beautifulsoup-demo-wikipedia.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

# From a saved Wikipedia page, plucks out the link titles from links #100-200

from bs4 import BeautifulSoup
with open('Royal_British_Columbia_Museum.html') as doc:
    text = BeautifulSoup(doc,"html.parser")

    links = text.find_all('a')
    for l in links[100:200]:
        l = l.get_text()
        if len(l) < 1:
            pass
        elif l[0] == '[':
            pass
        elif l == 'edit':
            pass
        else:
            print l