- single home return type bug fix

homeharvest/core/scrapers/models.py

@@ -25,6 +25,7 @@ class SiteName(Enum):
 
 class SearchPropertyType(Enum):
     SINGLE_FAMILY = "single_family"
+    APARTMENT = "apartment"
     CONDOS = "condos"
     CONDO_TOWNHOME_ROWHOME_COOP = "condo_townhome_rowhome_coop"
     CONDO_TOWNHOME = "condo_townhome"

homeharvest/core/scrapers/realtor/__init__.py

@@ -121,7 +121,10 @@ class RealtorScraper(Scraper):
 
         property_info = response_json["data"]["home"]
 
-        return [self.process_property(property_info)]
+        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:
@@ -257,7 +260,7 @@ class RealtorScraper(Scraper):
         sort_param = (
             "sort: [{ field: sold_date, direction: desc }]"
             if self.listing_type == ListingType.SOLD
-            else "sort: [{ field: list_date, direction: desc }]"
+            else ""  #: "sort: [{ field: list_date, direction: desc }]"  #: prioritize normal fractal sort from realtor
         )
 
         pending_or_contingent_param = (
@@ -448,6 +451,7 @@ class RealtorScraper(Scraper):
                 "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
@@ -220,19 +232,19 @@ HOMES_DATA = """%s
 }""" % _SEARCH_HOMES_DATA_BASE
 
 SEARCH_HOMES_DATA = """%s
-                    current_estimates {
+current_estimates {
-                            __typename
+    __typename
-                            source {
+    source {
-                                __typename
+        __typename
-                                type
+        type
-                                name
+        name
-                            }
+    }
-                            estimate
+    estimate
-                            estimateHigh: estimate_high
+    estimateHigh: estimate_high
-                            estimateLow: estimate_low
+    estimateLow: estimate_low
-                            date
+    date
-                            isBestHomeValue: isbest_homevalue
+    isBestHomeValue: isbest_homevalue
-                        }
+}
 }""" % _SEARCH_HOMES_DATA_BASE
 
 GENERAL_RESULTS_QUERY = """{

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.4.6"
+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),
+        "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"),
+        "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"),
+        "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 all(isinstance(result, pd.DataFrame) for result in results["pandas"])
-    assert isinstance(results["pydantic"][0], Property)
+    assert all(isinstance(result[0], Property) for result in results["pydantic"])
-    assert isinstance(results["raw"][0], dict)
+    assert all(isinstance(result[0], dict) for result in results["raw"])