From 3b7c17b7b59469b5eeed994570e52e6527d9d912 Mon Sep 17 00:00:00 2001
From: Zachary Hampton <69336300+ZacharyHampton@users.noreply.github.com>
Date: Thu, 28 Sep 2023 18:40:16 -0700
Subject: [PATCH] - zillow proxy support

---
 homeharvest/core/scrapers/__init__.py        | 10 ++++++++--
 homeharvest/core/scrapers/zillow/__init__.py |  5 +++--
 pyproject.toml                               |  2 +-
 3 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/homeharvest/core/scrapers/__init__.py b/homeharvest/core/scrapers/__init__.py
index 95ed3e1..e900dbe 100644
--- a/homeharvest/core/scrapers/__init__.py
+++ b/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
 
-        self.session = requests.Session()
+        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
 
diff --git a/homeharvest/core/scrapers/zillow/__init__.py b/homeharvest/core/scrapers/zillow/__init__.py
index d2d7e81..b77f5f0 100644
--- a/homeharvest/core/scrapers/zillow/__init__.py
+++ b/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',
diff --git a/pyproject.toml b/pyproject.toml
index 4be8834..5faef11 100644
--- a/pyproject.toml
+++ b/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"