Scrape Restaurant data with Selenium

restaurant_scrape.py

import csv
import time

from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.chrome.service import Service as ChromeService


class ResturantScrape:

    def __init__(self, driver):
        self.driver = driver


    def wait_for_element(self, locator, timeout=5):
        try:
            element_present = WebDriverWait(self.driver, timeout).until(
                EC.presence_of_element_located(locator)
            )
        except TimeoutException:
            element_present = None
        return element_present

    def search_location(self, url, searchdata):
        self.driver.get(url)
        searchbox_identifier = (By.ID, "searchboxinput")
        searchbox_element = self.wait_for_element(searchbox_identifier)
        searchbox_element.send_keys(searchdata)
        time.sleep(2)
        searchbox_element.send_keys(Keys.RETURN)
        time.sleep(5)

    def collect_data(self, required_records, output_file):
        """
        Collect data for the specified number of records.
        """
        records = []
        scroll_attempts = 0
        max_scrolls = 10

        while len(records) < required_records and scroll_attempts < max_scrolls:
            records = self.driver.find_elements(
                By.XPATH, '//*[@class="Nv2PK THOPZb CpccDe "]//a'
            )

            if len(records) < required_records:
                if scroll_attempts == 0:
                    scroll_identifier = (
                        By.XPATH,
                        '//*[@class="m6QErb DxyBCb kA9KIf dS8AEf XiKgde ecceSd"]',
                    )
                else:
                    scroll_identifier = (
                        By.XPATH,
                        '//*[@class="m6QErb DxyBCb kA9KIf dS8AEf XiKgde ecceSd QjC7t"]',
                    )

                results_container = self.driver.find_element(*scroll_identifier)
                results_container.send_keys(Keys.PAGE_DOWN)
                time.sleep(2)
                scroll_attempts += 1
            else:
                break
        
        with open(output_file, mode="w", newline="", encoding="utf-8") as file:
            writer = csv.writer(file)
            writer.writerow(["Name", "Link"])

            for tag in records:
                html_content = tag.get_attribute("outerHTML")
                soup = BeautifulSoup(html_content, "html.parser")
                a_tag = soup.find("a", class_="hfpxzc")
                if a_tag:
                    name = a_tag.get("aria-label")
                    link = a_tag.get("href")
                    writer.writerow([name, link])



service = ChromeService(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)
location = "35.851880,-80.521580"
endpoint = f"https://www.google.com/maps/@{location},12z?hl=en"
output_file = "restaurants.csv"
resturantscrape = ResturantScrape(driver)
resturantscrape.search_location(endpoint, "restaurant")
resturantscrape.collect_data(5, output_file)