Develop Reference

Deleting a specific word form a text file in python

I used this code to delete a word from a text file.
f = open('./test.txt','r')
a = ['word1','word2','word3']
lst = []
for line in f:
for word in a:
if word in line:
line = line.replace(word,'')
lst.append(line)
f.close()
f = open('./test.txt','w')
for line in lst:
f.write(line)
f.close()
But for some reason if the words have the same characters, all those characters get deleted. So for e.g
in my code:
def cancel():
global refID
f1=open("refID.txt","r")
line=f1.readline()
flag = 0
while flag==0:
refID=input("Enter the reference ID or type 'q' to quit: ")
for i in line.split(','):
if refID == i:
flag=1
if flag ==1:
print("reference ID found")
cancelsub()
elif (len(refID))<1:
print("Reference ID not found, please re-enter your reference ID\n")
cancel()
elif refID=="q":
flag=1
else:
print("reference ID not found\n")
menu()
def cancelsub():
global refIDarr, index
refIDarr=[]
index=0
f = open('flightbooking.csv')
csv_f = csv.reader(f)
for row in csv_f:
refIDarr.append(row[1])
for i in range (len(refIDarr)):
if refID==refIDarr[i]:
index=i
print(index)
while True:
proceed=input("You are about to cancel your flight booking, are you sure you would like to proceed? y/n?: ")
while proceed>"y" or proceed<"n" or (proceed>"n" and proceed<"y") :
proceed=input("Invalid entry. \nPlease enter y or n: ")
if proceed=="y":
Continue()
break
elif proceed=="n":
main_menu
break
exit
break
def Continue():
lines = list()
with open('flightbooking.csv', 'r') as readFile:
reader = csv.reader(readFile)
for row in reader:
lines.append(row)
for field in row:
if field ==refID:
lines.remove(row)
break
with open('flightbooking.csv', 'w') as writeFile:
writer = csv.writer(writeFile)
writer.writerows(lines)
f = open('refID.txt','r')
a=refIDarr[index]
print(a)
lst = []
for line in f:
for word in a:
if word in line:
line = line.replace(word,'')
lst.append(line)
print(lst)
f.close()
f = open('refID.txt','w')
for line in lst:
f.write(line)
f.close()
print("Booking successfully cancelled")
menu()
When the code is run, the refID variable has one word stored in it, and it should replace just that word with a blank space, but it takes that word for e.g 'AB123', finds all other words which might have an 'A' or a 'B' or the numbers, and replace all of them. How do I make it so it only deletes the word?
Text file before running code:
AD123,AB123
Expected Output in the text file:
AD123,
Output in text file:
D,
Edit: I have added the entire code, and maybe you can help now after seeing that the array is being appended to and then being used to delete from a text file.

here's my opinion.
refIDarr = ["AB123"]
a = refIDarr[0] => a = "AB123"
strings in python are iterable, so when you do for word in a, you're getting 5 loops where each word is actually a letter.
Something like the following is being executed.
if "A" in line:
line = line.replace("A","")
if "B" in line:
line = line.replace("B","")
if "1" in line:
line = line.replace("1","")
if "2" in line:
line = line.replace("2","")
if "3" in line:
line = line.replace("3","")
they correct way to do this is loop over refIDarr
for word in refIDarr:
line = line.replace(word,'')
NOTE: You don't need the if statement, since if the word is not in the line it will return the same line as it was.
"abc".replace("bananan", "") => "abc"
Here's a working example:
refIDarr = ["hello", "world", "lol"]
with open('mytext.txt', "r") as f:
data = f.readlines()
for word in refIDarr:
data = [line.replace(word, "") for line in data]
with open("mytext.txt", "w") as newf:
newf.writelines(data)

The problem is here:
a=refIDarr[index]
If refIDarr is a list of words, accessing specific index makes a be a word. Later, when you iterate over a (for word in a:), word becomes a letter and not a word as you expect, which causes eventually replacing characters of word instead the word itself in your file.
To avoid that, remove a=refIDarr[index] and change your loop to be:
for line in f:
for word in refIDarr:
if word in line:
line = line.replace(word,'')

Python string compare and replace

I have a .txt with:
#Date 111111:UhUidsiIds
#Name Sebastian-Forset
#Date 222222:UdfasdUDsa
#Name Sebastian_Forset2
#Date 333333:UDsafduD
#Name Solaris Mage
#Date 444444:Ghdsasra
#Name Marge S
and a file whith:
#Name Sebastian Forset
#Date 191020
#Name Sebastian Forset2
#Date 201020
#Date Homer S
#Date 281902
The names are the same, with some differences of characters (spaces, -, _ etc.)
I would copy the numbers of the second file to the first file in order to have a final file txt with:
#Name Sebastian Forset
#Date 191020:UhUidsiIds
#Name Sebastian Forset2
#Date 201020:UdfasdUDsa
#Name Solaris Mage
#Date 281902:UDsafduD
#Name Marge S
#Date 444444:Ghdsasra
This is my code, but merge the file, copy only same name
def isInFile(l, f):
with open(f, 'r') as f2:
for line in f2:
if l == line:
return True
return False
def similitudes(file1, file2):
same = 0
data = ''
copy = False
with open(file1, 'r') as f1:
for line in f1:
if copy == True:
data += line
if line == '\n' or line[0:6] != '#Name ':
copy = False
if (line[0:6] == '#Name ') or line[0:6] == '#Date ':
print line
if isInFile(line, file2) == True:
copy = True
data += line
print "true"
else:
print "ok"
same += 1
return data
def main(argv=2):
print (sys.argv[1])
print (sys.argv[2])
if argv == 2:
out = open('final.txt', 'w')
data = (
similitudes(sys.argv[1], sys.argv[2]) + '\n'
)
out.write(data)
out.close()
else:
print ("This program need 2 files")
exit (0)
return 0
if __name__ == '__main__':
status = main()
sys.exit(status)

First, list out the characters that will differ. Let's say "-" , "_" and " ".
Now split the two strings using these delimiters. you can use "re" package in python.
>>> a='Mr-Sebastian_Forset '
>>> import re
>>> re.split('- |_ | ',a)
['Mr', 'Sebastian', 'Forset']
If the resultant lists for the two strings are equal, paste the number in second file in first one.
You can use the same delimiter concept to split the number and paste it in other file.

Adding another answer, which will points out the bug in your code
Coming to the following piece of code
if (line[0:6] == '#Name ') or line[0:6] == '#Date ':
print line
if isInFile(line, file2) == True:
copy = True
data += line
Here, you are checking If your line starts with either "#Name " or "#Date ", and calling isInFile() method with line and file2 as arguments.
This is the first issue, there is no use of sending just one line that starts with "#Name " in your case.
If the current line starts with "#Date ", send the previous line and file as arguments to this method.
And second Issue is with the isInFile() definition, which is doing effectively nothing.
if l == line:
return true
You are just checking if two lines in file1 and file2 are same and if yes, you writing this line in sysout.
So, your program will just print the common lines between file1 and file2.
Modified code should like the below one:
def isInFile(l, f):
line_found = false
required_line = null
with open(f, 'r') as f2:
for line in f2:
if line_found:
required_line = line
break
elif l == line:
line_found = true
return (line_found, required_line)
def similitudes(file1, file2):
same = 0
data = ''
copy = False
previous_line = null
with open(file1, 'r') as f1:
for line in f1:
if copy == True:
data += line
if line == '\n' or line[0:6] != '#Name ':
copy = False
if (line[0:6] == '#Name '):
print line
previous_line = line
elif line[0:6] == '#Date ':
print line
file2_line_info = isInFile(previous_line, file2)
if file2_line_info[0] == True:
copy = True
data += file2_line_info[1]
print "true"
return data
def main(argv=2):
print (sys.argv[1])
print (sys.argv[2])
if argv == 2:
out = open('final.txt', 'w')
data = (
similitudes(sys.argv[1], sys.argv[2]) + '\n'
)
out.write(data)
out.close()
else:
print ("This program need 2 files")
exit (0)
return 0
if __name__ == '__main__':
status = main()
sys.exit(status)
Note: This is not the pythonic way of doing things. As I have mentioned in the above answer https://stackoverflow.com/a/34696778/3534696 use "re" module and solve the problem efficiently.

Read the first file into a dictionary, using maketrans/translate to clean up the name.
Using zip(file, file) to read 2 lines of the file at a time makes it much easier to handle.
And using .split(' ', 1)[1] to get rid of the first column.
And .strip() to get rid of any surrounding whitespace (i.e. \n)
Then you can read the second file updating the dictionary.
In Python3 this looks like:
>>> punc = str.maketrans('_-', ' ') # import string & string.maketrans() in Py2
>>> with open(filename1) as file1, open(filename2) as file2:
... data = {name.split(' ', 1)[1].strip().translate(punc):
... date.split(' ', 1)[1].strip().split(':')
... for name, date in zip(file1, file1)}
... for n, d in zip(file2, file2):
... data[n.split(' ', 1)[1].strip()][0] = d.split(' ', 1)[1].strip()
>>> data
{'Marge S': ['444444', 'Ghdsasra'],
'Sebastian Forset': ['191020', 'UhUidsiIds'],
'Sebastian Forset2': ['201020', 'UdfasdUDsa'],
'Solaris Mage': ['281902', 'UDsafduD']}
After that it is just a matter of writing the dictionary out to a new file.
>>> with open(<output>, 'w+') as output:
... for name, date in data.items():
... output.write('#Name {}\n'.format(name))
... output.write('#Date {}:{}\n'.format(*date))
Note: I had to change 'Homer S' to 'Solaris Mage' in the second file to get the stated output.

