تبدیل داده های بدون ساختار به ساخت یافته با پایتون و API نقشه گوگل — راهنمای کامل

1import requests
2import json
3import csv
4from tqdm import *

1def addresses_from_csv(path=None, column=None):
2        
3    addresses = []
4
5    with open(path, 'r') as f:
6        reader = csv.reader(f)
7        for row in reader:
8            addresses.append(row[column])
9            
10    return addresses

1# Get addresses from CSV
2addresses = addresses_from_csv(path='path/to/your/file.csv', column=0)
3
4# Set Google Maps API key
5api_key = YOUR_API_KEY
6
7# Initialize array for transformed addresses
8transformed = []
9transformed.append(['Country', 'Post code', 'City', 'Street & No'])

1for query in tqdm(addresses):
2    
3    # API call, storing information as JSON
4    url = 'https://maps.googleapis.com/maps/api/geocode/json?address=' + query + '&lang=en&key=' + api_key
5    r = requests.get(url)
6    data = r.json()

1{
2   "results" : [
3      {
4         "address_components" : [
5            {
6               "long_name" : "221B",
7               "short_name" : "221B",
8               "types" : [ "street_number" ]
9            },
10            {
11               "long_name" : "Baker Street",
12               "short_name" : "Baker St",
13               "types" : [ "route" ]
14            },
15            {
16               "long_name" : "Marylebone",
17               "short_name" : "Marylebone",
18               "types" : [ "neighborhood", "political" ]
19            },
20            {
21               "long_name" : "London",
22               "short_name" : "London",
23               "types" : [ "postal_town" ]
24            },
25            {
26               "long_name" : "Greater London",
27               "short_name" : "Greater London",
28               "types" : [ "administrative_area_level_2", "political" ]
29            },
30            {
31               "long_name" : "England",
32               "short_name" : "England",
33               "types" : [ "administrative_area_level_1", "political" ]
34            },
35            {
36               "long_name" : "United Kingdom",
37               "short_name" : "GB",
38               "types" : [ "country", "political" ]
39            },
40            {
41               "long_name" : "NW1 6XE",
42               "short_name" : "NW1 6XE",
43               "types" : [ "postal_code" ]
44            }
45         ]
46      }

1for query in tqdm(addresses):
2    
3    # API call, storing information as JSON
4    url = 'https://maps.googleapis.com/maps/api/geocode/json?address=' + query + '&lang=en&key=' + api_key
5    r = requests.get(url)
6    data = r.json()
7    
8    # clear all values to avoid appending values from previous iterations a second time
9    number = street = country = postal_code = city = '' 
10    
11    # looping over address components in JSON
12    for component in data['results'][0]['address_components']:
13        if 'street_number' in component['types']:
14            number = component['long_name']
15        elif 'route' in component['types']:
16            street = component['long_name']
17        elif 'country' in component['types']:
18            country = component['long_name']
19        elif 'postal_code' in component['types']:
20            postal_code = component['long_name']
21        elif 'locality' in component['types']:
22            city = component['long_name']
23        elif 'postal_town' in component['types']:
24            city = component['long_name']
25        else:
26            continue
27
28    street_and_no = street + ' ' + number
29    transformed.append([country, postal_code, city, street_and_no])

1with open('transformed_addresses.csv', 'w', newline='', encoding='utf-8') as f:
2    writer = csv.writer(f)
3    for row in transformed:
4        writer.writerow(row)