- fix limit parameter

- fix specific for_rent apartment listing prices

README.md

@@ -94,7 +94,9 @@ Optional
 │
 ├── extra_property_data (True/False): Increases requests by O(n). If set, this fetches additional property data (e.g. agent, broker, property evaluations etc.)
 │
-└── exclude_pending (True/False): If set, excludes pending properties from the results unless listing_type is 'pending'
+├── exclude_pending (True/False): If set, excludes pending properties from the results unless listing_type is 'pending'
+│
+└── limit (integer): Limit the number of properties to fetch. Max & default is 10000.
 ```
 
 ### Property Schema
@@ -126,6 +128,8 @@ Property
 ├── Property Listing Details:
 │ ├── days_on_mls
 │ ├── list_price
+│ ├── list_price_min
+│ ├── list_price_max
 │ ├── list_date
 │ ├── pending_date
 │ ├── sold_price

homeharvest/__init__.py

@@ -1,7 +1,7 @@
 import warnings
 import pandas as pd
 from .core.scrapers import ScraperInput
-from .utils import process_result, ordered_properties, validate_input, validate_dates
+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
 
@@ -18,6 +18,7 @@ def scrape_property(
     foreclosure: bool = None,
     extra_property_data: bool = True,
     exclude_pending: bool = False,
+    limit: int = 10000,
 ) -> pd.DataFrame:
     """
     Scrape properties from Realtor.com based on a given location and listing type.
@@ -31,9 +32,11 @@ def scrape_property(
     :param foreclosure: If set, fetches only foreclosure listings.
     :param extra_property_data: Increases requests by O(n). If set, this fetches additional property data (e.g. agent, broker, property evaluations etc.)
     :param exclude_pending: If true, this excludes pending or contingent properties from the results, unless listing type is pending.
+    :param limit: Limit the number of results returned. Maximum is 10,000.
     """
     validate_input(listing_type)
     validate_dates(date_from, date_to)
+    validate_limit(limit)
 
     scraper_input = ScraperInput(
         location=location,
@@ -47,6 +50,7 @@ def scrape_property(
         foreclosure=foreclosure,
         extra_property_data=extra_property_data,
         exclude_pending=exclude_pending,
+        limit=limit,
     )
 
     site = RealtorScraper(scraper_input)

homeharvest/core/scrapers/__init__.py

@@ -22,6 +22,7 @@ class ScraperInput:
     foreclosure: bool | None = False
     extra_property_data: bool | None = True
     exclude_pending: bool | None = False
+    limit: int = 10000
 
 
 class Scraper:
@@ -64,6 +65,7 @@ class Scraper:
         self.foreclosure = scraper_input.foreclosure
         self.extra_property_data = scraper_input.extra_property_data
         self.exclude_pending = scraper_input.exclude_pending
+        self.limit = scraper_input.limit
 
     def search(self) -> list[Property]: ...
 

homeharvest/core/scrapers/models.py

@@ -113,6 +113,9 @@ class Property:
     address: Address | None = None
 
     list_price: int | None = None
+    list_price_min: int | None = None
+    list_price_max: int | None = None
+
     list_date: str | None = None
     pending_date: str | None = None
     last_sold_date: str | None = None

homeharvest/core/scrapers/realtor/__init__.py

@@ -20,6 +20,7 @@ class RealtorScraper(Scraper):
     PROPERTY_GQL = "https://graph.realtor.com/graphql"
     ADDRESS_AUTOCOMPLETE_URL = "https://parser-external.geo.moveaws.com/suggest"
     NUM_PROPERTY_WORKERS = 20
+    DEFAULT_PAGE_SIZE = 200
 
     def __init__(self, scraper_input):
         super().__init__(scraper_input)
@@ -76,7 +77,6 @@ class RealtorScraper(Scraper):
                             baths_half
                             lot_sqft
                             sold_price
-                            sold_price
                             type
                             price
                             status
@@ -115,10 +115,10 @@ class RealtorScraper(Scraper):
         )
 
         able_to_get_lat_long = (
-            property_info
-            and property_info.get("address")
-            and property_info["address"].get("location")
-            and property_info["address"]["location"].get("coordinate")
+                property_info
+                and property_info.get("address")
+                and property_info["address"].get("location")
+                and property_info["address"]["location"].get("coordinate")
         )
         list_date_str = (
             property_info["basic"]["list_date"].split("T")[0] if property_info["basic"].get("list_date") else None
@@ -326,6 +326,8 @@ class RealtorScraper(Scraper):
                                 last_sold_price
                                 last_sold_date
                                 list_price
+                                list_price_max
+                                list_price_min
                                 price_per_sqft
                                 flags {
                                     is_contingent
@@ -481,7 +483,7 @@ class RealtorScraper(Scraper):
             )
         else:  #: general search, came from an address
             query = (
-                """query Property_search(
+                    """query Property_search(
                         $property_id: [ID]!
                         $offset: Int!,
                     ) {
@@ -492,7 +494,7 @@ class RealtorScraper(Scraper):
                             limit: 1
                             offset: $offset
                         ) %s"""
-                % results_query
+                    % results_query
             )
 
         payload = {
@@ -507,12 +509,12 @@ class RealtorScraper(Scraper):
         properties: list[Property] = []
 
         if (
-            response_json is None
-            or "data" not in response_json
-            or response_json["data"] is None
-            or search_key not in response_json["data"]
-            or response_json["data"][search_key] is None
-            or "results" not in response_json["data"][search_key]
+                response_json is None
+                or "data" not in response_json
+                or response_json["data"] is None
+                or search_key not in response_json["data"]
+                or response_json["data"][search_key] is None
+                or "results" not in response_json["data"][search_key]
         ):
             return {"total": 0, "properties": []}
 
@@ -523,10 +525,10 @@ class RealtorScraper(Scraper):
                 return
 
             able_to_get_lat_long = (
-                result
-                and result.get("location")
-                and result["location"].get("address")
-                and result["location"]["address"].get("coordinate")
+                    result
+                    and result.get("location")
+                    and result["location"].get("address")
+                    and result["location"]["address"].get("coordinate")
             )
 
             is_pending = result["flags"].get("is_pending") or result["flags"].get("is_contingent")
@@ -551,6 +553,8 @@ class RealtorScraper(Scraper):
                 ),
                 status="PENDING" if is_pending else result["status"].upper(),
                 list_price=result["list_price"],
+                list_price_min=result["list_price_min"],
+                list_price_max=result["list_price_max"],
                 list_date=result["list_date"].split("T")[0] if result.get("list_date") else None,
                 prc_sqft=result.get("price_per_sqft"),
                 last_sold_date=result.get("last_sold_date"),
@@ -571,9 +575,17 @@ class RealtorScraper(Scraper):
             )
             return realty_property
 
+        properties_list = response_json["data"][search_key]["results"]
+        total_properties = response_json["data"][search_key]["total"]
+        offset = variables.get("offset", 0)
+
+        #: limit the number of properties to be processed
+        #: example, if your offset is 200, and your limit is 250, return 50
+        properties_list = properties_list[:self.limit - offset]
+
         with ThreadPoolExecutor(max_workers=self.NUM_PROPERTY_WORKERS) as executor:
             futures = [
-                executor.submit(process_property, result) for result in response_json["data"][search_key]["results"]
+                executor.submit(process_property, result) for result in properties_list
             ]
 
             for future in as_completed(futures):
@@ -582,7 +594,7 @@ class RealtorScraper(Scraper):
                     properties.append(result)
 
         return {
-            "total": response_json["data"][search_key]["total"],
+            "total": total_properties,
             "properties": properties,
         }
 
@@ -654,7 +666,7 @@ class RealtorScraper(Scraper):
                     variables=search_variables | {"offset": i},
                     search_type=search_type,
                 )
-                for i in range(200, min(total, 10000), 200)
+                for i in range(self.DEFAULT_PAGE_SIZE, min(total, self.limit), self.DEFAULT_PAGE_SIZE)
             ]
 
             for future in as_completed(futures):
@@ -790,7 +802,10 @@ class RealtorScraper(Scraper):
         )
 
     @staticmethod
-    def _parse_description(result: dict) -> Description:
+    def _parse_description(result: dict) -> Description | None:
+        if not result:
+            return None
+
         description_data = result.get("description", {})
 
         if description_data is None or not isinstance(description_data, dict):
@@ -801,11 +816,8 @@ class RealtorScraper(Scraper):
             style = style.upper()
 
         primary_photo = ""
-        if result and "primary_photo" in result:
-            primary_photo_info = result["primary_photo"]
-            if primary_photo_info and "href" in primary_photo_info:
-                primary_photo_href = primary_photo_info["href"]
-                primary_photo = primary_photo_href.replace("s.jpg", "od-w480_h360_x2.webp?w=1080&q=75")
+        if (primary_photo_info := result.get('primary_photo')) and (primary_photo_href := primary_photo_info.get("href")):
+            primary_photo = primary_photo_href.replace("s.jpg", "od-w480_h360_x2.webp?w=1080&q=75")
 
         return Description(
             primary_photo=primary_photo,

homeharvest/utils.py

@@ -24,6 +24,8 @@ ordered_properties = [
     "year_built",
     "days_on_mls",
     "list_price",
+    "list_price_min",
+    "list_price_max",
     "list_date",
     "sold_price",
     "last_sold_date",
@@ -86,7 +88,8 @@ def process_result(result: Property) -> pd.DataFrame:
     if description:
         prop_data["primary_photo"] = description.primary_photo
         prop_data["alt_photos"] = ", ".join(description.alt_photos) if description.alt_photos else None
-        prop_data["style"] = description.style if isinstance(description.style, str) else description.style.value if description.style else None
+        prop_data["style"] = description.style if isinstance(description.style,
+                                                             str) else description.style.value if description.style else None
         prop_data["beds"] = description.beds
         prop_data["full_baths"] = description.baths_full
         prop_data["half_baths"] = description.baths_half
@@ -110,7 +113,7 @@ def validate_input(listing_type: str) -> None:
 
 
 def validate_dates(date_from: str | None, date_to: str | None) -> None:
-    if (date_from is not None and date_to is None) or (date_from is None and date_to is not None):
+    if isinstance(date_from, str) != isinstance(date_to, str):
         raise InvalidDate("Both date_from and date_to must be provided.")
