How to amend an existing python file - python

I am trying to ammend a group of files in a folder, by adding F to the 4th line (which is number 3 in python, if I'm correct). With the following code below, the code is just continuously running and not making the amendments, anyone got any ideas?
import os
from glob import glob
list_of_files = glob('*.gjf') # get list of all .gjf files
for file in list_of_files:
# read file:
with open(file, 'r+') as f:
lines=f.readlines()
for line in lines:
lines.insert(3,'F')


for file in files:
# read your file's lines
with open(file, 'r') as f:
lines = f.readlines()
# add the value to insert in the list of lines at index 3
# don't forget line-break (\n)
lines.insert(3, 'F\n')
# join lines to create a string
text = ''.join(lines)
# don't forget to write the string back in your file
with open(file, 'w') as f:
f.write(text)


You are not able to edit a file with Python in this way. You would need to create a temporary file and then do some cleanup at the end by renaming the temporary file and removing the temporary file. The core logic is to read through the original files and add an F to the 4th line, otherwise just add the line. This can be done with a function like this:
import os
def add_f_4th_line(filename):
with open(filename, 'r') as f_in:
with opne('temp', 'w') as f_out:
for line_number, line_contents in enumerate(f_in):
if line_number == 3:
f_out.write(line_contents.replace('\n', 'F\n'))
else:
f_out.write(line_contents)
os.rename('temp', filename)
os.remove('temp')
enumerate will keep make an iterator of the line number and the contents of the line, so just iterate over each line, and you can find the 4th line with line_number == 3. Then, it will take that line and replace \n with F\n. \n is a new line character, so I'm assuming the end of the line is this character. So after adding this function, you'll just need to call this function for each file you get with your glob call.
import os
from glob import glob
list_of_files = glob('*.gjf') # get list of all .gjf files
for file in list_of_files:
add_f_4th_line(file)

Related

Python adding a string leaves extra characters

If you need any more info just Let Me Know
I have a python script that adds a string after each line on a CSV file. the line file_lines = [''.join([x.strip(), string_to_add, '\n']) for x in f.readlines()] is the trouble maker. For each file line it will add the string and then add a new line after each time the string is added.
Here is the script:
#Adding .JPG string to the end of each line for the Part Numbers
string_to_add = ".JPG"
#Open the file and join the .JPG to the current lines
with open("PartNums.csv", 'r') as f:
file_lines = [''.join([x.strip(), string_to_add, '\n']) for x in f.readlines()]
#Writes to the file until its done
with open("PartNums.csv", 'w') as f:
f.writelines(file_lines)
The script works and does what it is supposed to, however my issue is later on in this larger script. This script outputs into a CSV file and it looks like this:
X00TB0001.JPG
X01BJ0003.JPG
X01BJ0004.JPG
X01BJ0005.JPG
X01BJ0006.JPG
X01BJ0007.JPG
X01BJ0008.JPG
X01BJ0026.JPG
X01BJ0038.JPG
X01BJ0039.JPG
X01BJ0040.JPG
X01BJ0041.JPG
...
X01BJ0050.JPG
X01BJ0058.JPG
X01BJ0059.JPG
X01BJ0060.JPG
X01BJ0061.JPG
X01BJ0170.JPG
X01BJ0178.JPG
Without the \n in that line the csv file output looks like this file_lines = [''.join([x.strip(), string_to_add]) for x in f.readlines()]:
X00TB0001.JPGX01BJ0003.JPGX01BJ0004.JPGX01BJ0005.JPGX01BJ0006.JPG
The issue is when I go to read this file later and move files with it using this script:
#If the string matches a file name move it to a new directory
dst = r"xxx"
with open('PicsWeHave.txt') as my_file:
for filename in my_file:
src = os.path.join(XXX") # .strip() to avoid un-wanted white spaces
#shutil.copy(src, os.path.join(dst, filename.strip()))
shutil.copy(os.path.join(src, filename), os.path.join(dst, filename))
When I run this whole Script it works until it has to move the files I get this error:
FileNotFoundError: [Errno 2] No such file or directory: 'XXX\\X15SL0447.JPG\n'
I know the file exist however the '\n' should not be there and that's why I am asking how can I still get everything on a new line and not have \n after each name so when I move the file the strings match.
Thank You For Your Help!

