Develop Reference

Store the contents of text file in return variable and manipulate wherever required in python?

I have below function & I am trying to get/store the contents of text file in another temp file(removing unnecessary line) with appending special character.
But I also want the same content which is in temp text file with different special character next time but I am not able to do that.Below function is creating a temp file.To get desired output I need to create file every time with same function again which is not good way.Is there anything we can do without creating a temp/extra file and store the contents in return variable and append the special character whatever we want multiple times
import os
import re
def mainfest():
pathfile = "abc_12.txt"
with open(pathfile, 'r') as firstfile, open('tmp.txt', 'r') as s:
for line in firstfile:
if line.strip().startswith("-") or line.startswith("<"):
print"ignore")
elif re.search('\\S', line):
name = str(os.path.basename(line))
s.write("*" +fname)
def contents():
temppath = "temp.txt"
with open(temp path, 'r') as f:
lines = f.readlines()
lines+= lines
return lines
manifest()
value = contents()
file abc_12.txt
---ABC-123
nice/abc.py
xml/abc.py
<<NOP-123
bac\nice.py
abc.py
---CDEF-345
jkl.oy
abc.py
I want the contents of abc_12.txt file I can get in return something like that
abc.py
abc.py
nice.py
abc.py
jkl.oy
abc.py
and manipulate them wherever I want similar to below output
Output 1:
* abc.py
* abc.py
* nice.py
* abc.py
* jkl.oy
* abc.py
Output 2:
##abc.py
##abc.py
##nice.py
##abc.py
##jkl.oy
##abc.py

Maybe first you should read file, search names and keep on list
def read_data():
results = []
with open("abc_12.txt") as infile:
for line in infile:
if line.strip().startswith(("-", "<")): # `startswith`/`endswith` can use tuple
print("ignore:", line)
elif re.search('\\S', line):
name = os.path.basename(line)
results.append(name)
return results
And later you can use this list to create temp file or other file
data = read_data()
with open('temp.txt', 'w') as outfile:
for line in data:
outfile.write(f'* {line}')
#print(f'* {line}', end='')
with open('other.txt', 'w') as outfile:
for line in data:
outfile.write(f'##{line}')
#print(f'##{line}', end='')
EDIT:
Minimal working code.
I used io.StringIO only to simulate file in memory - so everyone can simply copy and test it.
import os
import re
import io
text = r'''---ABC-123
nice/abc.py
xml/abc.py
<<NOP-123
bac\nice.py
abc.py
---CDEF-345
jkl.oy
abc.py
'''
def read_data():
results = []
with io.StringIO(text) as infile:
#with open("abc_12.txt") as infile:
for line in infile:
line = line.strip()
if line:
if line.startswith(("-", "<")): # `startswith`/`endswith` can use tuple
print("ignore:", line)
else:
name = os.path.basename(line)
results.append(name)
return results
data = read_data()
with open('temp.txt', 'w') as outfile:
for line in data:
outfile.write(f'* {line}\n')
print(f'* {line}')
with open('other.txt', 'w') as outfile:
for line in data:
outfile.write(f'##{line}\n')
print(f'##{line}')
EDIT:
If you don't want to save in file then you still need for-loop to create string
data = read_data()
string_1 = ''
for line in data:
string_1 += f'* {line}\n'
string_2 = ''
for line in data:
string_2 += f'##{line}\n'
or to create new list (and eventually string)
data = read_data()
list_1 = []
for line in data:
list_1.append(f'* {line}')
list_2 = []
for line in data:
list_2.append(f'##{line}')
string_1 = "\n".join(list_1)
string_2 = "\n".join(list_2)

How can I delete "\n" lines from a file in Python?

I need to check if the .csv file I'm working with ends with more than 1 "\n" line. If it finds more than a blank line, it removes them all but one.
My code is:
import os
from pathlib import Path
def remove_blanks():
dirname = os.path.dirname(os.path.abspath(__file__))
path: Path = Path(os.path.join(dirname, "data.csv"))
with open(path, "r+") as op:
lines = op.readlines()
for line in lines:
if line == "\n":
op.write(line.rstrip("\n"))
The .csv file is something like ['01-01-2019,0,0,0\n', '18-05-2019,33,31,48\n', '\n', '\n', '\n'] and the output I'd want is ['01-01-2019,0,0,0\n', '18-05-2019,33,31,48\n', '\n'] but it doesn't seem to be able to delete any line.

