Develop Reference

Removing characters in a file and also making it neat

I want to basically remove all the characters in delete list from the file (Line 11 to 15). What would be the neatest way to delete the words without making the code not neat. I am not sure whether to open the file again here which I know would not be the right way but I can't think of a different solution. Any help would be appreciated.
from os import write
import re
def readText():
with open(r'C:\Users\maxth\Desktop\TextCounter\Text.txt') as f:
print(f.read())
def longestWord():
with open(r'C:\Users\maxth\Desktop\TextCounter\Text.txt', 'r+') as f:
users_text = f.read()
#I want to basically remove all the char in delete list from the file. What would be the neatest way to delete the words without making the code not neat. I am not sure wether to open the file again here and re write it or what!
deleteList = ['!','£','$','%','^','&','*','()','_','+']
for line in f:
for word in deleteList:
line = line.replace(word, '')
longest = max(users_text.split(), key=len)
count_longest = str(len(longest))
print('The longest word in the file is: ' + long)
print('Thats a total of '+count_longest+' letters!')
def writeWord():
with open(r'C:\Users\maxth\Desktop\TextCounter\Text.txt', 'w') as f:
users_text = input('Enter your desired text to continue. \n: ')
f.write(users_text)
f.close()
with open(r'C:\Users\maxth\Desktop\TextCounter\Text.txt', 'r') as file:
print(file.read())
longestWord()

Had to re work it and implement it in a different def. Need to add relative paths and will be alot cleaner aswell.
from os import write
import re
def longestWord():
with open(r'C:\Users\maxth\Desktop\TextCounter\Text.txt', 'r+') as f:
users_text = f.read()
longest = max(users_text.split(), key=len)
count_longest = str(len(longest))
print('The longest word in the file is: ' + longest)
print('Thats a total of '+count_longest+' letters!')
def writeWord():
with open(r'C:\Users\maxth\Desktop\TextCounter\Text.txt', 'w') as f:
users_text = input('Enter your desired text to continue. \n: ')
cleanText = re.sub('[^a-zA-Z0-9 \n\.]', ' ', users_text)
f.write(cleanText)
with open(r'C:\Users\maxth\Desktop\TextCounter\Text.txt', 'r') as clean:
print('\nRemoved any illegal characters. Here is your text:\n\n' + cleanText + '\n')
f.close()
while True:
print("""
Welcome to Skies word text counter!
====================================================
""")
writeWord()
longestWord()
userDecide = input("""
====================================================
Would you like to enter new text and repeat?
Type 'yes' to continue else program will terminate.
====================================================
: """)
if not userDecide.lower == 'yes':
print('Application closing...')
exit()

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,'')

How do I split text from a text file at newlines?

I need to encrypt a message. The message follows, it is saved in a file named assignmenttest.txt
Hi my name is Allie
I am a Junior
I like to play volleyball
I need the program to encrypt each line and keep it's format so that So, I wrote the following program:
fileInputName = input("Enter the file you want to encrypt: ")
key = int(input("Enter your shift key: "))
outputFileName = input("Enter the file name to write to: ")
fileInputOpen = open(fileInputName, "r")
message = fileInputOpen.read()
alphabet = " ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
shiftedStart = alphabet[len(alphabet) - key:]
shiftedEnd = alphabet[:len(alphabet) - key]
shiftedAlphabet = shiftedStart + shiftedEnd
encryptedMessage = ""
for character in message:
letterIndex = message.split("\n")
letterIndex = alphabet.find(character)
encryptedCharacter = shiftedAlphabet[letterIndex]
#print( "{0} -> {1}".format(character, encryptedCharacter))
encryptedMessage += encryptedCharacter
print("The encrypted message is: {0}".format(encryptedMessage))
outputFile = open( outputFileName, "w")
print(encryptedMessage, file=outputFile)
outputFile.close()
print("Done writing encrypted message to file {0}".format(outputFileName))
I tried to use a split at \n, but the output is not formatted in three separate lines, instead it is all just one long string of encrypted letters.
Any ideas on how to split the encrypted message at the correct spot and have it display as such? I've tried multiple split methods and none have worked. Thank you so much.

