Last active
July 13, 2020 14:44
-
-
Save p3jitnath/c56abcb030e35059ee39c5ea66ba16d9 to your computer and use it in GitHub Desktop.
Geocoding Setup using Selenium
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
| import json | |
| from shapely.geometry import shape, Point | |
| with open('./Data/nyc-neighborhoods.geo.json') as f: | |
| js = json.load(f) | |
| def get_nbd(lng, lat): | |
| point = Point(lng, lat) | |
| for feature in js['features']: | |
| polygon = shape(feature['geometry']) | |
| if polygon.contains(point): | |
| return feature['properties']['name'] |
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
| """ | |
| Description: Code Snippets for NYC Traffic Data Extraction | |
| Author: Pritthijit Nath (nathzi1505) | |
| GitHub Gist: https://gist.github.com/nathzi1505/c56abcb030e35059ee39c5ea66ba16d9 | |
| NOTE: RESULTS WILL BE OFF BY LITTLE | |
| """ | |
| from selenium import webdriver | |
| from selenium.webdriver.common.keys import Keys | |
| import pandas as pd | |
| import time | |
| import os | |
| import re | |
| def geocode(name, address): | |
| try: | |
| driver = webdriver.Firefox() | |
| driver.get("https://www.google.com/maps/") | |
| searchbox = driver.find_element_by_css_selector("#searchboxinput") | |
| searchbox.clear() | |
| searchbox.send_keys(address) | |
| searchbox.send_keys(Keys.ENTER) | |
| time.sleep(15) | |
| url = driver.current_url | |
| coordinates = re.findall(r'(@[\-0-9\.]*,[\-0-9\.]*)', url)[0].replace('@', '').split(',') | |
| coordinates = [np.float64(item) for item in coordinates] | |
| driver.close() | |
| locations.append({ | |
| "road": name, | |
| "lat": coordinates[0], | |
| "lng": coordinates[1] | |
| }) | |
| except: | |
| driver.close() | |
| geocode(name, address) |
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
| cd /usr/bin | |
| wget https://github.com/mozilla/geckodriver/releases/download/v0.26.0/geckodriver-v0.26.0-linux64.tar.gz | |
| tar -xvzf geckodriver-v0.26.0-linux64.tar.gz | |
| rm geckodriver-v0.26.0-linux64.tar.gz | |
| chmod +x geckodriver | |
| export PATH=$PATH:/usr/bin/geckodriver |
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
| from joblib import Parallel, delayed | |
| locations = [] | |
| job = Parallel(n_jobs=-1, prefer="threads")(delayed(geocode)(road, road + ", New York City, USA") for road in roads) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment