Redfin & Apartments.com Price Monitoring Tutorial

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 time import sleep browser = uc.Chrome() browser.get("https://www.redfin.com/city/30749/CA/San-Francisco") sleep(5)

for card in cards: try: price = card.find_element(By.CLASS_NAME, "homecardV2Price").text except: price = "" try: address = card.find_element(By.CLASS_NAME, "homeAddressV2").text except: address = "" try: beds = card.find_element(By.XPATH, './/div[contains(text(),"Beds")]').text except: beds = "" try: baths = card.find_element(By.XPATH, './/div[contains(text(),"Baths")]').text except: baths = "" try: sqft = card.find_element(By.XPATH, './/div[contains(text(),"Sq Ft")]').text except: sqft = "" try: url = card.find_element(By.TAG_NAME, "a").get_attribute("href") except: url = "" redfin_records.append({ "platform": "Redfin", "price": price, "address": address, "beds": beds, "baths": baths, "sqft": sqft, "url": url })

for item in listings: try: name = item.find_element(By.CLASS_NAME, "property-title").text except: name = "" try: address = item.find_element(By.CLASS_NAME, "property-address").text except: address = "" try: price = item.find_element(By.CLASS_NAME, "property-pricing").text except: price = "" try: beds = item.find_element(By.CLASS_NAME, "property-beds").text except: beds = "" try: url = item.find_element(By.TAG_NAME, "a").get_attribute("href") except: url = "" apt_records.append({ "platform": "Apartments.com", "name": name, "address": address, "price": price, "beds": beds, "url": url })

import re def clean_price(p): if not p: return None p = p.replace(",", "") if "M" in p: return float(p.replace("$","").replace("M","").strip()) * 1_000_000 if "K" in p: return float(p.replace("$","").replace("K","").strip()) * 1_000 match = re.findall(r"\d+", p) return int(match[0]) if match else None Apply: df["price_clean"] = df["price"].apply(clean_price)

def extract_number(val): match = re.findall(r"\d+", val) return int(match[0]) if match else None df["beds_num"] = df["beds"].apply(extract_number) df["baths_num"] = df["baths"].apply(extract_number) df["sqft_num"] = df["sqft"].apply(extract_number)

import requests from bs4 import BeautifulSoup def scrape_unit_details(url): try: html = requests.get(url, timeout=10).text soup = BeautifulSoup(html, "lxml") amenities = [] for li in soup.select(".amenities .specList li"): amenities.append(li.text.strip()) availability = soup.select_one(".availabilityInfo") availability = availability.text.strip() if availability else None return { "amenities": amenities, "availability": availability } except: return {} Attach details: for row in apt_records: row.update(scrape_unit_details(row["url"]))

Column	Meaning
platform	Redfin or Apartments.com
address	Property location
price_clean	Numeric price
price_type	rent / sale
beds_num	#beds
baths_num	#baths
sqft_num	area
availability	units available
amenities	list
url	source link

Column

Meaning

platform

Redfin or Apartments.com

address

Property location

price_clean

Numeric price

price_type

rent / sale

beds_num

#beds

baths_num

#baths

sqft_num

area

availability

units available

amenities

list

url

source link

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