I don’t care what the differences are. I just want to know whether the contents are different.

The low level way:

from __future__ import with_statement
with open(filename1) as f1:
   with open(filename2) as f2:
      if f1.read() == f2.read():
         ...

The high level way:

import filecmp
if filecmp.cmp(filename1, filename2, shallow=False):
   ...

If you’re going for even basic efficiency, you probably want to check the file size first:

if os.path.getsize(filename1) == os.path.getsize(filename2):
  if open('filename1','r').read() == open('filename2','r').read():
    # Files are the same.

This saves you reading every line of two files that aren’t even the same size, and thus can’t be the same.

(Even further than that, you could call out to a fast MD5sum of each file and compare those, but that’s not “in Python”, so I’ll stop here.)

This is a functional-style file comparison function. It returns instantly False if the files have different sizes; otherwise, it reads in 4KiB block sizes and returns False instantly upon the first difference:

from __future__ import with_statement
import os
import itertools, functools, operator
try:
    izip= itertools.izip  # Python 2
except AttributeError:
    izip= zip  # Python 3

def filecmp(filename1, filename2):
    "Do the two files have exactly the same contents?"
    with open(filename1, "rb") as fp1, open(filename2, "rb") as fp2:
        if os.fstat(fp1.fileno()).st_size != os.fstat(fp2.fileno()).st_size:
            return False # different sizes ∴ not equal

        # set up one 4k-reader for each file
        fp1_reader= functools.partial(fp1.read, 4096)
        fp2_reader= functools.partial(fp2.read, 4096)

        # pair each 4k-chunk from the two readers while they do not return '' (EOF)
        cmp_pairs= izip(iter(fp1_reader, b''), iter(fp2_reader, b''))

        # return True for all pairs that are not equal
        inequalities= itertools.starmap(operator.ne, cmp_pairs)

        # voilà; any() stops at first True value
        return not any(inequalities)

if __name__ == "__main__":
    import sys
    print filecmp(sys.argv[1], sys.argv[2])

Just a different take 🙂

Since I can’t comment on the answers of others I’ll write my own.

If you use md5 you definitely must not just md5.update(f.read()) since you’ll use too much memory.

def get_file_md5(f, chunk_size=8192):
    h = hashlib.md5()
    while True:
        chunk = f.read(chunk_size)
        if not chunk:
            break
        h.update(chunk)
    return h.hexdigest()

f = open(filename1, "r").read()
f2 = open(filename2,"r").read()
print f == f2

I would use a hash of the file’s contents using MD5.

import hashlib

def checksum(f):
    md5 = hashlib.md5()
    md5.update(open(f).read())
    return md5.hexdigest()

def is_contents_same(f1, f2):
    return checksum(f1) == checksum(f2)

if not is_contents_same('foo.txt', 'bar.txt'):
    print 'The contents are not the same!'

For larger files you could compute a MD5 or SHA hash of the files.

from __future__ import with_statement

filename1 = "G:\test1.TXT"

filename2 = "G:\test2.TXT"


with open(filename1) as f1:

   with open(filename2) as f2:

      file1list = f1.read().splitlines()

      file2list = f2.read().splitlines()

      list1length = len(file1list)

      list2length = len(file2list)

      if list1length == list2length:

          for index in range(len(file1list)):

              if file1list[index] == file2list[index]:

                   print file1list[index] + "==" + file2list[index]

              else:                  

                   print file1list[index] + "!=" + file2list[index]+" Not-Equel"

      else:

          print "difference inthe size of the file and number of lines"

Simple and efficient solution:

import os


def is_file_content_equal(
    file_path_1: str, file_path_2: str, buffer_size: int = 1024 * 8
) -> bool:
    """Checks if two files content is equal
    Arguments:
        file_path_1 (str): Path to the first file
        file_path_2 (str): Path to the second file
        buffer_size (int): Size of the buffer to read the file
    Returns:
        bool that indicates if the file contents are equal
    Example:
        >>> is_file_content_equal("filecomp.py", "filecomp copy.py")
            True
        >>> is_file_content_equal("filecomp.py", "diagram.dio")
            False
    """
    # First check sizes
    s1, s2 = os.path.getsize(file_path_1), os.path.getsize(file_path_2)
    if s1 != s2:
        return False
    # If the sizes are the same check the content
    with open(file_path_1, "rb") as fp1, open(file_path_2, "rb") as fp2:
        while True:
            b1 = fp1.read(buffer_size)
            b2 = fp2.read(buffer_size)
            if b1 != b2:
                return False
            # if the content is the same and they are both empty bytes
            # the file is the same
            if not b1:
                return True