From d05bc5d79fa41a047c3de9a175f3d78d3d033a85 Mon Sep 17 00:00:00 2001
From: Cullen <cullen@cullenwatson.com>
Date: Thu, 4 Apr 2024 17:05:00 -0500
Subject: [PATCH] fix: redfin

---
 example.py                                   | 11 +++++++++++
 homeharvest/core/scrapers/__init__.py        |  1 +
 homeharvest/core/scrapers/redfin/__init__.py |  2 +-
 3 files changed, 13 insertions(+), 1 deletion(-)
 create mode 100644 example.py

diff --git a/example.py b/example.py
new file mode 100644
index 0000000..a926140
--- /dev/null
+++ b/example.py
@@ -0,0 +1,11 @@
+from homeharvest import scrape_property
+import pandas as pd
+
+properties: pd.DataFrame = scrape_property(
+    site_name=["redfin"],
+    location="85281",
+    listing_type="for_rent" # for_sale / sold
+)
+
+print(properties)
+properties.to_csv('properties.csv', index=False)
diff --git a/homeharvest/core/scrapers/__init__.py b/homeharvest/core/scrapers/__init__.py
index 95ed3e1..3107d5e 100644
--- a/homeharvest/core/scrapers/__init__.py
+++ b/homeharvest/core/scrapers/__init__.py
@@ -17,6 +17,7 @@ class Scraper:
         self.listing_type = scraper_input.listing_type
 
         self.session = requests.Session()
+        self.session.headers.update({"user-agent": 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36'})
         if scraper_input.proxy:
             proxy_url = scraper_input.proxy
             proxies = {"http": proxy_url, "https": proxy_url}
diff --git a/homeharvest/core/scrapers/redfin/__init__.py b/homeharvest/core/scrapers/redfin/__init__.py
index 80b91f8..9cdf28d 100644
--- a/homeharvest/core/scrapers/redfin/__init__.py
+++ b/homeharvest/core/scrapers/redfin/__init__.py
@@ -21,7 +21,7 @@ class RedfinScraper(Scraper):
     def _handle_location(self):
         url = "https://www.redfin.com/stingray/do/location-autocomplete?v=2&al=1&location={}".format(self.location)
 
-        response = self.session.get(url)
+        response = self.session.get(url, headers={"user-agent": 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36'})
         response_json = json.loads(response.text.replace("{}&&", ""))
 
         def get_region_type(match_type: str):