Spaces:
Sleeping
Sleeping
File size: 7,421 Bytes
4fd0f09 35645b4 4fd0f09 35645b4 a154445 35645b4 4fd0f09 35645b4 4fd0f09 35645b4 a154445 4fd0f09 35645b4 a154445 4fd0f09 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 |
import streamlit as st
import pandas as pd
import time
import os
import subprocess
import chromedriver_autoinstaller
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
def install_chrome():
if not os.path.exists("/usr/bin/chromium-browser"):
subprocess.run(["apt-get", "update"], check=True)
subprocess.run(["apt-get", "install", "-y", "chromium-browser"], check=True)
os.environ["PATH"] += os.pathsep + "/usr/bin/"
def scrape_redfin(zipcode):
install_chrome() # Ensure Chrome/Chromium is installed
chromedriver_autoinstaller.install() # Ensure the correct chromedriver version is installed
options = Options()
options.add_argument("--headless") # Run in headless mode
options.add_argument("--no-sandbox")
options.add_argument("--disable-dev-shm-usage")
options.add_argument("--incognito")
options.add_argument("--disable-blink-features=AutomationControlled")
options.add_argument("start-maximized")
options.add_argument("user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36")
options.binary_location = "/usr/bin/chromium-browser" # Use Chromium
service = Service(chromedriver_autoinstaller.install())
driver = webdriver.Chrome(service=service, options=options)
url = f"https://www.redfin.com/zipcode/{zipcode}"
driver.get(url)
try:
listings_container = WebDriverWait(driver, 60).until(
EC.presence_of_element_located((By.XPATH, "/html/body/div[1]/div[6]/div[1]/div[3]/div[1]/div[4]/div/div[1]/div"))
)
except Exception as e:
st.error("Error: Listings did not load properly")
driver.quit()
return pd.DataFrame()
scroll_pause_time = 5
screen_height = driver.execute_script("return window.innerHeight;")
last_height = driver.execute_script("return document.body.scrollHeight")
while True:
driver.execute_script("window.scrollBy(0, arguments[0]);", screen_height // 2)
time.sleep(scroll_pause_time)
new_height = driver.execute_script("return document.body.scrollHeight")
if new_height == last_height:
break
last_height = new_height
houses = []
listings = driver.find_elements(By.XPATH, "/html/body/div[1]/div[6]/div[1]/div[3]/div[1]/div[4]/div/div[1]/div/div")
for listing in listings:
try:
price = listing.find_element(By.XPATH, ".//div/div/div[2]/div[1]/div[1]/span").text
except:
price = "N/A"
try:
address = listing.find_element(By.XPATH, ".//div/div/div[2]/div[3]").text
except:
address = "N/A"
try:
size = listing.find_element(By.XPATH, ".//div/div/div[2]/div[4]/div").text
except:
size = "N/A"
try:
link = listing.find_element(By.TAG_NAME, "a").get_attribute("href")
except:
link = "N/A"
houses.append({"Price": price, "Address": address, "Size": size, "Link": link})
driver.quit()
return pd.DataFrame(houses)
st.title("Redfin House Listings Scraper")
zipcode = st.text_input("Enter ZIP code:")
if st.button("Scrape Data"):
if zipcode:
with st.spinner("Scraping data, please wait..."):
df = scrape_redfin(zipcode)
if not df.empty:
st.success("Scraping complete! Here are the available houses:")
st.dataframe(df)
else:
st.warning("No houses found for the given ZIP code.")
else:
st.error("Please enter a valid ZIP code.")
## working best code ever
# import streamlit as st
# import pandas as pd
# import time
# from selenium import webdriver
# from selenium.webdriver.common.by import By
# from selenium.webdriver.chrome.service import Service
# from selenium.webdriver.chrome.options import Options
# from selenium.webdriver.support.ui import WebDriverWait
# from selenium.webdriver.support import expected_conditions as EC
# from webdriver_manager.chrome import ChromeDriverManager
# def scrape_redfin(zipcode):
# options = Options()
# options.add_argument("--headless")
# options.add_argument("--incognito")
# options.add_argument("--disable-blink-features=AutomationControlled")
# options.add_argument("start-maximized")
# options.add_argument("user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36")
# driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=options)
# url = f"https://www.redfin.com/zipcode/{zipcode}"
# driver.get(url)
# try:
# listings_container = WebDriverWait(driver, 60).until(
# EC.presence_of_element_located((By.XPATH, "/html/body/div[1]/div[6]/div[1]/div[3]/div[1]/div[4]/div/div[1]/div"))
# )
# except Exception as e:
# st.error("Error: Listings did not load properly")
# driver.quit()
# return pd.DataFrame()
# scroll_pause_time = 5
# screen_height = driver.execute_script("return window.innerHeight;")
# last_height = driver.execute_script("return document.body.scrollHeight")
# while True:
# driver.execute_script("window.scrollBy(0, arguments[0]);", screen_height // 2)
# time.sleep(scroll_pause_time)
# new_height = driver.execute_script("return document.body.scrollHeight")
# if new_height == last_height:
# break
# last_height = new_height
# houses = []
# listings = driver.find_elements(By.XPATH, "/html/body/div[1]/div[6]/div[1]/div[3]/div[1]/div[4]/div/div[1]/div/div")
# for listing in listings:
# try:
# price = listing.find_element(By.XPATH, ".//div/div/div[2]/div[1]/div[1]/span").text
# except:
# price = "N/A"
# try:
# address = listing.find_element(By.XPATH, ".//div/div/div[2]/div[3]").text
# except:
# address = "N/A"
# try:
# size = listing.find_element(By.XPATH, ".//div/div/div[2]/div[4]/div").text
# except:
# size = "N/A"
# try:
# link = listing.find_element(By.TAG_NAME, "a").get_attribute("href")
# except:
# link = "N/A"
# houses.append({"Price": price, "Address": address, "Size": size, "Link": link})
# driver.quit()
# return pd.DataFrame(houses)
# st.title("Redfin House Listings Scraper")
# zipcode = st.text_input("Enter ZIP code:")
# if st.button("Scrape Data"):
# if zipcode:
# with st.spinner("Scraping data, please wait..."):
# df = scrape_redfin(zipcode)
# if not df.empty:
# st.success("Scraping complete! Here are the available houses:")
# st.dataframe(df)
# else:
# st.warning("No houses found for the given ZIP code.")
# else:
# st.error("Please enter a valid ZIP code.")
|