- zillow proxy support

homeharvest/core/scrapers/__init__.py

@@ -1,5 +1,6 @@
 from dataclasses import dataclass
 import requests
+import tls_client
 from .models import Property, ListingType, SiteName
 
 
@@ -12,15 +13,20 @@ class ScraperInput:
 
 
 class Scraper:
-    def __init__(self, scraper_input: ScraperInput):
+    def __init__(self, scraper_input: ScraperInput, session: requests.Session | tls_client.Session = None):
         self.location = scraper_input.location
         self.listing_type = scraper_input.listing_type
 
+        if not session:
             self.session = requests.Session()
+        else:
+            self.session = session
+
         if scraper_input.proxy:
             proxy_url = scraper_input.proxy
             proxies = {"http": proxy_url, "https": proxy_url}
             self.session.proxies.update(proxies)
+
         self.listing_type = scraper_input.listing_type
         self.site_name = scraper_input.site_name
 

homeharvest/core/scrapers/zillow/__init__.py

@@ -20,11 +20,12 @@ from datetime import datetime, timedelta
 
 class ZillowScraper(Scraper):
     def __init__(self, scraper_input):
-        super().__init__(scraper_input)
-        self.session = tls_client.Session(
+        session = tls_client.Session(
             client_identifier="chrome112", random_tls_extension_order=True
         )
 
+        super().__init__(scraper_input, session)
+
         self.session.headers.update({
             'authority': 'www.zillow.com',
             'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.2.17"
+version = "0.2.18"
 description = "Real estate scraping library supporting Zillow, Realtor.com & Redfin."
 authors = ["Zachary Hampton <zachary@zacharysproducts.com>", "Cullen Watson <cullen@cullen.ai>"]
 homepage = "https://github.com/ZacharyHampton/HomeHarvest"