Develop Reference

Python - open all txt files, remove empty lines and find a specific character

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()

How to edit specific line for all text files in a folder by python?

Here below is my code about how to edit text file.
Since python can't just edit a line and save it at the same time,
I save the previous text file's content into a list first then write it out.
For example,if there are two text files called sample1.txt and sample2.txt in the same folder.
Sample1.txt
A for apple.
Second line.
Third line.
Sample2.txt
First line.
An apple a day.
Third line.
Execute python
import glob
import os
#search all text files which are in the same folder with python script
path = os.path.dirname(os.path.abspath(__file__))
txtlist = glob.glob(path + '\*.txt')
for file in txtlist:
fp1 = open(file, 'r+')
strings = [] #create a list to store the content
for line in fp1:
if 'apple' in line:
strings.append('banana\n') #change the content and store into list
else:
strings.append(line) #store the contents did not be changed
fp2 = open (file, 'w+') # rewrite the original text files
for line in strings:
fp2.write(line)
fp1.close()
fp2.close()
Sample1.txt
banana
Second line.
Third line.
Sample2.txt
First line.
banana
Third line.
That's how I edit specific line for text file.
My question is : Is there any method can do the same thing?
Like using the other functions or using the other data type rather than list.
Thank you everyone.

Simplify it to this:
with open(fname) as f:
content = f.readlines()
content = ['banana' if line.find('apple') != -1 else line for line in content]
and then write value of content to file back.

Instead of putting all the lines in a list and writing it, you can read it into memory, replace, and write it using same file.
def replace_word(filename):
with open(filename, 'r') as file:
data = file.read()
data = data.replace('word1', 'word2')
with open(filename, 'w') as file:
file.write(data)
Then you can loop through all of your files and apply this function

The built-in fileinput module makes this quite simple:
import fileinput
import glob
with fileinput.input(files=glob.glob('*.txt'), inplace=True) as files:
for line in files:
if 'apple' in line:
print('banana')
else:
print(line, end='')
fileinput redirects print into the active file.

import glob
import os
def replace_line(file_path, replace_table: dict) -> None:
list_lines = []
need_rewrite = False
with open(file_path, 'r') as f:
for line in f:
flag_rewrite = False
for key, new_val in replace_table.items():
if key in line:
list_lines.append(new_val+'\n')
flag_rewrite = True
need_rewrite = True
break # only replace first find the words.
if not flag_rewrite:
list_lines.append(line)
if not need_rewrite:
return
with open(file_path, 'w') as f:
[f.write(line) for line in list_lines]
if __name__ == '__main__':
work_dir = os.path.dirname(os.path.abspath(__file__))
txt_list = glob.glob(work_dir + '/*.txt')
replace_dict = dict(apple='banana', orange='grape')
for txt_path in txt_list:
replace_line(txt_path, replace_dict)

Python; trying to add these files line by line with a tab inbetween

I'm reading in text files from the command line and I'm trying to produce output as follows...
Desired output given these command line arguments
Essentially, I want to read in files from the command line; take the first line from each file & print them on one line separated by a tab. Take the second line from each file & print them on the next line separated by a tab & so on.
This is the best code I've come up with (I'm a beginner and I've tried looking at other responses for far too long; glob & os hasn't been helping me understand how to do this; I'd just like to use basic loops and opening of files to do this):
import sys
l = []
list_files = sys.argv[:1]
for fname in list_files:
open(fname) as infile:
for line in infile:
line = line.strip()
if line == '':
l.append("''")
else:
l.append(line)
print(l) # List of all appended animals. Not in the right order
#(takes all names from one file, then all the names from the
#next instead of taking one line from every file on each iteration)

This is a minimally changed version that should work.
import sys
from itertools import zip_longest
files = []
list_files = sys.argv[:1]
for fname in list_files:
with open(fname) as infile: # Don't forget the `with`!
l = []
for line in infile:
line = line.strip()
if line == '':
l.append("''")
else:
l.append(line)
files.append(l) # list of lists
for lines in zip_longest(*files, fillvalue=''): # transpose list of lists
print(*lines, sep='\t') # separate with tabs.

