find duplcate text files python code example

Example 1: python read all text files in directory

import os
from re import search

arr = os.listdir()
strtxt = ".txt"
for txtfile in arr:
    if txtfile.__contains__(strtxt):
        fileObject = open(txtfile, "r")
        data = fileObject.read()
        print(data)

Example 2: extract tgz files in python

import os, sys, tarfile

def extract(tar_url, extract_path='.'):
    print tar_url
    tar = tarfile.open(tar_url, 'r')
    for item in tar:
        tar.extract(item, extract_path)
        if item.name.find(".tgz") != -1 or item.name.find(".tar") != -1:
            extract(item.name, "./" + item.name[:item.name.rfind('/')])
try:

    extract(sys.argv[1] + '.tgz')
    print 'Done.'
except:
    name = os.path.basename(sys.argv[0])
    print name[:name.rfind('.')], '<filename>'