Comparing two .txt files using difflib in Python

Question

I am trying to compare two text files and output the first string in the comparison file that does not match but am having difficulty since I am very new to python. Can anybody please give me a sample way to use this module.

When I try something like:

result = difflib.SequenceMatcher(None, testFile, comparisonFile)

I get an error saying object of type 'file' has no len.

Answer 1

For starters, you need to pass strings to difflib.SequenceMatcher, not files:

# Like so
difflib.SequenceMatcher(None, str1, str2)

# Or just read the files in
difflib.SequenceMatcher(None, file1.read(), file2.read())

That'll fix your error.

To get the first non-matching string, see the difflib documentation.

Answer 2

Here is a quick example of comparing the contents of two files using Python difflib...

import difflib

file1 = "myFile1.txt"
file2 = "myFile2.txt"

diff = difflib.ndiff(open(file1).readlines(),open(file2).readlines())
print ''.join(diff),

Answer 3

Are you sure both files exist ?

Just tested it and i get a perfect result.

To get the results i use something like:

import difflib

diff=difflib.ndiff(open(testFile).readlines(), open(comparisonFile).readlines())

try:
    while 1:
        print diff.next(),
except:
    pass

the first character of each line indicates if they are different: eg.: '+' means the following line has been added, etc.

Answer 4

It sounds like you may not need difflib at all. If you're comparing line by line, try something like this:

test_lines = open("test.txt").readlines()
correct_lines = open("correct.txt").readlines()

for test, correct in zip(test_lines, correct_lines):
    if test != correct:
        print "Oh no! Expected %r; got %r." % (correct, test)
        break
else:
    len_diff = len(test_lines) - len(correct_lines)
    if len_diff > 0:
        print "Test file had too much data."
    elif len_diff < 0:
        print "Test file had too little data."
    else:
        print "Everything was correct!"

Answer 5

Another easier method to check whether two text files are same line by line. Try it out.

fname1 = 'text1.txt'
fname2 = 'text2.txt'

f1 = open(fname1)
f2 = open(fname2)

lines1 = f1.readlines()
lines2 = f2.readlines()
i = 0
f1.seek(0)
f2.seek(0)
for line1 in f1:
    if lines1[i] != lines2[i]:
        print(lines1[i])
        exit(0)
    i = i+1

print("both are equal")

f1.close()
f2.close()

otherwise, there is a predefined file in python in filecmp which you can use.

import filecmp

fname1 = 'text1.txt'
fname2 = 'text2.txt'

print(filecmp.cmp(fname1, fname2))

:)

Answer 6

# -*- coding: utf-8 -*-
"""
   

"""

def compare_lines_in_files(file1_path, file2_path):
    try:
        with open(file1_path, 'r', encoding='utf-8') as file1, open(file2_path, 'r', encoding='utf-8') as file2:
            lines_file1 = file1.readlines()
            lines_file2 = file2.readlines()

            mismatched_lines = []

            # Compare each line in file1 to all lines in file2
            for line_num, line1 in enumerate(lines_file1, start=1):
                line1 = line1.strip()  # Remove leading/trailing whitespace
                found_match = False

                for line_num2, line2 in enumerate(lines_file2, start=1):
                    line2 = line2.strip()  # Remove leading/trailing whitespace

                    # Perform a case-insensitive comparison
                    if line1.lower() == line2.lower():
                        found_match = True
                        break

                if not found_match:
                    mismatched_lines.append(f"Line {line_num} in File 1: '{line1}' has no match in File 2")

            # Compare each line in file2 to all lines in file1 (vice versa)
            for line_num2, line2 in enumerate(lines_file2, start=1):
                line2 = line2.strip()  # Remove leading/trailing whitespace
                found_match = False

                for line_num, line1 in enumerate(lines_file1, start=1):
                    line1 = line1.strip()  # Remove leading/trailing whitespace

                    # Perform a case-insensitive comparison
                    if line2.lower() == line1.lower():
                        found_match = True
                        break

                if not found_match:
                    mismatched_lines.append(f"Line {line_num2} in File 2: '{line2}' has no match in File 1")

            return mismatched_lines

    except FileNotFoundError:
        print("One or both files not found.")
        return []

# Paths to the two text files you want to compare
file1_path = r'C:\Python Space\T1.txt'
file2_path = r'C:\Python Space\T2.txt'

mismatched_lines = compare_lines_in_files(file1_path, file2_path)

if mismatched_lines:
    print("Differences between the files:")
    for line in mismatched_lines:
        print(line)
else:
    print("No differences found between the files.")