Merge pull request #128 from Alexandre-Shofstall/fix/python39-compat

Fix syntax of __init__ line 24

README.md

@@ -8,8 +8,6 @@
 - **Data Format**: Structures data to resemble MLS listings.
 - **Export Flexibility**: Options to save as either CSV or Excel.
 
-[Video Guide for HomeHarvest](https://youtu.be/J1qgNPgmSLI) - _updated for release v0.3.4_
-
 ![homeharvest](https://github.com/ZacharyHampton/HomeHarvest/assets/78247585/b3d5d727-e67b-4a9f-85d8-1e65fd18620a)
 
 ## Installation

homeharvest/__init__.py

@@ -4,13 +4,13 @@ from .core.scrapers import ScraperInput
 from .utils import process_result, ordered_properties, validate_input, validate_dates, validate_limit
 from .core.scrapers.realtor import RealtorScraper
 from .core.scrapers.models import ListingType, SearchPropertyType, ReturnType, Property
-
+from typing import Union, Optional, List
 
 def scrape_property(
     location: str,
     listing_type: str = "for_sale",
     return_type: str = "pandas",
-    property_type: list[str] | None = None,
+    property_type: Optional[List[str]] = None,
     radius: float = None,
     mls_only: bool = False,
     past_days: int = None,
@@ -21,7 +21,7 @@ def scrape_property(
     extra_property_data: bool = True,
     exclude_pending: bool = False,
     limit: int = 10000
-) -> pd.DataFrame | list[dict] | list[Property]:
+) -> Union[pd.DataFrame, list[dict], list[Property]]:
     """
     Scrape properties from Realtor.com based on a given location and listing type.
     :param location: Location to search (e.g. "Dallas, TX", "85281", "2530 Al Lipscomb Way")

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 {
-                            __typename
-                            source {
-                                __typename
-                                type
-                                name
-                            }
-                            estimate
-                            estimateHigh: estimate_high
-                            estimateLow: estimate_low
-                            date
-                            isBestHomeValue: isbest_homevalue
-                        }
+current_estimates {
+    __typename
+    source {
+        __typename
+        type
+        name
+    }
+    estimate
+    estimateHigh: estimate_high
+    estimateLow: estimate_low
+    date
+    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 = "0.4.11"
 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"])