 
     if date_from and date_to:
@@ -122,3 +125,10 @@ def validate_dates(date_from: str | None, date_to: str | None) -> None:
                 raise InvalidDate("date_to must be after date_from.")
         except ValueError:
             raise InvalidDate(f"Invalid date format or range")
+
+
+def validate_limit(limit: int) -> None:
+    #: 1 -> 10000 limit
+
+    if limit is not None and (limit < 1 or limit > 10000):
+        raise ValueError("Property limit must be between 1 and 10,000.")

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.3.32"
+version = "0.3.34"
 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

@@ -105,8 +105,8 @@ def test_realtor():
             location="2530 Al Lipscomb Way",
             listing_type="for_sale",
         ),
-        scrape_property(location="Phoenix, AZ", listing_type="for_rent"),  #: does not support "city, state, USA" format
-        scrape_property(location="Dallas, TX", listing_type="sold"),  #: does not support "city, state, USA" format
+        scrape_property(location="Phoenix, AZ", listing_type="for_rent", limit=1000),  #: does not support "city, state, USA" format
+        scrape_property(location="Dallas, TX", listing_type="sold", limit=1000),  #: does not support "city, state, USA" format
         scrape_property(location="85281"),
     ]
 
@@ -117,6 +117,7 @@ def test_realtor_city():
     results = scrape_property(
         location="Atlanta, GA",
         listing_type="for_sale",
+        limit=1000
     )
 
     assert results is not None and len(results) > 0
@@ -140,7 +141,7 @@ def test_realtor_foreclosed():
 
 
 def test_realtor_agent():
-    scraped = scrape_property(location="Detroit, MI", listing_type="for_sale")
+    scraped = scrape_property(location="Detroit, MI", listing_type="for_sale", limit=1000)
     assert scraped["agent"].nunique() > 1
 
 
@@ -182,6 +183,58 @@ def test_style_value_error():
         location="Alaska, AK",
         listing_type="sold",
         extra_property_data=False,
+        limit=1000,
     )
 
-    assert results is not None and len(results) > 0
+    assert results is not None and len(results) > 0
+
+
+def test_primary_image_error():
+    results = scrape_property(
+        location="Spokane, PA",
+        listing_type="for_rent",  # or (for_sale, for_rent, pending)
+        past_days=360,
+        radius=3,
+        extra_property_data=False,
+    )
+
+    assert results is not None and len(results) > 0
+
+
+def test_limit():
+    over_limit = 876
+    extra_params = {"limit": over_limit}
+
+    over_results = scrape_property(
+        location="Waddell, AZ",
+        listing_type="for_sale",
+        **extra_params,
+    )
+
+    assert over_results is not None and len(over_results) <= over_limit
+
+    under_limit = 1
+    under_results = scrape_property(
+        location="Waddell, AZ",
+        listing_type="for_sale",
+        limit=under_limit,
+    )
+
+    assert under_results is not None and len(under_results) == under_limit
+
+
+def test_apartment_list_price():
+    results = scrape_property(
+        location="Spokane, WA",
+        listing_type="for_rent",  # or (for_sale, for_rent, pending)
+        extra_property_data=False,
+    )
+
+    assert results is not None
+
+    results = results[results["style"] == "APARTMENT"]
+
+    #: get percentage of results with atleast 1 of any column not none, list_price, list_price_min, list_price_max
+    assert len(results[results[["list_price", "list_price_min", "list_price_max"]].notnull().any(axis=1)]) / len(
+        results
+    ) > 0.5