As the other answers have said, you can replace
fileInputOpen = open(fileInputName, "r")
message = fileInputOpen.read()
with
with open(fileInputName, "r") as f:
messages = f.readlines()
This way, messages will be a list of strings, where each string is the text from a single line in your input file. Then, with some slight modifications to your loop over each character in messages, you can encrypt each string from your messages list. Here, I replaced your encryptedMessage with currentEncryptedMessage and added encryptedMessages, a list that keeps track of the encrypted version of each string in messages.
encryptedMessages = []
currentEncryptedMessage = ""
for message in messages:
for character in message:
... # same as code provided
currentEncryptedMessage += encryptedCharacter
encryptedMessages.append(currentEncryptedMessage)
When writing to your file, you can iterate through each element in encryptedMessages to print line-by-line.
with open( outputFileName, "w") as outputFile:
for message in encryptedMessages:
print(message, file=outputFile)
And so your output text file will preserve the line breaks from your input file.

Instead of splitting at '\n', you can append all the characters in message that are not in alphabet to encryptedMessage when you encounter one.
for character in message:
if !(character in alphabet):
encryptedMessage += character
continue # this takes back to begin of the loop
letterIndex = alphabet.find(character)
encryptedCharacter = shiftedAlphabet[letterIndex]
#print( "{0} -> {1}".format(character, encryptedCharacter))
encryptedMessage += encryptedCharacter

Try changing:
message = fileInputOpen.read()
to
message = fileInputOpen.readlines()
This will make your file reads handle the file line by line. This will allow you to do your processing on a line by line basis first. Beyond that, If you want to encrypt each character, you'll need another for loop for the characters.

Instead of reading the file all at once. Read the lines individually.
f = open("file.txt")
for i in f.readlines():
print (i)

You'll have to loop each line and every character you want to
un-shift;
The script should only un-shift characters present in alphabet;
Checking for file existence is also a must or you may get errors if it doesn't exist.
with open... is the recommended way of reading and writing files in python.
Here's an approach:
import os
import string
fileInputName = input("Enter the file you want to encrypt: ")
while not os.path.exists(fileInputName):
fileInputName = input("{} file doesn't exist.\nEnter the file you want to encrypt : ".format(fileInputName))
key = int(input("Enter your shift key (> 0): "))
while key < 1 :
key = int(input("Invalid shift key value ({}) \nEnter your shift key (> 0): ".format(key)))
fileOutputName = input("Enter the file name to write to: ")
if os.path.exists(fileOutputName) :
ow = input("{} exists, overwrite? (y/n): ".format(fileOutputName))
if not ow.startswith("y"):
fileOutputName = input("Enter the file name to write to: ") # asks for output filename again
alphabet = string.ascii_letters + " "
shiftedStart = alphabet[len(alphabet) - key:]
shiftedEnd = alphabet[:len(alphabet) - key]
shiftedAlphabet = shiftedStart + shiftedEnd
with open(fileOutputName, "a") as outputFile: # opens out file
with open(fileInputName, "r") as inFile: # opens in file
for line in inFile.readlines(): # loop all lines in fileInput
encryptedCharacter = ""
for character in line: # loop all characters in line
if character in alphabet: # un-shift only if character is present in `alphabet`
letterIndex = alphabet.find(character)
encryptedCharacter += shiftedAlphabet[letterIndex]
else:
encryptedCharacter += character # add the original character un-shifted
outputFile.write("{}".format(encryptedCharacter)) # append line to outfile

Indexing and search in a text file

I have a text file that contains the contents of a book. I want to take this file and build an index which allows the user to search through the file to make searches.
The search would consist of entering a word. Then, the program would return the following:
Every chapter which includes that word.
The line number of the line
which contains the word.
The entire line the word is on.
I tried the following code:
infile = open(file)
Dict = {}
word = input("Enter a word to search: ")
linenum = 0
line = infile.readline()
for line in infile
linenum += 1
for word in wordList:
if word in line:
Dict[word] = Dict.setdefault(word, []) + [linenum]
print(count, word)
line = infile.readline()
return Dict
Something like this does not work and seems too awkward for handling the other modules which would require:
An "or" operator to search for one word or another
An "and" operator to search for one word and another in the same chapter
Any suggestions would be great.

def classify_lines_on_chapter(book_contents):
lines_vs_chapter = []
for line in book_contents:
if line.isupper():
current_chapter = line.strip()
lines_vs_chapter.append(current_chapter)
return lines_vs_chapter
def classify_words_on_lines(book_contents):
words_vs_lines = {}
for i, line in enumerate(book_contents):
for word in set([word.strip(string.punctuation) for word in line.split()]):
if word:
words_vs_lines.setdefault(word, []).append(i)
return words_vs_lines
def main():
skip_lines = 93
with open('book.txt') as book:
book_contents = book.readlines()[skip_lines:]
lines_vs_chapter = classify_lines_on_chapter(book_contents)
words_vs_lines = classify_words_on_lines(book_contents)
while True:
word = input("Enter word to search - ")
# Enter a blank input to exit
if not word:
break
line_numbers = words_vs_lines.get(word, None)
if not line_numbers:
print("Word not found!!\n")
continue
for line_number in line_numbers:
line = book_contents[line_number]
chapter = lines_vs_chapter[line_number]
print("Line " + str(line_number + 1 + skip_lines))
print("Chapter '" + str(chapter) + "'")
print(line)
if __name__ == '__main__':
main()
Try it on this input file. Rename it as book.txt before running it.

Python reading files // making new list

so basically, I have a text file with a list of words. I then have to create a raw input to let the user type in words and if the inputted word is in the text file, it will print "Right". for any word that isn't on that list, I have to put it in a different file with the number of "wrong" words.
For the most part, I have the user input correct, where if the word inputted is in the text file, it'll respond whether it is right or wrong.. but im having difficulty adding the wrong words into a different file.
print 'Opening file wordlist.txt'
b = open('wordlist.txt')
print 'Reading file wordlist.txt'
word_list = b.readlines().lower().split()
b.close()
in_word = raw_input('Enter a word: ')
if in_word+'\n' in word_list:
print 'Right'
wrong_list = { word for word in in_word if word not in word_list}
return wrong_list

Why not do
wrong_list = []
print 'Opening file wordlist.txt'
b = open('wordlist.txt')
print 'Reading file wordlist.txt'
word_list = b.readlines().lower().split()
b.close()
in_word = raw_input('Enter a word: ')
if in_word+'\n' in word_list:
print 'Right'
else:
wrong_list.extend(in_word)

print 'Opening file wordlist.txt'
b = open('wordlist.txt', 'r')
print 'Reading file wordlist.txt'
word_list = b.read().splitlines()
b.close()
c = open('wronglist.txt', 'r')
wrong_list = c.read().splitlines()
c.close()
in_word = raw_input('Enter a word: ')
if in_word in word_list:
print 'Right'
else:
print 'Wrong'
c = open('wronglist.txt', 'a')
if in_word not in wrong_list:
c.write("%s\n" % in_word)
c.close()

try this:
in_word = ''
wrong_list = []
with open('wordlist.txt', 'r') as f:
word_list = f.read().lower().split()
while in_word is not '#':
in_word = raw_input('Enter a word(type # to exit): ')
if in_word is '#':
break
if in_word in word_list:
print 'right'
else:
print 'wrong'
wrong_list.append(in_word)
result = """Number of wrong words: %d
Wrong words: %s
""" % (len(wrong_list), ','.join(wrong_list))
print result
with open('wrong.txt', 'a') as f:
f.write(result)

The problem in your current implementation is you need to know how to indent and how to use some features of python's if statement namely "else"
There is a great tutorial on this very relevant topic here.
https://docs.python.org/3.5/tutorial/controlflow.html
You will also need to know how to open a file for writing.
explained here: https://docs.python.org/3.4/library/functions.html?highlight=open#open
which is simply:
with open('/path/filename_here.txt','w') as writeable_file:
#do stuff here with the file
writeable_file.write(line_to_write)
#the file is closed now.