Python-сообщество

# -*- coding: utf-8 -*-
import re
pattern = ur'href="(.*?)">(.*?)</a>'
number_re = re.compile(pattern)
hhh = u'<a href="www.ya.ru">яндекс</a>'
s = number_re.findall(hhh)
print unicode(s)

[(u'www.ya.ru', u'\u044f\u043d\u0434\u0435\u043a\u0441')]

<a href="www.ya.ru onClick=win(400,350) target=window">яндекс</a>

print s[0][1]
.....
pattern = ur'href="(.*?)[\ "].*?>(.*?)</a>'

# -*- coding: utf-8 -*-
import re
pattern = ur'href="(.*?)[\ "].*?>(.*?)</a>'
number_re = re.compile(pattern)
hhh = '<a href="www.ya.ru">яндекс</a>'
s = number_re.findall(hhh)
for k in s:
    for kk in k:
        print kk.decode('utf-8')