ΘΕΜΑ: συγκριση αρχειων

import codecs
c = {}
with open(r"C:\Users\Nikos-PC\Desktop\serlock.txt") as f:
    for line in f:
        #line=line.replace('.',' ')
        for word in line.lower().split():
            key = word.rstrip()
            c[key] = c.get(key, 0) + 1
for key in sorted(c):
    print(key,'\t\t',c[key])
 
#print(c)

import sys
import difflib
f=open(r"C:\Users\Nikos-PC\Desktop\serlock.txt",'r')  #anoigma arxeiwn
f1=open(r"C:\Users\Nikos-PC\Desktop\serlock1.txt",'r') #arxeio gia sygkrish 
str1=f.read()
str2=f1.read()  #.replace("."," ").replace("?"," ")
str1=str1.split()  
str2=str2.split()
d=difflib.Differ()     # sygkrish
diff=list(d.compare(str2,str1))
 
for line in diff: #deixnei mono tiw diafores
        #print(line)
        if line.startswith('-'):
            sys.stdout.write(line+'\n')
        elif line.startswith('+'):
            sys.stdout.write('\t\t'+line+'\n') 
#print ('\n'.join(diff)) #ta typvnei ola kai tiw diaforew
 
#sys.stdout.write(str(diff))

f=open(r"C:\Users\Nikos-PC\Desktop\serlock.txt", mode='r', encoding='windows-1253')

fi=open("C:\\Users\\Nikos-PC\Desktop\\ΠΡΟΣΧΕΔΙΟ.txt", mode="r", encoding="cp1253" )

>>> # Find the ten most common words in Hamlet
>>> import re
>>> words = re.findall(r'\w+', open('hamlet.txt').read().lower())
>>> Counter(words).most_common(10)
[('the', 1143), ('and', 966), ('to', 762), ('of', 669), ('i', 631),
 ('you', 554),  ('a', 546), ('my', 514), ('hamlet', 471), ('in', 451)]

 
def remove_accents(input_str):
    nfkd_form = unicodedata.normalize('NFKD', input_str)
    return u"".join([c for c in nfkd_form if not unicodedata.combining(c)])

encoding is the name of the encoding used to decode or encode the file. This should only be used in text mode. The default encoding is platform dependent (whatever locale.getpreferredencoding() returns), but any text encoding supported by Python can be used.

>>> a="Καλημέρα Ελλάδα"
>>> b=a.encode("utf-8")
>>> print(b)
b'\xce\x9a\xce\xb1\xce\xbb\xce\xb7\xce\xbc\xce\xad\xcf\x81\xce\xb1 \xce\x95\xce\xbb\xce\xbb\xce\xac\xce\xb4\xce\xb1'
>>> len(b)
29
>>> len(a)
15
>>> 
 

import codecs
import sys
from struct import * 
a=sys.stdout.encoding
print(a)
 
with open("C:\\Users\\Nikos-PC\\Desktop\\nays.txt", mode='r',buffering=-1,errors='ignore') as fi:
 
    for line in fi:
        [b]line=line.encode('utf-8')[/b]
 
        print(line)

import codecs
import sys
from struct import * 
a=sys.stdout.encoding
print(a)
 
with open("C:\\Users\\Nikos-PC\\Desktop\\nays.txt", mode='r',buffering=-1[b],encoding='utf8'[/b],errors='ignore') as fi:
 
    for line in fi:
        #line=line.encode('utf-8')
 
        print(line)