[Python] Why can't I extract listings information

I am trying to extract the EPC rating from each listings , each time i run my script it it's keeps timing out, what could be the issue ? though i tried increasing the waiting time for the main content to load but I still encounter the same issue. could it be the headless browser not been able to load?

from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium import webdriver
import pandas as pd
import time

# Initialize WebDriver
options = webdriver.ChromeOptions()
options.add_argument("--headless") # Run headless
driver = webdriver.Chrome(options=options)

# Open main URL
url = "https://www.zoopla.co.uk/house-prices/england/?new_homes=include&q=england+&orig_q=united+kingdom&view_type=list&pn=1"
driver.get(url)

# Wait for the main content to load
WebDriverWait(driver, 20).until(
EC.presence_of_element_located((By.CLASS_NAME, "_17smgnt0"))
)

# Initialize result list
result = []

# Find all house elements
houses = driver.find_elements(By.CLASS_NAME, "_1hzil3o0")

# Extract property details
for house in houses:
try:
# Extract listing URL
listing_url = house.find_element(By.XPATH, './/a').get_attribute("href")

item = {
"address": house.find_element(By.XPATH, './/a/h2').text,
"DateLast_sold": house.find_element(By.CSS_SELECTOR, "._1hzil3o9._1hzil3o8._194zg6t7").text,
"Property type": house.find_element(By.CSS_SELECTOR, "div._1pbf8i52 p").text,
"Number of room": house.find_element(By.CSS_SELECTOR, "._1pbf8i51 div:nth-child(2) p").text,
"Tenure": house.find_element(By.CSS_SELECTOR, ".agepcz0 div:nth-child(1) div").text,
"Square foot": house.find_element(By.CSS_SELECTOR, ".agepcz0 div:nth-child(2) div").text,
"Listing URL": listing_url,
"EPC Rating": "N/A" # Placeholder, will update
}

# Open property details in a new tab and scrape EPC
driver.execute_script("window.open('');") # Open new tab
driver.switch_to.window(driver.window_handles[1]) # Switch to new tab
driver.get(listing_url) # Open listing page

try:
# Wait for EPC section to load
epc_element = WebDriverWait(driver, 10).until(
EC.presence_of_element_located((By.CSS_SELECTOR, '.main-content .z3kgis3 ._1vhryas0 ._8lgu4x1 div:nth-child(3) div'))
)
item["EPC Rating"] = epc_element.text # Extract EPC rating

except Exception:
print(f"EPC not found for {item['address']}")

driver.close() # Close new tab
driver.switch_to.window(driver.window_handles[0]) # Switch back to main tab

result.append(item) # Append to the result list

except Exception as e:
print(f"Error extracting data: {e}")

# Store the result in a DataFrame
df = pd.DataFrame(result)

# Show the result
print(df)

# Save to CSV (optional)
# df.to_csv("zoopla_data.csv", index=False)

# Close the driver
driver.quit()

Continue reading...