Python-сообщество

p = re.search(u'^си(д|ж)(ел(а|о|и)|и(м|т(е|ь?ся)|ят|шь)(я(щ(ий|ая|е(му|го))|евш(ий|его|ему|им|ем|ие|их|им(и)$)

import codecs, re
words = []
m = 0
pl = 0
f = codecs.open(u'text.txt','r','utf-8')
for line in f:
    for word in line.split():
        word = word.lower()
        word = word.strip(u'.,:;-()?!')
        words.append(word)
f.close
for i in range(len(words)):
    m = re.search(u'как(о(й|го|му|е))|(ая|ую)|и(е|х|[ми]*)',words[i])
    if m != None:
        if m == m.group(2):
            m += 1
        if m == m.group(3):
            pl += 1
if f > pl:
    print 'muzhskogo roda > '
else:
    print 'mnozhestvennogo chisla > '

>>> import re
>>> m = re.search(r'.(.)', 'abc')
>>> m
<_sre.SRE_Match object at 0xb77e6120>
>>> m.group(1)
'b'
>>> type(m)
<type '_sre.SRE_Match'>
>>> type(m.group(1))
<type 'str'>
>>>

>>> f = open('/etc/passwd')
>>> n = 0
>>> f
<open file '/etc/passwd', mode 'r' at 0xb788ade0>
>>> n
0
>>> type(f)
<type 'file'>
>>> type(n)
<type 'int'>
>>>

import codecs, re
f = codecs.open(u'nya.html', 'r', 'utf-8-sig')
html = f.read()
f.close()
m = re.search(u'639-2</a>:</td><td style="background-color:white">(.{3})</td>', html)
if m != None:
    codes = codecs.open('ya.txt','w','utf-8')
    codes.write(m.groups(1))
    f.close()
    print m.group(1)