I'm trying to extract real estate listing info from a site using selenium and beautiful soup using this tutorial: https://medium.com/@ben.sturm/scraping-house-listing-data-using-selenium-and-beautiful-soup-1cbb94ba9492
Aim is to gather all the href links from the first page before finding the 'next page' button, navigating to next and collecting all links on that page and so on.
Tried with a single function to achieve this and repeat for each page but can't figure out why it's not working. New to learning code and have seems too trivial to find an answer yet. Would appreciate any help
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
import time
import sys
import numpy as np
import pandas as pd
import regex as re
driver = webdriver.Chrome
url = "http://property.shw.co.uk/searchproperties/Level2-0/Level1-0-181-236-167-165/Units/Development-or-House-and-Flat-or-Investment-or-Land-or-Office-or-Other/UnitIds-0/For-Sale"
driver.get(url)
try:
wait = WebDriverWait(driver, 3)
wait.until(EC.presence_of_element_located((By.ID, "body1")))
print("Page is Ready!")
except TimeoutException:
print("page took too long to load")
def get_house_links(url, driver, pages=3):
house_links = []
driver.get(url)
for i in range(pages):
soup = BeautifulSoup(driver.page_source, 'html.parser')
listings = soup.find_all("a", class_="L")
page_data = [row['href'] for row in listings]
house_links.append(page_data)
time.sleep(np.random.lognormal(0, 1))
next_button = soup.find_all("a", class_="pageingBlock darkBorder")
next_button_link = ['http://property.shw.co.uk'+row['href'] for row in next_button]
if i < 3:
driver.get(next_button_link[0])
return house_links
get_house_links(url, driver)
get_house_links()anywhere. - Guy