- optimizations & updated realtor headers

homeharvest/__init__.py

@@ -49,12 +49,10 @@ def scrape_property(
     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
@@ -71,18 +72,25 @@ 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"}}'
-        headers = {
-            "Host": "graph.realtor.com",
-            "x-client-version": "24.20.4.149916",
-            "accept": "*/*",
-            "content-type": "Application/json",
-            "user-agent": "Realtor.com/24.20.4.149916 CFNetwork/1410.0.3 Darwin/22.6.0",
-            "accept-language": "en-US,en;q=0.9",
-        }
-        response = requests.post(url, headers=headers, data=payload)
+        response = requests.post(
+            "https://graph.realtor.com/auth/token",
+            headers={
+                'Host': 'graph.realtor.com',
+                'Accept': '*/*',
+                'Content-Type': 'Application/json',
+                'X-Client-ID': 'rdc_mobile_native,iphone',
+                'X-Visitor-ID': device_id,
+                'X-Client-Version': '24.21.23.679885',
+                '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

@@ -166,7 +166,7 @@ class RealtorScraper(Scraper):
             longitude=property_info["address"]["location"]["coordinate"].get("lon") if able_to_get_lat_long else None,
             address=self._parse_address(property_info, search_type="handle_listing"),
             description=Description(
-                alt_photos=self.process_alt_photos(property_info.get("media", {}).get("photos", [])),
+                alt_photos=self.process_alt_photos(property_info["media"].get("photos", [])) if property_info.get("media") else None,
                 style=property_info["basic"].get("type", "").upper(),
                 beds=property_info["basic"].get("beds"),
                 baths_full=property_info["basic"].get("baths_full"),
@@ -805,7 +805,7 @@ class RealtorScraper(Scraper):
 
         return Description(
             primary_photo=primary_photo,
-            alt_photos=RealtorScraper.process_alt_photos(result.get("photos")),
+            alt_photos=RealtorScraper.process_alt_photos(result.get("photos", [])),
             style=PropertyType.__getitem__(style) if style and style in PropertyType.__members__ else None,
             beds=description_data.get("beds"),
             baths_full=description_data.get("baths_full"),

homeharvest/utils.py

@@ -84,7 +84,7 @@ def process_result(result: Property) -> pd.DataFrame:
 
     description = result.description
     prop_data["primary_photo"] = description.primary_photo
-    prop_data["alt_photos"] = ", ".join(description.alt_photos)
+    prop_data["alt_photos"] = ", ".join(description.alt_photos) if description.alt_photos else None
     prop_data["style"] = description.style if type(description.style) == str else description.style.value
     prop_data["beds"] = description.beds
     prop_data["full_baths"] = description.baths_full

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.3.25"
+version = "0.3.28"
 description = "Real estate scraping library"
 authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
 homepage = "https://github.com/Bunsly/HomeHarvest"