get geo coordinates for US cities with population 100,000+

coordinates.py

#!/usr/bin/env python

import json
import requests
from bs4 import BeautifulSoup
import re

LATLNG = re.compile(r'^.*?(-?\d+\.\d+); (-?\d+\.\d+).*$', re.S)
CITY = re.compile(r'^(.*?)(?:\[\d+\])?$', re.S)

def main():
    url = 'https://en.wikipedia.org/wiki/List_of_United_States_cities_by_population'
    html = requests.get(url).text
    soup = BeautifulSoup(html, 'html.parser')
    table = soup.select('table.wikitable.sortable')[0]
    cities = []
    for row in table.find_all('tr')[1:]:
        rank, city, state, estimate_2016, census_2010, change, land_area_2016_mi,\
                land_area_2016_km, pop_dens_2016_mi, pop_dens_2016_km, \
                location = row.find_all('td')
        city = CITY.match(city.text).group(1)
        state = state.text[1:]
        match = LATLNG.match(location.text)
        lat = match.group(1)
        lon = match.group(2)
        cities.append({
            'city': city,
            'state': state,
            'lat': lat,
            'lon': lon
        })
    print(json.dumps({'cities': cities }, indent=4))

if __name__=='__main__':
    main()