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)
This Python code runs but prints the last page of the text file. Not sure why, but I aim to print the whole line of text that is underneath a specified line of text (a line that contains the specific string ** Direct **). How can I loop through a text file, search each line for the specified string, and whenever it is found print the row directly below it? I have searched many online forums and have not found an easily understandable example. I use Python Sypder 2.7. Any help appreciated
import os
Path = '..\\Test.txt'
if os.path.isfile(Path):
with open(Path) as f:
for line in f:
print line
else:
print Path, "doesn't exist"
f.close()
Python 3.x:
dummy.txt
Mango
Anday Wala Burger
40
Aloo
Anday
Ghobi
Anday Wala Burger
30
Kheerey
Anday Wala Burger
py:
searchString = 'Anday Wala Burger'
with open('dummy.txt', "r") as input:
try:
for line in input:
if searchString in line:
print(next(input), end='')
except StopIteration:
pass
OUTPUT:
40
30
EDIT:
Python 2.7:
dummyFile= "dummy.txt"
searchString = 'Anday Wala Burger'
with open(dummyFile) as f:
content = f.readlines()
# you may also want to remove empty lines
content = [l.strip() for l in content if l.strip()]
# flag
nextLine = False
for line in content:
if searchString in line:
nextLine = not nextLine
else:
if nextLine:
print(line)
nextLine = not nextLine
else:
pass
OUTPUT:
40
30
You need to make some changes:
1.-Read the lines
2.- Compare with your text
import os
Path = '..\\Test.txt'
look='**Direct**'
if os.path.isfile(Path):
with open(Path, "r") as f:
for line in f:
if look in line:
print (line)
else:
print (Path, "doesn't exist")
Check out the re module. It includes the re.search() function, which searches for a pattern inside a string.
To print the next line you can take advantage of the fact that file objects are iterable, by using f.next().
For example, you could do:
import os
import re
Path = 'foo.txt'
Pattern = "spam" # String to be searched
if os.path.isfile(Path):
with open(Path) as f:
for line in f:
if re.search(Pattern, line):
print(f.next())
else:
print(Path, "doesn't exist")
By the way, you don't need that final f.close(). It is already taken care of by the with statement.
Check if one is in any line in the file and the print the next line as found will be the next lineno file will be set as currentlineno+1
Contents of file temp
one
two
three
four
Python file
with open('temp') as f:
found=-1
#no lines are found to print so found is negative in value since line no in a file cannot be negative
for index,line in enumerate(f):
if found==index:
print(line)
if 'one' in line:
found=index+1
# when the condition is True found is set to the line no that we need to print
Output
two
Am Writing a program that prompts for a file name, then opens that file and reads through the file, looking for lines of the form:
X-DSPAM-Confidence: 0.8475
I want to count these lines and extract the floating point values from each of the lines and compute the average of those values. Can I please get some help. I just started programming so I need something very simple. This is the code I have already written.
fname = raw_input("Enter file name: ")
if len(fname) == 0:
fname = 'mbox-short.txt'
fh = open(fname,'r')
count = 0
total = 0
#Average = total/num of lines
for line in fh:
if not line.startswith("X-DSPAM-Confidence:"): continue
count = count+1
print line
Try:
total += float(line.split(' ')[1])
so that total / count gives you the answer.
Iterate over the file (using the context manager ("with") handles the closing automatically), looking for such lines (like you did), and then read them in like this:
fname = raw_input("Enter file name:")
if not fname:
fname = "mbox-short.txt"
scores = []
with open(fname) as f:
for line in f:
if not line.startswith("X-DSPAM-Confidence:"):
continue
_, score = line.split()
scores.append(float(score))
print sum(scores)/len(scores)
Or a bit more compact:
mean = lambda x: sum(x)/len(x)
with open(fname) as f:
result = mean([float(l.split()[1]) if line.startswith("X-DSPAM-Confidence:") for l in f])
A program like the following should satisfy your needs. If you need to change what the program is looking for, just change the PATTERN variable to describe what you are trying to match. The code is written for Python 3.x but can be adapted for Python 2.x without much difficulty if needed.
Program:
#! /usr/bin/env python3
import re
import statistics
import sys
PATTERN = r'X-DSPAM-Confidence:\s*(?P<float>[+-]?\d*\.\d+)'
def main(argv):
"""Calculate the average X-DSPAM-Confidence from a file."""
filename = argv[1] if len(argv) > 1 else input('Filename: ')
if filename in {'', 'default'}:
filename = 'mbox-short.txt'
print('Average:', statistics.mean(get_numbers(filename)))
return 0
def get_numbers(filename):
"""Extract all X-DSPAM-Confidence values from the named file."""
with open(filename) as file:
for line in file:
for match in re.finditer(PATTERN, line, re.IGNORECASE):
yield float(match.groupdict()['float'])
if __name__ == '__main__':
sys.exit(main(sys.argv))
You may also implement the get_numbers generator in the following way if desired.
Alternative:
def get_numbers(filename):
"""Extract all X-DSPAM-Confidence values from the named file."""
with open(filename) as file:
yield from (float(match.groupdict()['float'])
for line in file
for match in re.finditer(PATTERN, line, re.IGNORECASE))
Currently, I'm trying to search for an exact word/phrase in a text file. I am using Python 3.4
Here is the code I have so far.
import re
def main():
fileName = input("Please input the file name").lower()
term = input("Please enter the search term").lower()
fileName = fileName + ".txt"
regex_search(fileName, term)
def regex_search(file,term):
source = open(file, 'r')
destination = open("new.txt", 'w')
lines = []
for line in source:
if re.search(term, line):
lines.append(line)
for line in lines:
destination.write(line)
source.close()
destination.close()
'''
def search(file, term): #This function doesn't work
source = open(file, 'r')
destination = open("new.txt", 'w')
lines = [line for line in source if term in line.split()]
for line in lines:
destination.write(line)
source.close()
destination.close()'''
main()
In my function regex_search I use regex to search for the particular string. However, I don't know how to search for a particular phrase.
In the second function, search, I split the line into a list and search for the word in there. However, this won't be able to search for a particular phrase because I am searching for ["dog walked"] in ['the','dog','walked'] which won't return the correct lines.
edit: Considering that you don't want to match partial words ('foo' should not match 'foobar'), you need to look ahead in the data stream. The code for that is a bit awkward, so I think regex (your current regex_search with a fix) is the way to go:
def regex_search(filename, term):
searcher = re.compile(term + r'([^\w-]|$)').search
with open(file, 'r') as source, open("new.txt", 'w') as destination:
for line in source:
if searcher(line):
destination.write(line)