As they said above you should use .strip():
shutil.copy(os.path.join(src, filename.strip()), os.path.join(dst, filename.strip()))
This way it gives you the file name or string you need and then it removes anything else.

Replace a text in File with python [duplicate]

I want to loop over the contents of a text file and do a search and replace on some lines and write the result back to the file. I could first load the whole file in memory and then write it back, but that probably is not the best way to do it.
What is the best way to do this, within the following code?
f = open(file)
for line in f:
if line.contains('foo'):
newline = line.replace('foo', 'bar')
# how to write this newline back to the file

The shortest way would probably be to use the fileinput module. For example, the following adds line numbers to a file, in-place:
import fileinput
for line in fileinput.input("test.txt", inplace=True):
print('{} {}'.format(fileinput.filelineno(), line), end='') # for Python 3
# print "%d: %s" % (fileinput.filelineno(), line), # for Python 2
What happens here is:
The original file is moved to a backup file
The standard output is redirected to the original file within the loop
Thus any print statements write back into the original file
fileinput has more bells and whistles. For example, it can be used to automatically operate on all files in sys.args[1:], without your having to iterate over them explicitly. Starting with Python 3.2 it also provides a convenient context manager for use in a with statement.
While fileinput is great for throwaway scripts, I would be wary of using it in real code because admittedly it's not very readable or familiar. In real (production) code it's worthwhile to spend just a few more lines of code to make the process explicit and thus make the code readable.
There are two options:
The file is not overly large, and you can just read it wholly to memory. Then close the file, reopen it in writing mode and write the modified contents back.
The file is too large to be stored in memory; you can move it over to a temporary file and open that, reading it line by line, writing back into the original file. Note that this requires twice the storage.

I guess something like this should do it. It basically writes the content to a new file and replaces the old file with the new file:
from tempfile import mkstemp
from shutil import move, copymode
from os import fdopen, remove
def replace(file_path, pattern, subst):
#Create temp file
fh, abs_path = mkstemp()
with fdopen(fh,'w') as new_file:
with open(file_path) as old_file:
for line in old_file:
new_file.write(line.replace(pattern, subst))
#Copy the file permissions from the old file to the new file
copymode(file_path, abs_path)
#Remove original file
remove(file_path)
#Move new file
move(abs_path, file_path)

Here's another example that was tested, and will match search & replace patterns:
import fileinput
import sys
def replaceAll(file,searchExp,replaceExp):
for line in fileinput.input(file, inplace=1):
if searchExp in line:
line = line.replace(searchExp,replaceExp)
sys.stdout.write(line)
Example use:
replaceAll("/fooBar.txt","Hello\sWorld!$","Goodbye\sWorld.")

This should work: (inplace editing)
import fileinput
# Does a list of files, and
# redirects STDOUT to the file in question
for line in fileinput.input(files, inplace = 1):
print line.replace("foo", "bar"),

Based on the answer by Thomas Watnedal.
However, this does not answer the line-to-line part of the original question exactly. The function can still replace on a line-to-line basis
This implementation replaces the file contents without using temporary files, as a consequence file permissions remain unchanged.
Also re.sub instead of replace, allows regex replacement instead of plain text replacement only.
Reading the file as a single string instead of line by line allows for multiline match and replacement.
import re
def replace(file, pattern, subst):
# Read contents from file as a single string
file_handle = open(file, 'r')
file_string = file_handle.read()
file_handle.close()
# Use RE package to allow for replacement (also allowing for (multiline) REGEX)
file_string = (re.sub(pattern, subst, file_string))
# Write contents to file.
# Using mode 'w' truncates the file.
file_handle = open(file, 'w')
file_handle.write(file_string)
file_handle.close()

As lassevk suggests, write out the new file as you go, here is some example code:
fin = open("a.txt")
fout = open("b.txt", "wt")
for line in fin:
fout.write( line.replace('foo', 'bar') )
fin.close()
fout.close()

If you're wanting a generic function that replaces any text with some other text, this is likely the best way to go, particularly if you're a fan of regex's:
import re
def replace( filePath, text, subs, flags=0 ):
with open( filePath, "r+" ) as file:
fileContents = file.read()
textPattern = re.compile( re.escape( text ), flags )
fileContents = textPattern.sub( subs, fileContents )
file.seek( 0 )
file.truncate()
file.write( fileContents )

A more pythonic way would be to use context managers like the code below:
from tempfile import mkstemp
from shutil import move
from os import remove
def replace(source_file_path, pattern, substring):
fh, target_file_path = mkstemp()
with open(target_file_path, 'w') as target_file:
with open(source_file_path, 'r') as source_file:
for line in source_file:
target_file.write(line.replace(pattern, substring))
remove(source_file_path)
move(target_file_path, source_file_path)
You can find the full snippet here.

fileinput is quite straightforward as mentioned on previous answers:
import fileinput
def replace_in_file(file_path, search_text, new_text):
with fileinput.input(file_path, inplace=True) as file:
for line in file:
new_line = line.replace(search_text, new_text)
print(new_line, end='')
Explanation:
fileinput can accept multiple files, but I prefer to close each single file as soon as it is being processed. So placed single file_path in with statement.
print statement does not print anything when inplace=True, because STDOUT is being forwarded to the original file.
end='' in print statement is to eliminate intermediate blank new lines.
You can used it as follows:
file_path = '/path/to/my/file'
replace_in_file(file_path, 'old-text', 'new-text')

Create a new file, copy lines from the old to the new, and do the replacing before you write the lines to the new file.

Expanding on #Kiran's answer, which I agree is more succinct and Pythonic, this adds codecs to support the reading and writing of UTF-8:
import codecs
from tempfile import mkstemp
from shutil import move
from os import remove
def replace(source_file_path, pattern, substring):
fh, target_file_path = mkstemp()
with codecs.open(target_file_path, 'w', 'utf-8') as target_file:
with codecs.open(source_file_path, 'r', 'utf-8') as source_file:
for line in source_file:
target_file.write(line.replace(pattern, substring))
remove(source_file_path)
move(target_file_path, source_file_path)

Using hamishmcn's answer as a template I was able to search for a line in a file that match my regex and replacing it with empty string.
import re
fin = open("in.txt", 'r') # in file
fout = open("out.txt", 'w') # out file
for line in fin:
p = re.compile('[-][0-9]*[.][0-9]*[,]|[-][0-9]*[,]') # pattern
newline = p.sub('',line) # replace matching strings with empty string
print newline
fout.write(newline)
fin.close()
fout.close()

if you remove the indent at the like below, it will search and replace in multiple line.
See below for example.
def replace(file, pattern, subst):
#Create temp file
fh, abs_path = mkstemp()
print fh, abs_path
new_file = open(abs_path,'w')
old_file = open(file)
for line in old_file:
new_file.write(line.replace(pattern, subst))
#close temp file
new_file.close()
close(fh)
old_file.close()
#Remove original file
remove(file)
#Move new file
move(abs_path, file)

search replace the string from number of .txt files in python

there are multiple files in directory with extension .txt, .dox, .qcr etc.
i need to list out txt files, search & replace the text from each txt files only.
need to search the $$\d ...where \d stands for the digit 1,2,3.....100.
need to replace with xxx.
please let me know the python script for this .
thanks in advance .
-Shrinivas
#created following script, it works for single txt files, but it is not working for txt files more than one lies in directory.
-----
def replaceAll(file,searchExp,replaceExp):
for line in fileinput.input(file, inplace=1):
if searchExp in line:
line = line.replace(searchExp,replaceExp)
sys.stdout.write(line)
#following code is not working, i expect to list out the files start #with "um_*.txt", open the file & replace the "$$\d" with replaceAll function.
for um_file in glob.glob('*.txt'):
t = open(um_file, 'r')
replaceAll("t.read","$$\d","xxx")
t.close()

fileinput.input(...) is supposed to process a bunch of files, and must be ended with a corresponding fileinput.close(). So you can either process all in one single call:
def replaceAll(file,searchExp,replaceExp):
for line in fileinput.input(file, inplace=True):
if searchExp in line:
line = line.replace(searchExp,replaceExp)
dummy = sys.stdout.write(line) # to avoid a possible output of the size
fileinput.close() # to orderly close everythin
replaceAll(glob.glob('*.txt'), "$$\d","xxx")
or consistently close fileinput after processing each file, but it rather ignores the main fileinput feature.

