2023-07-25 17:41:31 -05:00
|
|
|
#!/usr/bin/env python3
|
|
|
|
|
|
|
|
import requests
|
|
|
|
import json
|
|
|
|
from bs4 import BeautifulSoup
|
|
|
|
|
|
|
|
# Stolen from my machine, appears to work; sufficient and necessary to get
|
|
|
|
# around their firewall apparently?
|
|
|
|
UA={
|
|
|
|
"User-Agent": 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/114.0'
|
|
|
|
}
|
|
|
|
|
|
|
|
response = requests.get('https://milwaukeeburgercompany.com/', headers=UA)
|
|
|
|
|
|
|
|
soup = BeautifulSoup(response.text, 'html.parser')
|
|
|
|
location_lis = soup.select('section#locations ul.location-list > li')
|
|
|
|
|
|
|
|
locations = []
|
|
|
|
for location_li in location_lis:
|
|
|
|
lon = location_li
|
|
|
|
locations.append({
|
|
|
|
"type": "Feature",
|
|
|
|
"geometry": {
|
|
|
|
"type": "Point",
|
|
|
|
"coordinates": [float(location_li['data-lng']), float(location_li['data-lat'])], # yes, [lon, lat] since it's [x, y]
|
|
|
|
},
|
|
|
|
"properties": {
|
|
|
|
'address': location_li.find('dd', class_="street").text,
|
|
|
|
'city': location_li.find('dd', class_="city-state-zip").text.split(',')[0],
|
|
|
|
'state': location_li.find('dd', class_="city-state-zip").text.split(', ')[1].split(' ')[0],
|
|
|
|
'zip': location_li.find('dd', class_="city-state-zip").text.split(' ')[-1],
|
|
|
|
},
|
|
|
|
})
|
|
|
|
|
|
|
|
geojson = {
|
|
|
|
"type": "FeatureCollection",
|
|
|
|
"features": locations,
|
|
|
|
}
|
|
|
|
|
2023-07-25 19:12:30 -05:00
|
|
|
print(len(locations), "locations found")
|
|
|
|
|
|
|
|
with open("data.geojson", "w") as f:
|
2023-07-25 17:41:31 -05:00
|
|
|
f.write(json.dumps(geojson))
|