- redfin bug fix

- add recent features for issues

homeharvest/__init__.py

@@ -57,6 +57,10 @@ def _get_ordered_properties(result: Property) -> list[str]:
         "stories",
         "year_built",
         "agent_name",
+        "agent_phone",
+        "agent_email",
+        "days_on_market",
+        "sold_date",
         "mls_id",
         "img_src",
         "latitude",
@@ -84,6 +88,18 @@ def _process_result(result: Property) -> pd.DataFrame:
 
         del prop_data["address"]
 
+    if "agent" in prop_data and prop_data["agent"] is not None:
+        agent_data = prop_data["agent"]
+        prop_data["agent_name"] = agent_data.name
+        prop_data["agent_phone"] = agent_data.phone
+        prop_data["agent_email"] = agent_data.email
+
+        del prop_data["agent"]
+    else:
+        prop_data["agent_name"] = None
+        prop_data["agent_phone"] = None
+        prop_data["agent_email"] = None
+
     properties_df = pd.DataFrame([prop_data])
     properties_df = properties_df[_get_ordered_properties(result)]
 

homeharvest/core/scrapers/models.py

@@ -1,6 +1,7 @@
 from dataclasses import dataclass
 from enum import Enum
 from typing import Tuple
+from datetime import datetime
 
 
 class SiteName(Enum):
@@ -64,6 +65,13 @@ class Address:
     zip_code: str | None = None
 
 
+@dataclass
+class Agent:
+    name: str
+    phone: str | None = None
+    email: str | None = None
+
+
 @dataclass
 class Property:
     property_url: str
@@ -81,11 +89,11 @@ class Property:
     price_per_sqft: int | None = None
     mls_id: str | None = None
 
-    agent_name: str | None = None
+    agent: Agent | None = None
     img_src: str | None = None
     description: str | None = None
     status_text: str | None = None
-    posted_time: str | None = None
+    posted_time: datetime | None = None
 
     # building for sale
     bldg_name: str | None = None
@@ -107,3 +115,6 @@ class Property:
 
     latitude: float | None = None
     longitude: float | None = None
+
+    sold_date: datetime | None = None
+    days_on_market: int | None = None

homeharvest/core/scrapers/redfin/__init__.py

@@ -8,8 +8,9 @@ import json
 from typing import Any
 from .. import Scraper
 from ....utils import parse_address_two, parse_address_one
-from ..models import Property, Address, PropertyType, ListingType, SiteName
-from ....exceptions import NoResultsFound
+from ..models import Property, Address, PropertyType, ListingType, SiteName, Agent
+from ....exceptions import NoResultsFound, SearchTooBroad
+from datetime import datetime
 
 
 class RedfinScraper(Scraper):
@@ -30,6 +31,8 @@ class RedfinScraper(Scraper):
                 return "6"  #: city
             elif match_type == "1":
                 return "address"  #: address, needs to be handled differently
+            elif match_type == "11":
+                return "state"
 
         if "exactMatch" not in response_json["payload"]:
             raise NoResultsFound("No results found for location: {}".format(self.location))
@@ -74,6 +77,8 @@ class RedfinScraper(Scraper):
         else:
             lot_size = lot_size_data
 
+        lat_long = get_value("latLong")
+
         return Property(
             site_name=self.site_name,
             listing_type=self.listing_type,
@@ -88,15 +93,20 @@ class RedfinScraper(Scraper):
             sqft_min=get_value("sqFt"),
             sqft_max=get_value("sqFt"),
             stories=home["stories"] if "stories" in home else None,
-            agent_name=get_value("listingAgent"),
+            agent=Agent(  #: listingAgent, some have sellingAgent as well
+                name=home['listingAgent'].get('name') if 'listingAgent' in home else None,
+                phone=home['listingAgent'].get('phone') if 'listingAgent' in home else None,
+            ),
             description=home["listingRemarks"] if "listingRemarks" in home else None,
             year_built=get_value("yearBuilt") if not single_search else home.get("yearBuilt"),
             lot_area_value=lot_size,
             property_type=PropertyType.from_int_code(home.get("propertyType")),
             price_per_sqft=get_value("pricePerSqFt") if type(home.get("pricePerSqFt")) != int else home.get("pricePerSqFt"),
             mls_id=get_value("mlsId"),
-            latitude=home["latLong"]["latitude"] if "latLong" in home and "latitude" in home["latLong"] else None,
-            longitude=home["latLong"]["longitude"] if "latLong" in home and "longitude" in home["latLong"] else None,
+            latitude=lat_long.get('latitude') if lat_long else None,
+            longitude=lat_long.get('longitude') if lat_long else None,
+            sold_date=datetime.fromtimestamp(home['soldDate'] / 1000) if 'soldDate' in home else None,
+            days_on_market=get_value("dom")
         )
 
     def _handle_rentals(self, region_id, region_type):
@@ -207,6 +217,9 @@ class RedfinScraper(Scraper):
     def search(self):
         region_id, region_type = self._handle_location()
 
