minimal wikipedia beautiful soup table parser from local file

parse_airports.py

from bs4 import BeautifulSoup
from pprint import pprint as pp

report = []

# open local version
soup = BeautifulSoup(open('airports.html'), 'html.parser')

# assumes one matching table on page with class wikitable
table = soup.find('table', {'class' : 'wikitable'})

for row in table.findAll('tr'):
    tds = row.find_all('td')
    items = [td.text.strip() for td in tds]
    # ignore th element rows
    if items:
        report.append(items)
    
pp(report)