Try out this.
import re
def replaceAll(file,searchExp,replaceExp):
for line in file.readlines():
try:
line = line.replace(re.findall(searchExp,line)[0],replaceExp)
except:
pass
sys.stdout.write(line)
#following code is not working, i expect to list out the files start #with "um_*.txt", open the file & replace the "$$\d" with replaceAll function.
for um_file in glob.glob('*.txt'):
t = open(um_file, 'r')
replaceAll(t,"\d+","xxx")
t.close()
Here we are sending file handler to the replaceAll function rather than a string.

You can try this:
import os
import re
the_files = [i for i in os.listdir("foldername") if i.endswith("txt")]
for file in the_files:
new_data = re.sub("\d+", "xxx", open(file).read())
final_file = open(file, 'w')
final_file.write(new_data)
final_file.close()

Python write to multiple files write data to the previous file

I have twenty files. I read them one by one and count the items, and I write the answer in another file. If I name each file manually, (e.g. run40.txt), it works well.
But instead I read the file in a loop. It works only for the first file, but for the rest it starts adding the answer of previous files to the current file.
#!/usr/bin python
import glob
import sys
from collections import Counter
import time
c=Counter()
for file in glob.glob("*.txt"):
print file
myfile = open(file, "r")
for line in myfile:
c.update(line.split())
for item in c.items():
outfile= open(file + ".out", 'a+')
print >> outfile, "{}\t{}".format(*item)
outfile.close()
myfile.close()
Why did it add the output of the previously closed file to the new file?

Search and replace a line in a file in Python

I want to loop over the contents of a text file and do a search and replace on some lines and write the result back to the file. I could first load the whole file in memory and then write it back, but that probably is not the best way to do it.
What is the best way to do this, within the following code?
f = open(file)
for line in f:
if line.contains('foo'):
newline = line.replace('foo', 'bar')
# how to write this newline back to the file

The shortest way would probably be to use the fileinput module. For example, the following adds line numbers to a file, in-place:
import fileinput
for line in fileinput.input("test.txt", inplace=True):
print('{} {}'.format(fileinput.filelineno(), line), end='') # for Python 3
# print "%d: %s" % (fileinput.filelineno(), line), # for Python 2
What happens here is:
The original file is moved to a backup file
The standard output is redirected to the original file within the loop
Thus any print statements write back into the original file
fileinput has more bells and whistles. For example, it can be used to automatically operate on all files in sys.args[1:], without your having to iterate over them explicitly. Starting with Python 3.2 it also provides a convenient context manager for use in a with statement.
While fileinput is great for throwaway scripts, I would be wary of using it in real code because admittedly it's not very readable or familiar. In real (production) code it's worthwhile to spend just a few more lines of code to make the process explicit and thus make the code readable.
There are two options:
The file is not overly large, and you can just read it wholly to memory. Then close the file, reopen it in writing mode and write the modified contents back.
The file is too large to be stored in memory; you can move it over to a temporary file and open that, reading it line by line, writing back into the original file. Note that this requires twice the storage.

I guess something like this should do it. It basically writes the content to a new file and replaces the old file with the new file:
from tempfile import mkstemp
from shutil import move, copymode
from os import fdopen, remove
def replace(file_path, pattern, subst):
#Create temp file
fh, abs_path = mkstemp()
with fdopen(fh,'w') as new_file:
with open(file_path) as old_file:
for line in old_file:
new_file.write(line.replace(pattern, subst))
#Copy the file permissions from the old file to the new file
copymode(file_path, abs_path)
#Remove original file
remove(file_path)
#Move new file
move(abs_path, file_path)

Here's another example that was tested, and will match search & replace patterns:
import fileinput
import sys
def replaceAll(file,searchExp,replaceExp):
for line in fileinput.input(file, inplace=1):
if searchExp in line:
line = line.replace(searchExp,replaceExp)
sys.stdout.write(line)
Example use:
replaceAll("/fooBar.txt","Hello\sWorld!$","Goodbye\sWorld.")