The simplest way would be to keep track if you've seen an empty line, then write one just before you write a non-empty line.
pre = ""
for line in lines:
if line == "\n":
pre = line
else:
op.write(pre)
op.write(line)
pre = "\n"
op.write(pre)
This reduces any sequence of empty lines to a single empty line, and writes that single line just before writing a non-empty line or the end of the file. When pre is the empty string, writing it is a no-op.
If you want to preserve multiple blank lines in the middle of the file, build up the sequence of blank lines in pre as you find them, and at the end of the file, only write a single blank line (rather than pre itself) if pre is not empty.
pre = ""
for line in lines:
if line == "\n":
pre += line
else:
op.write(pre)
op.write(line)
pre = ""
if pre:
op.write("\n")

Oops, never rewrite the file that you are reading: it is likely not to work or at best will lead to a maintenance nightmare.
If the file is small enough to fit in main memory, this slight change in your code could be enough:
import os.path
from pathlib import Path
def remove_blanks():
dirname = os.path.dirname(os.path.abspath(__file__))
path: Path = Path(os.path.join(dirname, "data.csv"))
with open(path, "r") as op:
lines = op.readlines() # read lines in memory
with open(path("w") as op: # re-write everything from the beginning
flag = False
for line in lines:
if line == "\n":
if not flag:
op.write(line)
flag = True
else:
op.write(line)
# flag = False # uncomment if you want to keep one blank line
# per group of consecutive lines

You could try using the Counter().
import os
from pathlib import Path
from collections import Counter
def remove_blanks():
dirname = os.path.dirname(os.path.abspath(__file__))
path: Path = Path(os.path.join(dirname, "data.csv"))
with open(path, "r+") as op:
lines = op.readlines()
for line in lines:
count = Counter()
# Add 1 for every time word appears in line
for word in line:
count[word] += 1
# Change the number of newlines to 1
if count['\n'] > 1:
count['\n'] = 1
# Returns list with the number of elements
line = list(count.elements())

I managed to work this out, with this code:
import os
from pathlib import Path
def remove_blanks():
dirname = os.path.dirname(os.path.abspath(__file__))
path: Path = Path(os.path.join(dirname, "data.csv"))
with open(path, "r") as op:
lines = op.readlines() # read lines in memory
with open(path, "w") as op: # re-write everything from the beginning
for line in lines:
if line != "\n":
op.write(line)
else:
continue
It can remove every new line in excess, no matter where it is in the file.
Thanks to everyone who tried to help me!

OOP Variable Not Defined in Python Class -Need Help Understanding __init__

I'm very new to OOP and I have been trying to write a class I can import which will help me with parsing files. I realize I do not need to make a class to do this, but thought I'd try to so I can start getting familiar with OOP.
This code works
import re
import os
destdir = r"FilePathToDirectory"
class Parsey():
def GetNums(self,source, destination, trim = True):
with open (os.path.join(destdir,source), 'r') as infile:
with open (os.path.join(destdir,destination), 'w') as outfile:
for line in infile:
#Look for number patern match
if re.match(r'(.*)\d\d-\d\d-\d\d\d\d(.*)', line):
#If trim is True clean up the line
if trim == True:
#Find the first numeric character
firstdig = re.search("\d",line)
#Set the firstdig variable to the integer of that index
firstdig = firstdig.start()
#Set the line equal to only the begining and ending indexes of the number
line=line[firstdig:firstdig+10]
#Remove the dashes from the string
line = line.replace('-','')
outfile.writelines(line+'\n')
else:
outfile.writelines(line)
This code does not and I'm not sure why it doesn't.
import re
import os
class Parsey():
def __init__(self, destdir=''):
self.destdir = r"FilePathToDirectory"
def GetNums(self,source, destination, trim = True):
with open (os.path.join(destdir,source), 'r') as infile:
with open (os.path.join(destdir,destination), 'w') as outfile:
for line in infile:
#Look for number patern match
if re.match(r'(.*)\d\d-\d\d-\d\d\d\d(.*)', line):
#If trim is True clean up the line
if trim == True:
#Find the first numeric character
firstdig = re.search("\d",line)
#Set the firstdig variable to the integer of that index
firstdig = firstdig.start()
#Set the line equal to only the begining and ending indexes of the number
line=line[firstdig:firstdig+11]
#Remove the dashes from the string
line = line.replace('-','')
outfile.writelines(line+'\n')
else:
outfile.writelines(line)
I receive the error:
line 10, in GetNums
with open (os.path.join(destdir,source), 'r') as infile:
NameError: name 'destdir' is not defined
It was my understanding that the namespace of the class object would allow the functions within the class to see all variables declared in that class.