What is wrong with this code? I'm trying to insert this file

I am trying to insert a file and I keep getting a syntax error on the line line = infile.redline()
def main():
# Declare variables
line = ''
counter = 0
# Prompt for file name
fileName = input('Enter the name of the file: ')
# Open the specified file for reading
infile = open('test.txt', 'r')
# Priming read
line = infile.redline()
counter = 1
# Read in and display first five lines
while line != '' and counter <= 5:
# Strip '\n'
line = line.rtrip('\n')
print(line)
1ine = infile.readline()
# Update counter when line is read
counter +=1
# Close file
infile.close()
# Call the main function.
main()

rtrip should be rstrip. redline should be readline. infile.close() should be indented, and main() should not be.
However, the most serious problem is here:
1ine = infile.readline()
That first character is a one, not an L.

Knowing the standard libraries can make your life much simpler!
from itertools import islice
def main():
fname = input('Enter the name of the file: ')
with open(fname) as inf:
for line in islice(inf, 5): # get the first 5 lines
print(line.rstrip())
if __name__=="__main__":
main()

It is not redline but readline:
line = infile.redline()

Write to file without redundant lines in python

I'm writing python script to read line from a input file and write a unique lines(if the same line is not already in output file) to output file. somehow, my scripts always append the first line of input file to output file even if the same line is already in output file. I can't figure out why this happens.
can anyone know why and how do I fix this?
thanks,
import os
input_file= 'input.txt'
output_file = 'output.txt'
fo = open(output_file, 'a+')
flag = False
with open(input_file, 'r') as fi:
for line1 in fi:
print line1
for line2 in fo:
print line2
if line2 == line1:
flag = True
print('Found Match!!')
break
if flag == False:
fo.write(line1)
elif flag == True:
flag == False
fo.seek(0)
fo.close()
fi.close()

When you open a file in append mode, the file object position is at the end of the file. So the first time through, when it reaches for line2 in fo:, there aren't any more lines in fo, so that block is skipped, and flag is still true, so that first line is written to the output file. After that, you do fo.seek(0), so you are checking against the entire file for subsequent lines.

The answer by kmacinnis is right on as to why your code isn't working; you need to use mode 'r+' instead of 'a+', or else put fo.seek(0) at the beginning of the for loop instead of the end.
That said, there's a much better way to do this than reading the entire output file for every line of the input file.
def ensure_file_ends_with_newline(handle):
position = handle.tell()
handle.seek(-1, 2)
handle_end = handle.read(1)
if handle_end != '\n':
handle.write('\n')
handle.seek(position)
input_filepath = 'input.txt'
output_filepath = 'output.txt'
with open(input_file, 'r') as infile, open(output_file, 'r+') as outfile:
ensure_file_ends_with_newline(outfile)
written = set(outfile)
for line in infile:
if line not in written:
outfile.write(line)
written.add(line)

Your flag was never set to False.
flag == True is an equality
flag = True is an assignment.
Try the latter.
import os
input_file= 'input.txt'
output_file = 'output.txt'
fo = open(output_file, 'a+')
flag = False
with open(input_file, 'r') as fi:
for line1 in fi:
#print line1
for line2 in fo:
#print line2
if line2 == line1:
flag = True
print('Found Match!!')
print (line1,line2)
break
if flag == False:
fo.write(line1)
elif flag == True:
flag = False
fo.seek(0)

Why aren't the lists populating in this code?

I wrote this code for class and cannot figure out why my lists are not populating with any values. I've tried using a debugger and still can't figure out why it won't work. Any ideas? Also... I know for loops would have made more sense, but I needed to use while loops for the assignment.
__author__ = 'Ethan'
#This program reads in a file from the user which contains lines of
def mileage():
filename = input("Please enter the file name: ")
file = open(filename,"r")
line_list = []
num_lines = sum(1 for line in file)
line_counter = 0
while line_counter <= num_lines:
line = file.readline()
line_items = line.split()
line_list.append(line_items)
line_counter += 1
current_index_pos = 0
while current_index_pos <= num_lines:
current_item = line_list[current_index_pos]
print("Leg",current_index_pos + 1,"---", current_item[0]/current_item[1],"miles/gallon")
current_index_pos += 1
mileage()

This reads to the end of the file
num_lines = sum(1 for line in file)
so there are no lines left to read when you get here
line = file.readline()
Better to structure the code like this
with open(filename, "r") as fin:
for line_counter, line in enumerate(fin):
line_items = line.split()
line_list.append(line_items)
# after the loop line_counter has counted the lines
or even (if you don't need line_counter)
with open(filename, "r") as fin:
line_list = [line.split() for line in fin]
More advanced would be to use a generator expression or do everything in a single loop to avoid needing to read the whole file into memory at once
def mileage():
filename = input("Please enter the file name: ")
with open(filename, "r") as fin:
for line_counter, line in enumerate(fin):
current_item = line.split()
print("Leg",line_counter + 1,"---", float(current_item[0])/float(current_item[1]),"miles/gallon")