This should work: (inplace editing)
import fileinput
# Does a list of files, and
# redirects STDOUT to the file in question
for line in fileinput.input(files, inplace = 1):
print line.replace("foo", "bar"),

Based on the answer by Thomas Watnedal.
However, this does not answer the line-to-line part of the original question exactly. The function can still replace on a line-to-line basis
This implementation replaces the file contents without using temporary files, as a consequence file permissions remain unchanged.
Also re.sub instead of replace, allows regex replacement instead of plain text replacement only.
Reading the file as a single string instead of line by line allows for multiline match and replacement.
import re
def replace(file, pattern, subst):
# Read contents from file as a single string
file_handle = open(file, 'r')
file_string = file_handle.read()
file_handle.close()
# Use RE package to allow for replacement (also allowing for (multiline) REGEX)
file_string = (re.sub(pattern, subst, file_string))
# Write contents to file.
# Using mode 'w' truncates the file.
file_handle = open(file, 'w')
file_handle.write(file_string)
file_handle.close()

As lassevk suggests, write out the new file as you go, here is some example code:
fin = open("a.txt")
fout = open("b.txt", "wt")
for line in fin:
fout.write( line.replace('foo', 'bar') )
fin.close()
fout.close()

If you're wanting a generic function that replaces any text with some other text, this is likely the best way to go, particularly if you're a fan of regex's:
import re
def replace( filePath, text, subs, flags=0 ):
with open( filePath, "r+" ) as file:
fileContents = file.read()
textPattern = re.compile( re.escape( text ), flags )
fileContents = textPattern.sub( subs, fileContents )
file.seek( 0 )
file.truncate()
file.write( fileContents )

A more pythonic way would be to use context managers like the code below:
from tempfile import mkstemp
from shutil import move
from os import remove
def replace(source_file_path, pattern, substring):
fh, target_file_path = mkstemp()
with open(target_file_path, 'w') as target_file:
with open(source_file_path, 'r') as source_file:
for line in source_file:
target_file.write(line.replace(pattern, substring))
remove(source_file_path)
move(target_file_path, source_file_path)
You can find the full snippet here.

fileinput is quite straightforward as mentioned on previous answers:
import fileinput
def replace_in_file(file_path, search_text, new_text):
with fileinput.input(file_path, inplace=True) as file:
for line in file:
new_line = line.replace(search_text, new_text)
print(new_line, end='')
Explanation:
fileinput can accept multiple files, but I prefer to close each single file as soon as it is being processed. So placed single file_path in with statement.
print statement does not print anything when inplace=True, because STDOUT is being forwarded to the original file.
end='' in print statement is to eliminate intermediate blank new lines.
You can used it as follows:
file_path = '/path/to/my/file'
replace_in_file(file_path, 'old-text', 'new-text')

Create a new file, copy lines from the old to the new, and do the replacing before you write the lines to the new file.

Expanding on #Kiran's answer, which I agree is more succinct and Pythonic, this adds codecs to support the reading and writing of UTF-8:
import codecs
from tempfile import mkstemp
from shutil import move
from os import remove
def replace(source_file_path, pattern, substring):
fh, target_file_path = mkstemp()
with codecs.open(target_file_path, 'w', 'utf-8') as target_file:
with codecs.open(source_file_path, 'r', 'utf-8') as source_file:
for line in source_file:
target_file.write(line.replace(pattern, substring))
remove(source_file_path)
move(target_file_path, source_file_path)

Using hamishmcn's answer as a template I was able to search for a line in a file that match my regex and replacing it with empty string.
import re
fin = open("in.txt", 'r') # in file
fout = open("out.txt", 'w') # out file
for line in fin:
p = re.compile('[-][0-9]*[.][0-9]*[,]|[-][0-9]*[,]') # pattern
newline = p.sub('',line) # replace matching strings with empty string
print newline
fout.write(newline)
fin.close()
fout.close()

if you remove the indent at the like below, it will search and replace in multiple line.
See below for example.
def replace(file, pattern, subst):
#Create temp file
fh, abs_path = mkstemp()
print fh, abs_path
new_file = open(abs_path,'w')
old_file = open(file)
for line in old_file:
new_file.write(line.replace(pattern, subst))
#close temp file
new_file.close()
close(fh)
old_file.close()
#Remove original file
remove(file)
#Move new file
move(abs_path, file)

Categories