input.txt

at
bu
bc
bg
ch
cy
de
eg
fg
gp
hr
kc
ks
la
ln
lv
me
mr
nb
nj
nk
nz
pp
rg
sa
si
sz
tr
uk
ur
vn
wb

nextbike.py

import requests
import codecs
from bs4 import BeautifulSoup
from slugify import slugify
import json

def get_networks(domain):
    results = []
    payload = {'domains': domain}
    baseurl = 'http://nextbike.net/maps/nextbike-live.xml'
    r = requests.get(baseurl, params=payload)
    soup = BeautifulSoup(r.text, "lxml")
    country = soup.find('country')

    for city in soup.findAll('city'):
        network = {}
        network['domain'] = domain
        if "nextbike" in country['name']:
            name = "nextbike-" + city['name']
        else:
            name = country['name'] + '-' + city['name']
        network['tag'] = slugify(name)
        network['meta'] = {}
        network['meta']['name'] = country['name']
        network['meta']['latitude'] = float(city['lat'])
        network['meta']['longitude'] = float(city['lng'])
        network['meta']['city'] = city['name']
        network['meta']['country'] = country['country']
        network['city_uid'] = city['uid']
        results.append(network)

    return results

if __name__ == "__main__":
    results = []
    domains = [line.rstrip('\n') for line in open('input.txt')]
    for domain in domains:
        print("Processing %s" % domain)
        for result in get_networks(domain):
            results.append(result)
    data = json.dumps({'instances': sorted(results)}, ensure_ascii=False, indent=4, separators=(',', ': ')).encode('utf8')
    print(data)

requirements.txt

Unidecode==0.04.18
argparse==1.2.1
beautifulsoup4==4.4.0
lxml==3.4.4
python-slugify==1.1.3
requests==2.7.0
wsgiref==0.1.2
xmlutils==1.1