- redfin bug fix

- .get

README.md

@@ -4,7 +4,13 @@
 
 [![Try with Replit](https://replit.com/badge?caption=Try%20with%20Replit)](https://replit.com/@ZacharyHampton/HomeHarvestDemo)
 
+\
+**Not technical?** Try out the web scraping tool on our site at [tryhomeharvest.com](https://tryhomeharvest.com).
+
 *Looking to build a data-focused software product?* **[Book a call](https://calendly.com/zachary-products/15min)** *to work with us.*
+
+Check out another project we wrote: ***[JobSpy](https://github.com/cullenwatson/JobSpy)** – a Python package for job scraping*
+
 ## Features
 
 - Scrapes properties from **Zillow**, **Realtor.com** & **Redfin** simultaneously

homeharvest/core/scrapers/redfin/__init__.py

@@ -93,7 +93,7 @@ class RedfinScraper(Scraper):
             year_built=get_value("yearBuilt") if not single_search else home["yearBuilt"],
             lot_area_value=lot_size,
             property_type=PropertyType.from_int_code(home.get("propertyType")),
-            price_per_sqft=get_value("pricePerSqFt"),
+            price_per_sqft=get_value("pricePerSqFt") if type(home.get("pricePerSqFt")) != int else home.get("pricePerSqFt"),
             mls_id=get_value("mlsId"),
             latitude=home["latLong"]["latitude"] if "latLong" in home and "latitude" in home["latLong"] else None,
             longitude=home["latLong"]["longitude"] if "latLong" in home and "longitude" in home["latLong"] else None,
@@ -183,7 +183,7 @@ class RedfinScraper(Scraper):
             ),
             property_url="https://www.redfin.com{}".format(building["url"]),
             listing_type=self.listing_type,
-            unit_count=building["numUnitsForSale"],
+            unit_count=building.get("numUnitsForSale"),
         )
 
     def handle_address(self, home_id: str):
@@ -220,7 +220,14 @@ class RedfinScraper(Scraper):
                 url = f"https://www.redfin.com/stingray/api/gis?al=1&region_id={region_id}&region_type={region_type}&sold_within_days=30&num_homes=100000"
             response = self.session.get(url)
             response_json = json.loads(response.text.replace("{}&&", ""))
-            homes = [self._parse_home(home) for home in response_json["payload"]["homes"]] + [
-                self._parse_building(building) for building in response_json["payload"]["buildings"].values()
-            ]
-            return homes
+
+            if "payload" in response_json:
+                homes_list = response_json["payload"].get("homes", [])
+                buildings_list = response_json["payload"].get("buildings", {}).values()
+
+                homes = [self._parse_home(home) for home in homes_list] + [
+                    self._parse_building(building) for building in buildings_list
+                ]
+                return homes
+            else:
+                return []

homeharvest/core/scrapers/zillow/__init__.py

@@ -147,18 +147,18 @@ class ZillowScraper(Scraper):
             if "hdpData" in result:
                 home_info = result["hdpData"]["homeInfo"]
                 address_data = {
-                    "address_one": parse_address_one(home_info["streetAddress"])[0],
+                    "address_one": parse_address_one(home_info.get("streetAddress"))[0],
                     "address_two": parse_address_two(home_info["unit"]) if "unit" in home_info else "#",
-                    "city": home_info["city"],
-                    "state": home_info["state"],
-                    "zip_code": home_info["zipcode"],
+                    "city": home_info.get("city"),
+                    "state": home_info.get("state"),
+                    "zip_code": home_info.get("zipcode"),
                 }
                 property_obj = Property(
                     site_name=self.site_name,
                     address=Address(**address_data),
                     property_url=f"https://www.zillow.com{result['detailUrl']}",
                     tax_assessed_value=int(home_info["taxAssessedValue"]) if "taxAssessedValue" in home_info else None,
-                    property_type=PropertyType(home_info["homeType"]),
+                    property_type=PropertyType(home_info.get("homeType")),
                     listing_type=ListingType(
                         home_info["statusType"] if "statusType" in home_info else self.listing_type
                     ),
@@ -198,18 +198,17 @@ class ZillowScraper(Scraper):
                     site_name=self.site_name,
                     property_type=PropertyType("BUILDING"),
                     listing_type=ListingType(result["statusType"]),
-                    img_src=result["imgSrc"],
+                    img_src=result.get("imgSrc"),
                     address=self._extract_address(result["address"]),
-                    baths_min=result["minBaths"],
+                    baths_min=result.get("minBaths"),
                     area_min=result.get("minArea"),
                     bldg_name=result.get("communityName"),
-                    status_text=result["statusText"],
-                    beds_min=result["minBeds"],
-                    price_min=price_value if "+/mo" in result["price"] else None,
-                    price_max=price_value if "+/mo" in result["price"] else None,
-                    latitude=result["latLong"]["latitude"],
-                    longitude=result["latLong"]["longitude"],
-                    unit_count=result["unitCount"],
+                    status_text=result.get("statusText"),
+                    price_min=price_value if "+/mo" in result.get("price") else None,
+                    price_max=price_value if "+/mo" in result.get("price") else None,
+                    latitude=result.get("latLong", {}).get("latitude"),
+                    longitude=result.get("latLong", {}).get("longitude"),
+                    unit_count=result.get("unitCount"),
                 )
 
                 properties_list.append(building_obj)

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.2.8"
+version = "0.2.12"
 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"