- single home return type bug fix

homeharvest/core/scrapers/realtor/__init__.py

@@ -121,7 +121,10 @@ class RealtorScraper(Scraper):
 
         property_info = response_json["data"]["home"]
 
+        if self.return_type != ReturnType.raw:
             return [self.process_property(property_info)]
+        else:
+            return [property_info]
 
     @staticmethod
     def process_advertisers(advertisers: list[dict] | None) -> Advertisers | None:
@@ -305,15 +308,20 @@ class RealtorScraper(Scraper):
             )
         elif search_type == "area":  #: general search, came from a general location
             query = """query Home_search(
-                                $location: String!,
+                                $city: String,
+                                $county: [String],
+                                $state_code: String,
+                                $postal_code: String
                                 $offset: Int,
                             ) {
                                 home_search(
                                     query: {
                                         %s
-                                        search_location: {location: $location}
+                                        city: $city
+                                        county: $county
+                                        postal_code: $postal_code
+                                        state_code: $state_code
                                         status: %s
-                                        unique: true
                                         %s
                                         %s
                                         %s
@@ -439,7 +447,11 @@ class RealtorScraper(Scraper):
 
         else:  #: general search, location
             search_variables |= {
-                "location": self.location,
+                "city": location_info.get("city"),
+                "county": location_info.get("county"),
+                "state_code": location_info.get("state_code"),
+                "postal_code": location_info.get("postal_code"),
+
             }
 
         if self.foreclosure:

homeharvest/core/scrapers/realtor/queries.py

@@ -36,6 +36,13 @@ _SEARCH_HOMES_DATA_BASE = """{
           sqft
           __typename
         }
+        photos(https: true) {
+            title
+            href
+            tags {
+                label
+            }
+        }
         list_price
         __typename
     }
@@ -90,12 +97,17 @@ _SEARCH_HOMES_DATA_BASE = """{
         }
     }
     tax_record {
+        cl_id
         public_record_id
+        last_update_date
+        apn
+        tax_parcel_id
     }
     primary_photo(https: true) {
         href
     }
     photos(https: true) {
+        title
         href
         tags {
             label

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.4.7"
+version = "0.4.9"
 description = "Real estate scraping library"
 authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
 homepage = "https://github.com/Bunsly/HomeHarvest"

tests/test_realtor.py

@@ -292,11 +292,14 @@ def test_phone_number_matching():
 
 def test_return_type():
     results = {
-        "pandas": scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100),
-        "pydantic": scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100, return_type="pydantic"),
-        "raw": scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100, return_type="raw"),
+        "pandas": [scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100)],
+        "pydantic": [scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100, return_type="pydantic")],
+        "raw": [
+            scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100, return_type="raw"),
+            scrape_property(location="66642", listing_type="for_rent", limit=100, return_type="raw"),
+        ],
     }
 
-    assert isinstance(results["pandas"], pd.DataFrame)
-    assert isinstance(results["pydantic"][0], Property)
-    assert isinstance(results["raw"][0], dict)
+    assert all(isinstance(result, pd.DataFrame) for result in results["pandas"])
+    assert all(isinstance(result[0], Property) for result in results["pydantic"])
+    assert all(isinstance(result[0], dict) for result in results["raw"])