- None address bug fix

homeharvest/core/scrapers/realtor/__init__.py

@@ -471,6 +471,9 @@ class RealtorScraper(Scraper):
 
             is_pending = result["flags"].get("is_pending") or result["flags"].get("is_contingent")
 
+            if is_pending and self.listing_type != ListingType.PENDING:
+                continue
+
             realty_property = Property(
                 mls=mls,
                 mls_id=result["source"].get("listing_id")
@@ -584,21 +587,28 @@ class RealtorScraper(Scraper):
         return ", ".join(neighborhoods_list) if neighborhoods_list else None
 
     @staticmethod
-    def _parse_address(result: dict, search_type):
+    def handle_none_safely(address_part):
+        if address_part is None:
+            return ""
+
+        return address_part
+
+    def _parse_address(self, result: dict, search_type):
         if search_type == "general_search":
+            address = result['location']['address']
+        else:
+            address = result["address"]
+
         return Address(
-                street=f"{result['location']['address']['street_number']} {result['location']['address']['street_name']} {result['location']['address']['street_suffix']}",
+            street=" ".join([
-                unit=result["location"]["address"]["unit"],
+                self.handle_none_safely(address.get('street_number')),
-                city=result["location"]["address"]["city"],
+                self.handle_none_safely(address.get('street_name')),
-                state=result["location"]["address"]["state_code"],
+                self.handle_none_safely(address.get('street_suffix')),
-                zip=result["location"]["address"]["postal_code"],
+            ]).strip(),
-            )
+            unit=address["unit"],
-        return Address(
+            city=address["city"],
-            street=f"{result['address']['street_number']} {result['address']['street_name']} {result['address']['street_suffix']}",
+            state=address["state_code"],
-            unit=result["address"]["unit"],
+            zip=address["postal_code"],
-            city=result["address"]["city"],
-            state=result["address"]["state_code"],
-            zip=result["address"]["postal_code"],
         )
 
     @staticmethod

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.3.6"
+version = "0.3.7"
 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/Bunsly/HomeHarvest"

tests/test_realtor.py

@@ -50,6 +50,16 @@ def test_realtor_pending_comps():
     assert len(set([len(result) for result in results])) == len(results)
 
 
+def test_realtor_sold_past():
+    result = scrape_property(
+        location="San Diego, CA",
+        past_days=30,
+        listing_type="sold",
+    )
+
+    assert result is not None and len(result) > 0
+
+
 def test_realtor_comps():
     result = scrape_property(
         location="2530 Al Lipscomb Way",