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)
I have text file which contains lines of text and IPs with port number and I want to remove port number and print just IP.
Example text file:
77.55.211.77:8080
NoIP
79.127.57.42:80
Desired output:
77.55.211.77
79.127.57.42
My code:
import re
with open('IPs.txt', 'r') as infile:
for ip in infile:
ip = ip.strip('\n')
IP_without_port_number = re.sub(r'((?::))(?:[0-9]+)$', "", ip)
re_for_IP = re.match(r'^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$',ip)
print(IP_without_port_number)
I am not understand why I see all lines as output when I am printing to console "IP_without_port_number"
All you need is the second match:
import re
with open('IPs.txt', 'r') as infile:
for ip in infile:
re_for_IP = re.match(r'(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})', ip)
if re_for_IP:
print(re_for_IP[0])
Output:
77.55.211.77
79.127.57.42
One-liner:
import re
ips = []
with open('IPs.txt', 'r') as infile:
ips = [ip[0] for ip in [re.match(r'(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})', ip) for ip in infile] if ip]
print(ips)
You don't need regex, use the split function on the : character when reading the line. Then you would be left with an array with two positions, the first containing only the IP address and the other containing the port.
Try this:
import re
regex = '''^(25[0-5]|2[0-4][0-9]|[0-1]?[0-9][0-9]?)\.(
25[0-5]|2[0-4][0-9]|[0-1]?[0-9][0-9]?)\.(
25[0-5]|2[0-4][0-9]|[0-1]?[0-9][0-9]?)\.(
25[0-5]|2[0-4][0-9]|[0-1]?[0-9][0-9]?)$'''
with open('IP.txt', 'r') as infile:
for ip in infile:
ip = ip.strip('\n')
IP_without_port_number = re.sub(r':.*$', "", ip)
re_for_IP = re.match(r'^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$',ip)
if(re.search(regex, IP_without_port_number)):
print(IP_without_port_number)
Output:
77.55.211.77
79.127.57.42
I came up wit this regex code, it works for me and its easy.
import re
text = input("Input text: ")
pattern = re.findall(r'\d+\.\d+\.\d+\.\d+', text)
print(pattern)
I want to apply regex for every newline in my txt file.
For example
comments={ts=2010-02-09T04:05:20.777+0000,comment_id=529590|2886|LOL|Baoping Wu|529360}
comments={ts=2010-02-09T04:20:53.281+0000, comment_id=529589|2886|cool|Baoping Wu|529360}
comments={ts=2010-02-09T05:19:19.802+0000,comment_id=529591|2886|ok|Baoping Wu|529360}
My Python Code is:
import re
p = re.compile(ur'(comment_id=)(\d+)\|(\d+)\|([^|]+)\|([^|]+)\|(\d+)', re.MULTILINE|re.DOTALL)
#open =
test_str = r"comments={ts=2010-02-09T04:05:20.777+0000, comment_id=529590|2886|LOL|Baoping Wu|529360}"
subst = ur"\1\2, user_id = \3, comment='\4', user= '\5', post_commented=\6"
result = re.sub(p, subst, test_str)
print result
I want to solve it with help of MULTILINE, but it doesnt Work.
Can anyone help me
The Output for the first line should be
comments={ts=2010-02-09T04:05:20.777+0000, comment_id=529590, user_id = 2886, comment='LOL', user= 'Baoping Wu', post_commented=529360}
My issue is only to apply the regex for every line and write it on txt file.
Your regex works without having to use MULTILINE or DOTALL. You can replace through the entire document at once. In action
import re
with open('file.txt', 'r') as f:
txt = f.read()
pattern = r'(comment_id=)(\d+)\|(\d+)\|([^|]+)\|([^|]+)\|(\d+)'
repl = r"\1\2, user_id = \3, comment='\4', user= '\5', post_commented=\6"
result = re.sub(pattern, repl, txt)
with open('file2.txt', 'w') as f:
f.write(result)
import os
import sys
import re
import string
f=open('./iprange','r')
s=f.readline()
f.close()
pattern='inet addr:'+s
pattern=pattern.split('x')[0]
pattern='('+pattern+'...'+')'
os.system('ifconfig -a >> interfaces')
f=open('./interfaces','r')
s=f.readline()
while (len(s))!=0:
i=re.search(pattern,s)
if i!=None:
sp=re.split(pattern,s)[1]
ip=re.split('inet addr:',sp)[1]
break
s=f.readline()
f.close()
os.system('rm ./interfaces')
f=open('./userip','w')
f.write(ip)
f.close()
NameError;name 'ip' is not defined
I split pattern by s and store the result in sp, then I find the IP address and store the result in ip. But the error says ip is not defined - what's going on?
while (len(s))!=0:
i=re.search(pattern,s)
if i!=None:
sp=re.split(pattern,s)[1]
ip=re.split('inet addr:',sp)[1]
break
s=f.readline()
The ip assignment is inside the if closure, which is apparently never being executed.
I'd do something more like this:
import os
import sys
import re
from itertools import takewhile
with open('./iprange','r') as f:
s = f.readline()
prefix = 'inet addr:'
pattern = prefix + s
pattern = pattern.split('x')[0]
pattern = '(%s...)' % pattern
os.system('ifconfig -a >> interfaces')
with open('interfaces', 'r') as f:
# Put all lines up to the first empty line into a list
# http://docs.python.org/2/library/itertools.html#itertools.takewhile
# `[line.rstrip() for line in f]` could be a generator instead:
# (line.rstrip() for line in f)
lines = list(takewhile(lambda x: x, [line.rstrip() for line in f]))
os.remove('interfaces')
for s in lines:
if re.search(pattern, s):
sp = re.split(pattern, s)[1]
ip = sp[len(prefix):]
with open('./userip', 'w') as f:
f.write(ip)
break
else:
print "No match found"
For one thing, you only write to the file userip if you find a match and you get a message if no match was found.