Last active
February 22, 2025 11:27
-
-
Save vivekthedev/271e34e440fb4abe0847915d78331d93 to your computer and use it in GitHub Desktop.
Scraping tutorial Article for BrightData
This file contains hidden or 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
| # requirements.txt | |
| # selenium==4.28.1 | |
| # schedule==1.2.2 | |
| from selenium import webdriver | |
| from selenium.webdriver.common.by import By | |
| from time import sleep | |
| import csv | |
| import schedule | |
| def scrape_maps(): | |
| driver = webdriver.Chrome() | |
| query = "restaurants in Paris" | |
| url = "https://www.google.com/maps/search/" + query.replace(" ", "+") | |
| driver.get(url) | |
| sleep(10) | |
| results = [] | |
| elements = driver.find_elements(By.CLASS_NAME, "bfdHYd") | |
| prevCount = 0 | |
| while len(elements) != prevCount: | |
| prevCount = len(elements) | |
| feed_element = driver.find_element(By.CSS_SELECTOR, '[role=feed]') | |
| driver.execute_script("arguments[0].scrollTop = arguments[0].scrollHeight;", feed_element) | |
| sleep(10) | |
| elements = driver.find_elements(By.CLASS_NAME, "bfdHYd") | |
| for element in elements: | |
| data = dict() | |
| data["Name"] = element.find_element(By.CLASS_NAME, "qBF1Pd").text | |
| try: | |
| data["Rating"] = element.find_element(By.CLASS_NAME, "MW4etd").text | |
| except : | |
| data["Rating"] = "-" | |
| try: | |
| num = element.find_element(By.CLASS_NAME, "UY7F9").text | |
| data["Reviews"] = num[1:-1] | |
| except: | |
| data["Reviews"] = "-" | |
| child = element.find_elements(By.CLASS_NAME, "W4Efsd")[2] | |
| data["Type"] = child.find_elements(By.TAG_NAME, "span")[0].text | |
| data["Address"] = child.find_elements(By.TAG_NAME, "span")[-1].text | |
| results.append(data) | |
| with open('businesses.csv', mode='w', newline='', encoding='utf-8') as file: | |
| writer = csv.DictWriter(file, fieldnames=["Name", "Rating", "Reviews", "Type", "Address"]) | |
| writer.writeheader() | |
| for result in results: | |
| writer.writerow(result) | |
| driver.close() | |
| scrape_maps() | |
| schedule.every(7).days.do(scrape_maps) | |
| while True: | |
| schedule.run_pending() | |
| sleep(60) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment