0)
f.seek(0)
f.write(d)
print('All words have been replaced!!!')
I have worked this out as an exercise of a course: open file, find and replace string and write to a new file.
class Letter:
def __init__(self):
with open("./Input/Names/invited_names.txt", "r") as file:
# read the list of names
list_names = [line.rstrip() for line in file]
with open("./Input/Letters/starting_letter.docx", "r") as f:
# read letter
file_source = f.read()
for name in list_names:
with open(f"./Output/ReadyToSend/LetterTo{name}.docx", "w") as f:
# replace [name] with name of the list in the file
replace_string = file_source.replace('[name]', name)
# write to a new file
f.write(replace_string)
brief = Letter()
Like so:
def find_and_replace(file, word, replacement):
with open(file, 'r+') as f:
text = f.read()
f.write(text.replace(word, replacement))
def findReplace(find, replace):
import os
src = os.path.join(os.getcwd(), os.pardir)
for path, dirs, files in os.walk(os.path.abspath(src)):
for name in files:
if name.endswith('.py'):
filepath = os.path.join(path, name)
with open(filepath) as f:
s = f.read()
s = s.replace(find, replace)
with open(filepath, "w") as f:
f.write(s)