The best way to open files in python is with with. More information can be found at https://www.pythonforbeginners.com/files/with-statement-in-python. Anyways:
import sys
if len(sys.argv) != 3:
sys.exit(1)
filename1 = sys.argv[1]
filename2 = sys.argv[2]
with open(filename1, 'r') as file1, open(filename2, 'r') as file2:
for line1, line2 in zip(file1, file2):
print(line1.strip(), line2.strip(), sep='\t')
This can be changed to allow for more than two files:
import sys
if len(sys.argv) != 3:
sys.exit(1)
filenames = sys.argv[1:]
all_lines = []
for filename in filenames:
with open(filename, 'r') as file:
all_lines.append([l.strip() for l in file.readlines()])
for line in zip(*all_lines):
print(*line, sep='\t')

How to replace a string in a file?

I have 2 numbers in two similar files. There is a new.txt and original.txt. They both have the same string in them except for a number. The new.txt has a string that says boothNumber="3". The original.txt has a string that says boothNumber="1".
I want to be able to read the new.txt, pick the number 3 out of it and replace the number 1 in original.txt.
Any suggestions? Here is what I am trying.
import re # used to replace string
import sys # some of these are use for other code in my program
def readconfig():
with open("new.text") as f:
with open("original.txt", "w") as f1:
for line in f:
match = re.search(r'(?<=boothNumber=")\d+', line)
for line in f1:
pattern = re.search(r'(?<=boothNumber=")\d+', line)
if re.search(pattern, line):
sys.stdout.write(re.sub(pattern, match, line))
When I run this, my original.txt gets completely cleared of any text.
I did a traceback and I get this:
in readconfig
for line in f1:
io.UnsupportedOperationo: not readable
UPDATE
I tried:
def readconfig(original_txt_path="original.txt",
new_txt_path="new.txt"):
with open(new_txt_path) as f:
for line in f:
if not ('boothNumber=') in line:
continue
booth_number = int(line.replace('boothNumber=', ''))
# do we need check if there are more than one 'boothNumber=...' line?
break
with open(original_txt_path) as f1:
modified_lines = [line.startswith('boothNumber=') if not line
else 'boothNumber={}'.format(booth_number)
for line in f1]
with open(original_txt_path, mode='w') as f1:
f1.writelines(modified_lines)
And I get error:
booth_number = int(line.replace('boothNumber=', ''))
ValueError: invalid literal for int() with base 10: '
(workstationID="1" "1" window=1= area="" extra parts of the line here)\n
the "1" after workstationID="1" is where the boothNumber=" " would normally go. When I open up original.txt, I see that it actually did not change anything.
UPDATE 3
Here is my code in full. Note, the file names are changed but I'm still trying to do the same thing. This is another idea or revision I had that is still not working:
import os
import shutil
import fileinput
import re # used to replace string
import sys # prevents extra lines being inputed in config
# example: sys.stdout.write
def convertconfig(pattern):
source = "template.config"
with fileinput.FileInput(source, inplace=True, backup='.bak') as file:
for line in file:
match = r'(?<=boothNumber=")\d+'
sys.stdout.write(re.sub(match, pattern, line))
def readconfig():
source = "bingo.config"
pattern = r'(?<=boothNumber=")\d+' # !!!!!!!!!! This probably needs fixed
with fileinput.FileInput(source, inplace=True, backup='.bak') as file:
for line in file:
if re.search(pattern, line):
fileinput.close()
convertconfig(pattern)
def copyfrom(servername):
source = r'//' + servername + '/c$/remotedirectory'
dest = r"C:/myprogram"
file = "bingo.config"
try:
shutil.copyfile(os.path.join(source, file), os.path.join(dest, file))
except:
print ("Error")
readconfig()
# begin here
os.system('cls' if os.name == 'nt' else 'clear')
array = []
with open("serverlist.txt", "r") as f:
for servername in f:
copyfrom(servername.strip())
bingo.config is my new file
template.config is my original
It's replacing the number in template.config with the literal string "r'(?<=boothNumber=")\d+'"
So template.config ends up looking like
boothNumber="r'(?<=boothNumber=")\d+'"
instead of
boothNumber="2"

