-
-
Save jurand71/4dbdfee9eb96f7eec4c01ecdfe763cc9 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
port pandas as pd | |
import requests | |
from bs4 import BeautifulSoup | |
url='https://pl.wikisource.org/wiki/Polskie_powiaty_wed%C5%82ug_kodu_TERYT' | |
page = requests.get(url) | |
soup = BeautifulSoup(page.text,'html.parser') | |
table = soup.find_all('table')[3] | |
powiaty_teryt_df = pd.read_html(str(table)) | |
powiaty_teryt_df = pd.DataFrame(powiaty_teryt_df[0]) | |
powiaty_teryt_df.columns = ['Nazwa_powiatu','Kod_TERYT'] | |
powiaty_teryt_df['Nazwa_powiatu'] = powiaty_teryt_df['Nazwa_powiatu'].str.replace('m. ','', regex=False) | |
powiaty_teryt_df['Nazwa_powiatu'] = powiaty_teryt_df['Nazwa_powiatu'].str.replace(r'\s(.*)','',regex=True) | |
url='https://pl.wikipedia.org/wiki/Wojew%C3%B3dztwo' | |
page = requests.get(url) | |
soup = BeautifulSoup(page.text,'html.parser') | |
table = soup.find('table',{'class':"wikitable"}) | |
wojewodztwa_teryt_df = pd.read_html(str(table)) | |
wojewodztwa_teryt_df = pd.DataFrame(wojewodztwa_teryt_df[0]) | |
wojewodztwa_teryt_df = wojewodztwa_teryt_df.iloc[:,:2] | |
wojewodztwa_teryt_df.columns = ['Kod_TERYT','Nazwa_wojewodztwa'] | |
wojewodztwa_teryt_df['Kod_TERYT'] = wojewodztwa_teryt_df['Kod_TERYT'].str.replace(r'\s(.*)','',regex=True) | |
miejscowosci_df = pd.read_csv('SIMC_miejscowosci_baza.csv') | |
miejscowosci_df = miejscowosci_df.iloc[:,[0,1,6]] | |
miejscowosci_df['WOJ'] = miejscowosci_df['WOJ'].apply(str).str.rjust(2, "0") | |
miejscowosci_df['POW'] = miejscowosci_df['POW'].apply(str).str.rjust(2, "0") | |
miejscowosci_df['Kod_TERYT'] = miejscowosci_df['WOJ'] + ' ' + miejscowosci_df['POW'] | |
places_df = miejscowosci_df.merge(powiaty_teryt_df, left_on='Kod_TERYT', right_on='Kod_TERYT', how='left') | |
places_df = places_df.merge(wojewodztwa_teryt_df, left_on='WOJ', right_on='Kod_TERYT', how='left') | |
places_df = places_df.iloc[:,[2,4,6]] | |
places_df.columns = ['city','county','state'] | |
places_df = places_df.drop_duplicates() | |
# geocoding with Nominatim | |
import urllib.parse | |
import http.client | |
import json | |
def api_call(host, base_url, headers, params): | |
try: | |
conn = http.client.HTTPSConnection(host) | |
conn.request("GET", base_url + "?%s" %params, "{body}", headers) | |
response = conn.getresponse() | |
data = json.loads(response.read()) | |
conn.close() | |
return data | |
except Exception as e: | |
print("[Error {0}] {1}".format(e.errno, e.strerror)) | |
return None | |
def get_lat_long(city, county, state, country): | |
params = urllib.parse.urlencode({'city': city, | |
'county': county, | |
'state': state, | |
'country': country, | |
'format': 'json' }) | |
headers = { 'User-Agent': 'python-requests/2.25.1', 'Accept-Encoding': 'gzip, deflate', | |
'Accept': '/', 'Connection': 'keep-alive' } | |
r = api_call("nominatim.openstreetmap.org", "/search", headers, params) | |
return float(r[0]['lat']), float(r[0]['lon']), int(r[0]['place_id']), int(r[0]['osm_id']), str(r[0]['display_name']) | |
def get_lat_long_place(city, county, state): | |
try: | |
return get_lat_long(city, county, state, 'Polska') | |
except: | |
return None, None | |
location = places_df.apply(lambda x: get_lat_long_place(x.city,x.county,x.state), axis=1) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment