Simple regex for fetching href and title attributes of <a> tag

regex_simple_href_title.py

import re

pattern = re.compile('.*<a.*href="(?P<link>[a-zA-Z0-9\+\/\.\?#:_-]+)".*>(?P<title>\w+)</a>.*')

data = '<div calss="bla"><a href="http://link1.domain/index.php" class="test">Link1</a></div>'

print pattern.findall(data)

##output : [('http://link1.domain/index.php', 'Link1')]