To find boothNumber value we can use next regular expression (checked with regex101)
(?<=\sboothNumber=\")(\d+)(?=\")
Something like this should work
import re
import sys # some of these are use for other code in my program
BOOTH_NUMBER_RE = re.compile('(?<=\sboothNumber=\")(\d+)(?=\")')
search_booth_number = BOOTH_NUMBER_RE.search
replace_booth_number = BOOTH_NUMBER_RE.sub
def readconfig(original_txt_path="original.txt",
new_txt_path="new.txt"):
with open(new_txt_path) as f:
for line in f:
search_res = search_booth_number(line)
if search_res is None:
continue
booth_number = int(search_res.group(0))
# do we need check if there are more than one 'boothNumber=...' line?
break
else:
# no 'boothNumber=...' line was found, so next lines will fail,
# maybe we should raise exception like
# raise Exception('no line starting with "boothNumber" was found')
# or assign some default value
# booth_number = -1
# or just return?
return
with open(original_txt_path) as f:
modified_lines = []
for line in f:
search_res = search_booth_number(line)
if search_res is not None:
line = replace_booth_number(str(booth_number), line)
modified_lines.append(line)
with open(original_txt_path, mode='w') as f:
f.writelines(modified_lines)
Test
# Preparation
with open('new.txt', mode='w') as f:
f.write('some\n')
f.write('<jack Fill workstationID="1" boothNumber="56565" window="17" Code="" area="" section="" location="" touchScreen="False" secureWorkstation="false">')
with open('original.txt', mode='w') as f:
f.write('other\n')
f.write('<jack Fill workstationID="1" boothNumber="23" window="17" Code="" area="" section="" location="" touchScreen="False" secureWorkstation="false">')
# Invocation
readconfig()
# Checking output
with open('original.txt') as f:
for line in f:
# stripping newline character
print(line.rstrip('\n'))
gives
other
<jack Fill workstationID="1" boothNumber="56565" window="17" Code="" area="" section="" location="" touchScreen="False" secureWorkstation="false">

How do I search a file for a string and replace it with multiple lines in Python?

I am running Python 3.5.1
I have a text file that I'm trying to search through and replace or overwrite text if it matches a predefined variable. Below is a simple example:
test2.txt
A Bunch of Nonsense Stuff
############################
# More Stuff Goes HERE #
############################
More stuff here
Outdated line of information that has no comment above - message_label
The last line in this example needs to be overwritten so the new file looks like below:
test2.txt after script
A Bunch of Nonsense Stuff
############################
# More Stuff Goes HERE #
############################
More stuff here
# This is an important line that needs to be copied
Very Important Line of information that the above line is a comment for - message_label
The function I have written idealAppend does not work as intended and subsequent executions create a bit of a mess. My workaround has been to separate the two lines into single line variables but this doesn't scale well. I want to use this function throughout my script with the ability to handle any number of lines. (if that makes sense)
Script
#!/usr/bin/env python3
import sys, fileinput, os
def main():
file = 'test2.txt'
fullData = r'''
# This is an important line that needs to be copied
Very Important Line of information that the above line is a comment for - message_label
'''
idealAppend(file, fullData)
def idealAppend(filename, data):
label = data.split()[-1] # Grab last word of the Append String
for line in fileinput.input(filename, inplace=1, backup='.bak'):
if line.strip().endswith(label) and line != data: # If a line 2 exists that matches the last word (label)
line = data # Overwrite with new line, comment, new line, and append data.
sys.stdout.write(line) # Write changes to current line
with open(filename, 'r+') as file: # Open File with rw permissions
line_found = any(data in line for line in file) # Search if Append exists in file
if not line_found: # If data does NOT exist
file.seek(0, os.SEEK_END) # Goes to last line of the file
file.write(data) # Write data to the end of the file
if __name__ == "__main__": main()
Workaround Script
This seems to work perfectly as long as I only need to write exactly two lines. I'd love this to be more dynamic when it comes to number of lines so I can reuse the function easily.
#!/usr/bin/env python3
import sys, fileinput, os
def main():
file = 'test2.txt'
comment = r'# This is an important line that needs to be copied'
append = r'Very Important Line of information that the above line is a comment for - message_label'
appendFile(file, comment, append)
def appendFile(filename, comment, append):
label = append.split()[-1] # Grab last word of the Append String
for line in fileinput.input(filename, inplace=1, backup='.bak'):
if line.strip().endswith(label) and line != append: # If a line 2 exists that matches the last word (label)
line = '\n' + comment + '\n' + append # Overwrite with new line, comment, new line, and append data.
sys.stdout.write(line) # Write changes to current line
with open(filename, 'r+') as file: # Open File with rw permissions
line_found = any(append in line for line in file) # Search if Append exists in file
if not line_found: # If data does NOT exist
file.seek(0, os.SEEK_END) # Goes to last line of the file
file.write('\n' + comment + '\n' + append) # Write data to the end of the file
if __name__ == "__main__": main()
I am very new to Python so I'm hoping there is a simple solution that I overlooked. I thought it might make sense to try and split the fullData variable at the new line characters into a list or tuple, filter the label from the last item in the list, then output all entries but this is starting to move beyond what I've learned so far.