+        if region_type == "state":
+            raise SearchTooBroad("State searches are not supported, please use a more specific location.")
+
         if region_type == "address":
             home_id = region_id
             return self.handle_address(home_id)

homeharvest/core/scrapers/zillow/__init__.py

@@ -9,7 +9,7 @@ import json
 from .. import Scraper
 from ....utils import parse_address_one, parse_address_two
 from ....exceptions import GeoCoordsNotFound, NoResultsFound
-from ..models import Property, Address, ListingType, PropertyType
+from ..models import Property, Address, ListingType, PropertyType, Agent
 
 
 class ZillowScraper(Scraper):
@@ -165,10 +165,10 @@ class ZillowScraper(Scraper):
                         home_info["statusType"] if "statusType" in home_info else self.listing_type
                     ),
                     status_text=result.get("statusText"),
-                    posted_time=result["variableData"]["text"]
+                    posted_time=result["variableData"]["text"]  #: TODO: change to datetime
                     if "variableData" in result
-                    and "text" in result["variableData"]
-                    and result["variableData"]["type"] == "TIME_ON_INFO"
+                       and "text" in result["variableData"]
+                       and result["variableData"]["type"] == "TIME_ON_INFO"
                     else None,
                     price_min=home_info.get("price"),
                     price_max=home_info.get("price"),
@@ -246,7 +246,9 @@ class ZillowScraper(Scraper):
             tax_assessed_value=property_data.get("taxAssessedValue"),
             lot_area_value=property_data.get("lotAreaValue"),
             lot_area_unit=property_data["lotAreaUnits"].lower() if "lotAreaUnits" in property_data else None,
-            agent_name=property_data.get("attributionInfo", {}).get("agentName"),
+            agent=Agent(
+                name=property_data.get("attributionInfo", {}).get("agentName")
+            ),
             stories=property_data.get("resoFacts", {}).get("stories"),
             mls_id=property_data.get("attributionInfo", {}).get("mlsId"),
             beds_min=property_data.get("bedrooms"),
@@ -298,20 +300,21 @@ class ZillowScraper(Scraper):
 
     def _get_headers(self):
         headers = {
-            "authority": "www.zillow.com",
-            "accept": "*/*",
-            "accept-language": "en-US,en;q=0.9",
-            "content-type": "application/json",
-            "origin": "https://www.zillow.com",
-            "referer": "https://www.zillow.com",
-            "sec-ch-ua": '"Chromium";v="116", "Not)A;Brand";v="24", "Google Chrome";v="116"',
-            "sec-ch-ua-mobile": "?0",
-            "sec-ch-ua-platform": '"Windows"',
-            "sec-fetch-dest": "empty",
-            "sec-fetch-mode": "cors",
-            "sec-fetch-site": "same-origin",
-            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36",
+            'authority': 'www.zillow.com',
+            'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
+            'accept-language': 'en-US,en;q=0.9',
+            'sec-ch-ua': '"Google Chrome";v="117", "Not;A=Brand";v="8", "Chromium";v="117"',
+            'sec-ch-ua-mobile': '?0',
+            'sec-ch-ua-platform': '"Windows"',
+            'sec-fetch-dest': 'document',
+            'sec-fetch-mode': 'navigate',
+            'sec-fetch-site': 'none',
+            'sec-fetch-user': '?1',
+            'upgrade-insecure-requests': '1',
+            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36',
         }
+
         if self.cookies:
             headers['Cookie'] = self.cookies
+
         return headers

homeharvest/exceptions.py

@@ -12,3 +12,7 @@ class NoResultsFound(Exception):
 
 class GeoCoordsNotFound(Exception):
     """Raised when no property is found for the given address"""
+
+
+class SearchTooBroad(Exception):
+    """Raised when the search is too broad"""

tests/test_redfin.py

@@ -4,11 +4,13 @@ from homeharvest.exceptions import (
     InvalidListingType,
     NoResultsFound,
     GeoCoordsNotFound,
+    SearchTooBroad,
 )
 
 
 def test_redfin():
     results = [
+        scrape_property(location="San Diego", site_name="redfin", listing_type="for_sale"),
         scrape_property(location="2530 Al Lipscomb Way", site_name="redfin", listing_type="for_sale"),
         scrape_property(location="Phoenix, AZ, USA", site_name=["redfin"], listing_type="for_rent"),
         scrape_property(location="Dallas, TX, USA", site_name="redfin", listing_type="sold"),
@@ -24,9 +26,10 @@ def test_redfin():
                 location="abceefg ju098ot498hh9",
                 site_name="redfin",
                 listing_type="for_sale",
-            )
+            ),
+            scrape_property(location="Florida", site_name="redfin", listing_type="for_rent"),
         ]
-    except (InvalidSite, InvalidListingType, NoResultsFound, GeoCoordsNotFound):
+    except (InvalidSite, InvalidListingType, NoResultsFound, GeoCoordsNotFound, SearchTooBroad):
         assert True
 
     assert all([result is None for result in bad_results])