- exclude_pending parameter

README.md

@@ -90,9 +90,11 @@ Optional
 │
 ├── foreclosure (True/False): If set, fetches only foreclosures
 │
-└── proxy (string): In format 'http://user:pass@host:port'
+├── proxy (string): In format 'http://user:pass@host:port'
 │
-└── extra_property_data (bool): Increases requests by O(n). If set, this fetches additional property data (e.g. agent, broker, property evaluations etc.)
+├── 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'
 ```
 
 ### Property Schema
@@ -142,6 +144,11 @@ Property
 │ ├── agent
 │ ├── agent_email
 │ └── agent_phone
+
+├── Broker Info:
+│ ├── broker
+│ ├── broker_email
+│ └── broker_website
 ```
 
 ### Exceptions

homeharvest/__init__.py

@@ -17,11 +17,12 @@ def scrape_property(
     date_to: str = None,
     foreclosure: bool = None,
     extra_property_data: bool = True,
+    exclude_pending: bool = False,
 ) -> pd.DataFrame:
     """
     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")
-    :param listing_type: Listing Type (for_sale, for_rent, sold)
+    :param listing_type: Listing Type (for_sale, for_rent, sold, pending)
     :param radius: Get properties within _ (e.g. 1.0) miles. Only applicable for individual addresses.
     :param mls_only: If set, fetches only listings with MLS IDs.
     :param proxy: Proxy to use for scraping
@@ -29,6 +30,7 @@ def scrape_property(
     :param date_from, date_to: Get properties sold or listed (dependent on your listing_type) between these dates. format: 2021-01-28
     :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.
     """
     validate_input(listing_type)
     validate_dates(date_from, date_to)
@@ -44,17 +46,16 @@ def scrape_property(
         date_to=date_to,
         foreclosure=foreclosure,
         extra_property_data=extra_property_data,
+        exclude_pending=exclude_pending,
     )
 
     site = RealtorScraper(scraper_input)
     results = site.search()
 
-    properties_dfs = [process_result(result) for result in results]
+    properties_dfs = [df for result in results if not (df := process_result(result)).empty]
     if not properties_dfs:
         return pd.DataFrame()
 
-    properties_dfs = [df for df in properties_dfs if not df.empty]
-
     with warnings.catch_warnings():
         warnings.simplefilter("ignore", category=FutureWarning)
 

homeharvest/core/scrapers/__init__.py

@@ -6,6 +6,7 @@ from urllib3.util.retry import Retry
 import uuid
 from ...exceptions import AuthenticationError
 from .models import Property, ListingType, SiteName
+import json
 
 
 @dataclass
@@ -20,6 +21,7 @@ class ScraperInput:
     date_to: str | None = None
     foreclosure: bool | None = False
     extra_property_data: bool | None = True
+    exclude_pending: bool | None = False
 
 
 class Scraper:
@@ -61,6 +63,7 @@ class Scraper:
         self.date_to = scraper_input.date_to
         self.foreclosure = scraper_input.foreclosure
         self.extra_property_data = scraper_input.extra_property_data
+        self.exclude_pending = scraper_input.exclude_pending
 
     def search(self) -> list[Property]: ...
 
@@ -71,18 +74,25 @@ class Scraper:
 
     @staticmethod
     def get_access_token():
-        url = "https://graph.realtor.com/auth/token"
+        device_id = str(uuid.uuid4()).upper()
 
-        payload = f'{{"client_app_id":"rdc_mobile_native,24.20.4.149916,iphone","device_id":"{str(uuid.uuid4()).upper()}","grant_type":"device_mobile"}}'
+        response = requests.post(
-        headers = {
+            "https://graph.realtor.com/auth/token",
-            "Host": "graph.realtor.com",
+            headers={
-            "x-client-version": "24.20.4.149916",
+                'Host': 'graph.realtor.com',
-            "accept": "*/*",
+                'Accept': '*/*',
-            "content-type": "Application/json",
+                'Content-Type': 'Application/json',
-            "user-agent": "Realtor.com/24.20.4.149916 CFNetwork/1410.0.3 Darwin/22.6.0",
+                'X-Client-ID': 'rdc_mobile_native,iphone',
-            "accept-language": "en-US,en;q=0.9",
+                'X-Visitor-ID': device_id,
-        }
+                'X-Client-Version': '24.21.23.679885',
-        response = requests.post(url, headers=headers, data=payload)
+                'Accept-Language': 'en-US,en;q=0.9',
+                'User-Agent': 'Realtor.com/24.21.23.679885 CFNetwork/1494.0.7 Darwin/23.4.0',
+            },
+            data=json.dumps({
+                "grant_type": "device_mobile",
+                "device_id": device_id,
+                "client_app_id": "rdc_mobile_native,24.21.23.679885,iphone"
+            }))
 
         data = response.json()
 

homeharvest/core/scrapers/realtor/__init__.py

@@ -525,7 +525,7 @@ class RealtorScraper(Scraper):
 
             is_pending = result["flags"].get("is_pending") or result["flags"].get("is_contingent")
 
-            if is_pending and self.listing_type != ListingType.PENDING:
+            if is_pending and (self.exclude_pending and self.listing_type != ListingType.PENDING):
                 return
 
             property_id = result["property_id"]

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.3.27"
+version = "0.3.29"
 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

@@ -4,7 +4,7 @@ from homeharvest import scrape_property
 def test_realtor_pending_or_contingent():
     pending_or_contingent_result = scrape_property(location="Surprise, AZ", listing_type="pending")
 
-    regular_result = scrape_property(location="Surprise, AZ", listing_type="for_sale")
+    regular_result = scrape_property(location="Surprise, AZ", listing_type="for_sale", exclude_pending=True)
 
     assert all([result is not None for result in [pending_or_contingent_result, regular_result]])
     assert len(pending_or_contingent_result) != len(regular_result)
@@ -165,3 +165,13 @@ def test_pr_zip_code():
     )
 
     assert results is not None and len(results) > 0
+
+
+def test_exclude_pending():
+    results = scrape_property(
+        location="33567",
+        listing_type="pending",
+        exclude_pending=True,
+    )
+
+    assert results is not None and len(results) > 0