If I understand your issue correctly, you can just open the input and output files, then check whether the line contains old information and ends with the label and write the appropriate content accordingly.
with open('in.txt') as f, open('out.txt', 'r') as output:
for line in f:
if line.endswith(label) and not line.startswith(new_info):
output.write(replacement_text)
else:
output.write(line)
If you want to update the original file instead of creating a second one, it's easiest to just delete the original and rename the new one instead of trying to modify it in place.

Is this what you are looking for ? It's looking for a label and then replaces the whole line with whatever you want.
test2.txt
A Bunch of Nonsense Stuff
############################
# More Stuff Goes HERE #
############################
More stuff here
Here is to be replaced - to_replace
script.py
#!/usr/bin/env python3
def main():
file = 'test2.txt'
label_to_modify = "to_replace"
replace_with = "# Blabla\nMultiline\nHello"
"""
# Raw string stored in a file
file_replace_with = 'replace_with.txt'
with open(file_replace_with, 'r') as f:
replace_with = f.read()
"""
appendFile(file, label_to_modify, replace_with)
def appendFile(filename, label_to_modify, replace_with):
new_file = []
with open(filename, 'r') as f:
for line in f:
if len(line.split()) > 0 and line.split()[-1] == label_to_modify:
new_file.append(replace_with)
else:
new_file.append(line)
with open(filename + ".bak", 'w') as f:
f.write(''.join(new_file))
if __name__ == "__main__": main()
test2.txt.bak
A Bunch of Nonsense Stuff
############################
# More Stuff Goes HERE #
############################
More stuff here
# Blabla
Multiline
Hello

Reading over both answers I've come up with the following as the best solution i can get to work. It seems to do everything I need. Thanks Everyone.
#!/usr/bin/env python3
def main():
testConfFile = 'test2.txt' # /etc/apache2/apache2.conf
testConfLabel = 'timed_combined'
testConfData = r'''###This is an important line that needs to be copied - ##-#-####
Very Important Line of information that the above line is a \"r\" comment for - message_label'''
testFormatAppend(testConfFile, testConfData, testConfLabel) # Add new test format
def testFormatAppend(filename, data, label):
dataSplit = data.splitlines()
fileDataStr = ''
with open(filename, 'r') as file:
fileData = stringToDictByLine(file)
for key, val in fileData.items():
for row in dataSplit:
if val.strip().endswith(row.strip().split()[-1]):
fileData[key] = ''
fileLen = len(fileData)
if fileData[fileLen] == '':
fileLen += 1
fileData[fileLen] = data
else:
fileLen += 1
fileData[fileLen] = '\n' + data
for key, val in fileData.items():
fileDataStr += val
with open(filename, 'w') as file:
file.writelines(str(fileDataStr))
def stringToDictByLine(data):
fileData = {}
i = 1
for line in data:
fileData[i] = line
i += 1
return fileData
if __name__ == "__main__": main()