Python-сообщество

<a href="/level/51/type/video/post/1753/" class="continue">Фантом, Красные хвосты</a></span>
    <p class="sub">07.08.2011&nbsp;12:42 &#149;&nbsp;

Python 2.7.1 (r271:86832, Nov 27 2010, 18:30:46) [MSC v.1500 32 bit (Intel)] on win32
Type "copyright", "credits" or "license()" for more information.
>>> import re
>>> string = '<a href="/level/51/type/video/post/1753/" class="continue">Фантом, Красные хвосты</a></span> \
<p class="sub">07.08.2011&nbsp;12:42 •&nbsp;'
>>> string = string.strip('\r\n')
>>> regexp1 = re.compile(r'<a href="(.*?)"\sclass="continue">(.*?)</a></span>\s{0,}<p\sclass="sub">(.*?)\s', re.MULTILINE)
>>> regexp2 = re.compile(r'<a href="/level/51/type/video/post/(\d+)/"\sclass="continue">(.*?)</a></span>\s{0,}<p\sclass="sub">(.*?)\s', re.MULTILINE)
>>> print re.findall(regexp1, string)
[('/level/51/type/video/post/1753/', '\xd4\xe0\xed\xf2\xee\xec, \xca\xf0\xe0\xf1\xed\xfb\xe5 \xf5\xe2\xee\xf1\xf2\xfb', '07.08.2011&nbsp;12:42')]
>>> print re.findall(regexp2, string)
[('1753', '\xd4\xe0\xed\xf2\xee\xec, \xca\xf0\xe0\xf1\xed\xfb\xe5 \xf5\xe2\xee\xf1\xf2\xfb', '07.08.2011&nbsp;12:42')]
>>>