I need some help, I have a a txt file with spaces between words, I want to replace the space with underscore.
fileHandler = open('nog_rename_update.txt')
for eachline in fileHandler:
new_name = fileHandler.replace(" ","_")
print(new_name)
That's my code but it keeps throwing error messages
new_name = fileHandler.replace(" ","_")
AttributeError: '_io.TextIOWrapper' object has no attribute 'replace'
example files that I want to remove space and add underscore
Here's a generic approach that should work for you:
teststring = 'hello world this is just a test. don\'t mind me 123.'
# replace multiple spaces with one space
while ' ' in teststring:
teststring = teststring.replace(' ', ' ')
# replace space with underscore (_)
teststring = teststring.replace(' ', '_')
print(teststring)
assert teststring == "hello_world_this_is_just_a_test._don't_mind_me_123." # True
Using a file example:
fname = 'mah_file.txt'
with open(fname) as in_file:
contents = in_file.read()
while ' ' in contents:
contents = contents.replace(' ', ' ')
# write updated contents back to file
with open(fname, 'w') as out_file:
out_file.write(contents.replace(' ', '_'))
This opens the files, reads line by line, splits the line into two parts, and combines the two parts with an underscore. I stored it in a list that you can use to do your next step.
with open('nog_rename_update.txt') as f:
new_list = []
for line in f:
# split the line
split = line.split()
new_list.append(split[0]+"_"+split[1])
# print the list to see results
print(new_list)
#
# add code to loop through the new list and to write to a file
#
Try out this
fileHandler = open('nog_rename_update.txt').read()
new_name = fileHandler.replace(" ", "_")
print(new_name)
f = open("test.txt", "r")
text=f.read()
f.close()
f=open("testfile.txt", "w+")
text2=''
if ' ' in text:
text2 = text.replace(' ' , '_')
print(text2)
f.write(text2)
f.close()
Here is another, less verbose solution. Simply use re.sub:
import re
file_name = r"D:\projects\playground\python\data\test.txt"
with open(file_name, "r") as file:
for line in file:
print(re.sub("( )+", "_", line), end="")
And if you want to replace the spaces in your text file:
import re
file_name = r"D:\projects\playground\python\data\test.txt"
lines = []
with open(file_name, "r") as file:
lines = [
re.sub("( )+", "_", line) for line in file.readlines()
]
with open(file_name, "w") as file:
file.writelines(lines)
Or use fileinput:
import re
import fileinput
file_name = r"D:\projects\playground\python\data\test.txt"
with fileinput.FileInput(file_name, inplace=True, backup=".bak") as file:
for line in file:
print(re.sub("( )+", "_", line), end="")
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)
What I want to do:
a) open all files in directory (in this case: chapters from long stories)
b) remove all empty lines
c) find sentences started with "- " (in this case: dialogues)
I was able to create code that works well, but only for one file:
file = open('.\\stories\\test\\01.txt', 'r', encoding="utf-16 LE")
string_with_empty_lines = file.read()
lines = string_with_empty_lines.split("\n")
non_empty_lines = [line for line in lines if line.strip() != ""]
string_without_empty_lines = ""
for line in non_empty_lines:
if line.startswith('- '):
string_without_empty_lines += line + "\n"
print(string_without_empty_lines)
I started mixed up with this because I have a lot of files and I want to open them all and print the results from all files (and probably save all results to one file, but it's not necessary right now). The first part of the new code successfully open files (checked with commented print line), but when I add the part with editing, nothing happens at all (I don't even have errors in console).
import os
import glob
folder_path = os.path.join('G:' '.\\stories\\test')
for filename in glob.glob(os.path.join(folder_path, '**', '*.txt'), recursive=True):
with open(filename, 'r', encoding="utf-16 LE") as f:
string_with_empty_lines = f.read()
# print(string_with_empty_lines)
lines = string_with_empty_lines.split("\n")
non_empty_lines = [line for line in lines if line.strip() != ""]
string_without_empty_lines = ""
for line in non_empty_lines:
if line.startswith("- "):
string_without_empty_lines += line + "\n"
print(string_without_empty_lines)
If you have your source files in the source_dir and you want to output the target files in the target_dir, you can do it like that:
import os
import path
source_dir = "source_dir"
target_dir = "target_dir"
# on linux or mac, you can get filenames in the specific dir.
# not sure what will happen on Windows
filenames = os.listdir(source_dir)
for filename in filenames:
# get full path of source and target file
filepath_source = path.join(source_dir, filename)
filepath_target = path.join(target_dir, filename)
# open source file and target file
with open(filepath_source) as f_source, open(filepath_target, 'w') as f_target:
for line in f_source:
if len(line.strip()) == 0:
continue
if line[0] == '-':
# do something
f_target.write(line)
On the example of one file, if there are more files, before you can say smt like
for file in dir: with open(file) ...., remember that you would also have to change the target file
with open('source.txt') as source:
with open('target.txt','w') as target:
for line in source.readlines():
l = line.strip('\n')
# identify if the 1st char is '-'
if l[0] == '-':
# do somethin e.g. add 'dialog' at the beginning...
# skip empty line
if len(l) == 0:
continue
#Rewrite to target file
target.write(l + '\n')
target.close()
source.close()
I have a folder full of .mpt files, each of them having the same data format.
I need to delete the first 57 lines from all files and append these files into one csv - output.csv.
I have that section already:
import glob
import os
dir_name = 'path name'
lines_to_ignore = 57
input_file_format = '*.mpt'
output_file_name = "output.csv"
def convert():
files = glob.glob(os.path.join(dir_name, input_file_format))
with open(os.path.join(dir_name, output_file_name), 'w') as out_file:
for f in files:
with open(f, 'r') as in_file:
content = in_file.readlines()
content = content[lines_to_ignore:]
for i in content:
out_file.write(i)
print("working")
convert()
print("done")
This part works ok.
how do i add the filename of each .mpt file as the last column of the output.csv
Thank you!
This is a quick 'n dirty solution.
In this loop the variable i is just a string (a line from a CSV file):
for i in content:
out_file.write(i)
So you just need to 1) strip off the end of line character(s) (either "\n" or "\r\n") and append ",".
If you're using Unix, try:
for i in content:
i = i.rstrip("\n") + "," + output_file_name + "\n"
out_file.write(i)
This assumes that the field separator is a comma. Another option is:
for i in content:
i = i.rstrip() + "," + output_file_name
print >>out_file, i
This will strip all white space from the end of i.
Add quotes if you need to quote the output file name:
i = i.rstrip(...) + ',"' + output_file_name '"'
The relevant part:
with open(f, 'r') as in_file:
content = in_file.readlines()
content = content[lines_to_ignore:]
for i in content:
new_line = ",".join([i.rstrip(), f]) + "\n" #<-- this is new
out_file.write(new_line) #<-- this is new