Python-сообщество

import html5lib, urllib2
from html5lib import treebuilders
from lxml.html import fromstring
from lxml import etree

url = urllib2.Request('http://www.yandex.ru')
url.add_header('User-Agent', 'Mozilla/5.0 (X11; U; Linux x86_64; ru; rv:1.9.2.3) Gecko/20100423 Ubuntu/10.04 (lucid) Firefox/3.6.3')
content = urllib2.urlopen(url).read()

parser = html5lib.HTMLParser(tree=treebuilders.getTreeBuilder("lxml"))
doc = parser.parse(content)

#print(doc.xpath("//text()"))
print(doc.find("//p"))

<a href="http://USERNAME.livejournal.com/">
<b>USERNAME</b>
</a>

from BeautifulSoup import BeautifulSoup
import urllib2
import re
page = urllib2.urlopen("http://od-group.livejournal.com/23659.html")
soup = BeautifulSoup(page)
ljuser = soup.findAll('a') # нашёл вообще все ссылки
soup.findAll('a', '*.livejournal.com') # выдал []
soup.findAll("a", { "href" : "*.livejournal.com"}) # выдал []
soup.findAll("span", { "lj:user" : "True"}) # выдал []
soup.findAll(href=re.compile('http://*.livejournal.com')) # выдал []