In [1]:
import urllib2

search_address = "http://lernpython.de/21-machine-learning-pythonmodule-auf-github"
response = urllib2.urlopen(search_address)
html = response.read()
html = html.split('<ol>')[-1].split('</ol>')[0]
new = html.split('"')
new2 = new[1::4]

print  new2
['https://github.com/scikit-learn/scikit-learn', 'https://github.com/numenta/nupic', 'https://github.com/machinalis/iepy', 'https://github.com/machinalis/quepy', 'https://github.com/machinalis/featureforge', 'https://github.com/jaberg/skdata', 'https://github.com/rasbt/mlxtend', 'https://github.com/awslabs/machine-learning-samples', 'https://github.com/yandex/rep', 'https://github.com/dclambert/Python-ELM', 'https://github.com/mila-udem/fuel', 'https://github.com/nilearn/nilearn', 'https://github.com/idiap/bob', 'https://github.com/pybrain/pybrain', 'https://github.com/clips/pattern', 'https://github.com/lisa-lab/pylearn2', 'https://github.com/luispedro/milk', 'https://github.com/numenta/nupic', 'https://github.com/kvh/ramp', 'https://github.com/dnouri/nolearn', 'https://github.com/Theano/Theano']

In []: