Python-сообщество

#!/usr/bin/python
# -*- coding: utf-8 -*-

import re
from collections import Counter
import sys

bad_sl=sys.argv[1]
txt=sys.argv[2]


content = open('bad.txt', 'r').read().split(' ')
w=bad_sl.split(';')
d=str(' '.join(w))
words = ''

file=open('3.dat','wb')
file.write(str(d))
file.close()

con = open('3.dat', 'r').read().split(' ')

for word in content:
    for i in con:
        if word==i:
            words += i + " "

er=words.split(" ")          

cnt = Counter()
for word in er:
    cnt[word] += 1
print cnt

import argparse
 
 
parser = argparse.ArgumentParser(description='Bad Words Parser')
 
parser.add_argument('-bad-words', dest='bad_words')
parser.add_argument('-f', '-file', dest='file_in')
 
args = parser.parse_args()
 
with open(args.file_in, 'r') as fin:
    for idx, line in enumerate(fin):
        for bad_word in args.bad_words.split(';'):
             
            if bad_word in line:
                print 'Bad word "{0}" was found at line {1}'.format(bad_word, idx)

[17:29] home:~/dev python parse.py -bad-words 'import;bad;add' -f parse.py
Bad word "import" was found at line 1
Bad word "bad" was found at line 6
Bad word "add" was found at line 6
Bad word "add" was found at line 7
Bad word "bad" was found at line 13
Bad word "bad" was found at line 15
Bad word "bad" was found at line 16

...
with open(args.file_in, 'r') as fin:
    appearances = [ (bad_word, idx) for idx, line in enumerate(fin, 1)
                                        for bad_word in args.bad_words.split(';')
                                            if bad_word in line ]
 
    for pair in sorted(appearances):                   
        print 'Bad word "{0}" was found at line {1}'.format(*pair)