You need to change line 10 to:
with open (os.path.join(self.destdir, destination), 'w') as outfile:
In your case Python looks for testdir inside GetNums first and, if it cannot find it there, it will look for this name in the module. It does not magically use tesdir from __init__. The name self stands for the instance you will create later. So in __init__ you essentially set mysinstance.testdir and later in GetNums you can access with mysinstance.testdir. self is just the placeholder for mysinstance, i.e the instance you create later.
You can read the detail in the documentation.

#Mike Müller nailed it, but here is the corrected code in its entirety.
import re
import os
class Parsey():
def __init__(self, destdir=''):
self.destdir = r"FilePathToDirectory"
def GetNums(self,source, destination, trim = True):
with open (os.path.join(self.destdir,source), 'r') as infile:
with open (os.path.join(self.destdir,destination), 'w') as outfile:
for line in infile:
#Look for number patern match
if re.match(r'(.*)\d\d-\d\d-\d\d\d\d(.*)', line):
#If trim is True clean up the line
if trim == True:
#Find the first numeric character
firstdig = re.search("\d",line)
#Set the firstdig variable to the integer of that index
firstdig = firstdig.start()
#Set the line equal to only the begining and ending indexes of the number
line=line[firstdig:firstdig+10]
#Remove the dashes from the string
line = line.replace('-','')
outfile.writelines(line+'\n')
else:
outfile.writelines(line)

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">

python: search file for string

I have tried to create a python function which takes in 2 parameters; a file name and a search string. In this case the file name is the script itself (script.py) and the search string is 'name = "JOHN"'
#!/usr/local/bin/python2.7
import os, sys
#################
# Variable string
name = "JOHN"
#################
# Main function
def search_script_for_string(filename, searchString):
f = open(filename,'r') #open the given filename then
filedata = f.read() #assign it to variable then
f.close() #close the open filename
for lines in filedata: #loop through each line in the filedata variable
if searchString in lines: #if search string is found, then do all of this
print ('Found string: %s') % searchString
return True
else: #if not found, then do all of this
print ('Did not find: %s') % searchString
return False
break
#################
# Pass the file name and the search string parameter to the function
search_script_for_string("test.py","name = \"" + name + "\"")
The problem is that it doesn't return expected results:
$ Did not find: name = "JOHN"
When it meant to say:
$ Found string: name = "JOHN"
If anyone can help correct my understanding of where I'm going wrong here, I'd be massively appreciative. Thanks

f.read() returns the entire contents of the file as a single string. You then iterate over those contents -- but iterating over a string yields only 1 character at a time so there is no way a character will contain the substring you are looking for.
def search_script_for_string(filename, searchString):
with open(filename, 'r') as f:
return searchString in f.read()
should do the trick. Alternatively, if you want to search line-by-line:
def search_script_for_string(filename, searchString):
with open(filename, 'r') as f:
for line in f:
return searchString in line

You are iterating over each character of the file by calling for c in f.read().
Use for line in f and you will indeed iterate over each line.
Also prefer the use of with, this makes your code a lot more robust.
So this would be better:
with open('fileName') as f:
for line in f:
#process