Inmuebles24 Property Scraping Tutorial | Spain & Mexico

Array ( [as_domain] => amazon.com [as_name] => Amazon.com, Inc. [asn] => AS16509 [continent] => North America [continent_code] => NA [country] => United States [country_code] => US )

Start Your Project

import undetected_chromedriver as uc from selenium.webdriver.common.by import By from selenium.webdriver.common.keys import Keys from time import sleep browser = uc.Chrome() browser.get("https://www.inmuebles24.com/casas-en-venta-en-ciudad-de-mexico.html") sleep(5)

for card in cards: try: title = card.find_element(By.CLASS_NAME, "posting-card-title").text except: title = "" try: price = card.find_element(By.CLASS_NAME, "first-price").text except: price = "" try: location = card.find_element(By.CLASS_NAME, "posting-location").text except: location = "" try: details = card.find_element(By.CLASS_NAME, "posting-features").text except: details = "" try: url = card.find_element(By.TAG_NAME, "a").get_attribute("href") except: url = "" mx_records.append({ "country": "Mexico", "title": title, "price_raw": price, "location": location, "details_raw": details, "url": url })

import requests from bs4 import BeautifulSoup def scrape_inmuebles_detail(url): try: html = requests.get(url, timeout=10).text soup = BeautifulSoup(html, "lxml") description = soup.find("p", {"class": "posting-description-text"}) description = description.text.strip() if description else "" specs = {} spec_blocks = soup.find_all("li", {"class": "icon-feature"}) for sb in spec_blocks: key = sb.find("span").text.strip() val = sb.text.replace(key, "").strip() specs[key] = val amenities = [] for li in soup.select(".amenities-list li"): amenities.append(li.text.strip()) return { "description": description, "specifications": specs, "amenities": amenities } except Exception as e: return {}

for card in cards: try: title = card.find_element(By.CLASS_NAME, "posting-card-title").text except: title = "" try: price = card.find_element(By.CLASS_NAME, "first-price").text except: price = "" try: location = card.find_element(By.CLASS_NAME, "posting-location").text except: location = "" try: details = card.find_element(By.CLASS_NAME, "posting-features").text except: details = "" try: url = card.find_element(By.TAG_NAME, "a").get_attribute("href") except: url = "" spain_records.append({ "country": "Spain", "title": title, "price_raw": price, "location": location, "details_raw": details, "url": url })

import re def clean_price(val): if not val: return None nums = re.findall(r"\d[\d,]*", val) if not nums: return None return int(nums[0].replace(",", "")) Apply: df["price_num"] = df["price_raw"].apply(clean_price)

from currency_converter import CurrencyConverter c = CurrencyConverter() def convert_to_usd(row): try: return c.convert(row["price_num"], row["currency"], "USD") except: return None df["price_usd"] = df.apply(convert_to_usd, axis=1)

def extract_beds(val): match = re.search(r"(\d+)\s?(rec|hab|bed)", val.lower()) return int(match.group(1)) if match else None Extract bathrooms: def extract_baths(val): match = re.search(r"(\d+)\s?ba", val.lower()) return int(match.group(1)) if match else None Extract area: def extract_area(val): match = re.search(r"(\d+)\s?m²", val.lower()) return int(match.group(1)) if match else None Apply: df["beds"] = df["details_raw"].apply(extract_beds) df["baths"] = df["details_raw"].apply(extract_baths) df["area_m2"] = df["details_raw"].apply(extract_area)

Array ( [as_domain] => amazon.com [as_name] => Amazon.com, Inc. [asn] => AS16509 [continent] => North America [continent_code] => NA [country] => United States [country_code] => US )

Start Your Project

Our Data Drives Impact - Real Client Stories