Last active
September 15, 2020 21:21
-
-
Save getmehire/feb31afd4de5ea9649f5352e97083aeb to your computer and use it in GitHub Desktop.
Real Estate Scraper with Python 3, Beautiful Soup and Pandas
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from bs4 import BeautifulSoup | |
import requests | |
import random | |
import pandas | |
from random import randint | |
from time import sleep | |
targetURL = "https://www.zoopla.co.uk/for-sale/property/edinburgh/" | |
headers = {"Accept-Language": "en-GB, en;q=0.5"} | |
results = requests.get(targetURL, headers=headers) | |
bsSoup = BeautifulSoup(results.text, 'html.parser') | |
pandas.options.display.max_columns = None | |
pandas.options.display.max_rows = None | |
price = [] | |
address = [] | |
beds = [] | |
baths = [] | |
reception = [] | |
soldby = [] | |
size = [] | |
phone = [] | |
mainWrapper = bsSoup.find_all("div", class_ ="listing-results-wrapper") | |
url = "https://www.zoopla.co.uk/for-sale/property/edinburgh/?identifier=edinburgh&q=Edinburgh&radius=0&pn=" | |
for page in range(1,5): | |
pageURL = url+str(page) | |
response = requests.get(pageURL) | |
soup = BeautifulSoup(response.text, 'html.parser') | |
wrapperDiv = soup.find_all("div", class_ ="listing-results-wrapper") | |
sleep(randint(2,10)) | |
print(pageURL) | |
for property in mainWrapper: | |
housePrice = property.find("a", class_ = "text-price").text.replace("\n", "").replace("Offers over", "").replace(" ", "") | |
housePrice = str(housePrice) | |
price.append(housePrice) | |
houseAddress = property.find("a", class_ = "listing-results-address").text | |
address.append(houseAddress) | |
try: | |
nBeds = property.find("span", class_ = "num-beds")['title'] | |
except: | |
nBeds = None | |
beds.append(nBeds) | |
try: | |
nBaths = property.find("span", class_ = "num-baths")['title'] | |
except: | |
nBaths = None | |
baths.append(nBaths) | |
try: | |
recRooms = property.find("span", class_ = "num-reception")['title'] | |
except: | |
recRooms = None | |
reception.append(recRooms) | |
agentName = property.find("p", class_ = "listing-results-marketed").find("span").text | |
soldby.append(agentName) | |
propertyArea = random.randint(300,2200) | |
size.append(propertyArea) | |
agentPhone = property.find("span", class_ = "agent_phone").text.replace(" **", "").replace("\n", "") | |
phone.append(agentPhone) | |
properties = pandas.DataFrame({ | |
'Price': price, | |
'Address': address, | |
'Beds': beds, | |
'Baths': baths, | |
'Receptions': reception, | |
'Size (sq. ft)': size, | |
'Agent Name': soldby, | |
'Agent Phone': phone | |
}) | |
print(len(properties)) | |
properties.to_csv("properties.csv", index = False) | |
print(properties.isnull().sum()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment