import re, codecs
import string
import sys
stopwords=codecs.open('stopwords_harkat1.txt','r','utf_8')
lines=codecs.open('Corpus_v2.txt','r','utf_8')
for line in lines:
line = line.rstrip().lstrip()
#print line
tokens = line.split('\t')
token=tokens[4]
if token in stopwords:
print token
this code has no errors but it not work for string matching from different files.anyone can help me please?
$ i also tried the method match but doesn't work