Compare two different files line by line in python

Once the file object is iterated, it is exausted.

>>> f = open('1.txt', 'w')
>>> f.write('1n2n3n')
>>> f.close()
>>> f = open('1.txt', 'r')
>>> for line in f: print line
...
1

2

3

# exausted, another iteration does not produce anything.
>>> for line in f: print line
...
>>>

Use file.seek (or close/open the file) to rewind the file:

>>> f.seek(0)
>>> for line in f: print line
...
1

2

3

If order is preserved between files you might also prefer difflib. Although Robᵩ’s result is the bona-fide standard for intersections you might actually be looking for a rough diff-like:

from difflib import Differ

with open('cfg1.txt') as f1, open('cfg2.txt') as f2:
    differ = Differ()

    for line in differ.compare(f1.readlines(), f2.readlines()):
        if line.startswith(" "):
            print(line[2:], end="")

That said, this has a different behaviour to what you asked for (order is important) even though in this instance the same output is produced.

Yet another example…

from __future__ import print_function #Only for Python2

with open('file1.txt') as f1, open('file2.txt') as f2, open('outfile.txt', 'w') as outfile:
    for line1, line2 in zip(f1, f2):
        if line1 == line2:
            print(line1, end='', file=outfile)

And if you want to eliminate common blank lines, just change the if statement to:

if line1.strip() and line1 == line2:

.strip() removes all leading and trailing whitespace, so if that’s all that’s on a line, it will become an empty string "", which is considered false.

I have just been faced with the same challenge, but I thought “Why programming this in Python if you can solve it with a simple “grep”?, which led to the following Python code:

import subprocess
from subprocess import PIPE

try:
  output1, errors1 = subprocess.Popen(["c:\cygwin\bin\grep", "-Fvf" ,"c:\file1.txt", "c:\file2.txt"], shell=True, stdout=PIPE, stderr=PIPE).communicate();
  output2, errors2 = subprocess.Popen(["c:\cygwin\bin\grep", "-Fvf" ,"c:\file2.txt", "c:\file1.txt"], shell=True, stdout=PIPE, stderr=PIPE).communicate();
  if (len(output1) + len(output2) + len(errors1) + len(errors2) > 0):
    print ("Compare result : There are differences:");
    if (len(output1) + len(output2) > 0):
      print ("  Output differences : ");
      print (output1);
      print (output2);
    if (len(errors1) + len(errors2) > 0):
      print (" Errors : ");
      print (errors1);
      print (errors2);
  else:
    print ("Compare result : Both files are equal");
except Exception as ex:
  print("Compare result : Exception during comparison");
  print(ex);
  raise;

The trick behind this is the following:
grep -Fvf file1.txt file2.txt verifies if all entries in file2.txt are present in file1.txt. By doing this in both directions we can see if the content of both files are “equal”. I put “equal” between quotes because duplicate lines are disregarded in this way of working.

Obviously, this is just an example: you can replace grep by any commandline file comparison tool.

Try this:

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"

If you are specifically looking for getting the difference between two files, then this might help:

with open('first_file', 'r') as file1:
    with open('second_file', 'r') as file2:
        difference = set(file1).difference(file2)

difference.discard('n')

with open('diff.txt', 'w') as file_out:
    for line in difference:
        file_out.write(line)

difflib is well worth the effort, with nice condensed output.

from pathlib import Path
import difflib
  
mypath = '/Users/x/lib/python3'
file17c = Path(mypath, 'oop17c.py')
file18c = Path(mypath, 'oop18c.py')

with open(file17c) as file_1:
    file1 = file_1.readlines()
  
with open(file18c) as file_2:
    file2 = file_2.readlines()
  
for line in difflib.unified_diff(
         file1, file2, fromfile=str(file17c), tofile=str(file18c), lineterm=''):
    print(line)

output

+ … unique stuff present in file18c

– … stuff absent in file18c but present in file17c