[fix] add back zillow/redfin

homeharvest/__init__.py

@@ -24,7 +24,12 @@ def _validate_input(site_name: str, status: str) -> None:
 
 
 def _scrape_single_site(
-    location: str, site_name: str, status: str, proxy: str = None, timeframe: str = None
+    location: str,
+    site_name: str,
+    status: str,
+    radius: float,
+    proxy: str = None,
+    timeframe: str = None,
 ) -> pd.DataFrame:
     """
     Helper function to scrape a single site.
@@ -36,6 +41,7 @@ def _scrape_single_site(
         status=status,
         site_name=SiteName.get_by_value(site_name.lower()),
         proxy=proxy,
+        radius=radius,
         timeframe=timeframe,
     )
 
@@ -53,7 +59,8 @@ def scrape_property(
     location: str,
     timeframe: str = None,
     site_name: Union[str, list[str]] = None,
-    status: str = "sale",
+    listing_type: str = "for_sale",
+    radius: float = None,
     proxy: str = None,
 ) -> pd.DataFrame:
     """
@@ -65,6 +72,7 @@ def scrape_property(
     :param listing_type: Listing type (e.g. 'for_sale', 'for_rent', 'sold')
     :return: pd.DataFrame containing properties
     """
+    status = listing_type
     if site_name is None:
         site_name = list(_scrapers.keys())
 
@@ -80,7 +88,13 @@ def scrape_property(
         with ThreadPoolExecutor() as executor:
             futures = {
                 executor.submit(
-                    _scrape_single_site, location, s_name, status, proxy, timeframe
+                    _scrape_single_site,
+                    location,
+                    s_name,
+                    status,
+                    radius,
+                    proxy,
+                    timeframe,
                 ): s_name
                 for s_name in site_name
             }

homeharvest/core/scrapers/__init__.py

@@ -16,6 +16,7 @@ class ScraperInput:
     site_name: str
     proxy: Optional[str] = None
     timeframe: Optional[str] = None
+    radius: float | None = None
 
     def __post_init__(self):
         if self.status == "sold" and not self.timeframe:
@@ -50,6 +51,7 @@ def __init__(
 
         self.listing_type = scraper_input.status
         self.site_name = scraper_input.site_name
+        self.radius = scraper_input.radius
 
     def search(self) -> list[Property]:
         ...

homeharvest/core/scrapers/realtor/__init__.py

@@ -590,19 +590,29 @@ def get_query(self):
     def search(self):
         location_info = self.handle_location()
         location_type = location_info["area_type"]
+        is_for_comps = self.radius is not None and location_type == "address"
 
-        if location_type == "address":
+        if location_type == "address" and not is_for_comps:
             property_id = location_info["mpr_id"]
             return self.handle_address(property_id)
 
         offset = 0
-        search_variables = {
-            "city": location_info.get("city"),
-            "county": location_info.get("county"),
-            "state_code": location_info.get("state_code"),
-            "postal_code": location_info.get("postal_code"),
-            "offset": offset,
-        }
+
+        if not is_for_comps:
+            search_variables = {
+                "city": location_info.get("city"),
+                "county": location_info.get("county"),
+                "state_code": location_info.get("state_code"),
+                "postal_code": location_info.get("postal_code"),
+                "offset": offset,
+            }
+        else:
+            coordinates = list(location_info["centroid"].values())
+            search_variables = {
+                "coordinates": coordinates,
+                "radius": "{}mi".format(self.radius),
+                "offset": offset,
+            }
 
         result = self.handle_area(search_variables)
         total = result["total"]

homeharvest/core/scrapers/redfin/__init__.py

@@ -0,0 +1,228 @@
+"""
+homeharvest.redfin.__init__
+~~~~~~~~~~~~
+
+This module implements the scraper for redfin.com
+"""
+import json
+from typing import Any
+from .. import Scraper
+from ..models import Property, Address, Status
+from ....exceptions import NoResultsFound, SearchTooBroad
+from datetime import datetime
+
+
+class RedfinScraper(Scraper):
+    def __init__(self, scraper_input):
+        super().__init__(scraper_input)
+        self.listing_type = scraper_input.status
+
+    def _handle_location(self):
+        url = "https://www.redfin.com/stingray/do/location-autocomplete?v=2&al=1&location={}".format(
+            self.location
+        )
+
+        response = self.session.get(url)
+        response_json = json.loads(response.text.replace("{}&&", ""))
+
+        def get_region_type(match_type: str):
+            if match_type == "4":
+                return "2"  #: zip
+            elif match_type == "2":
+                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)
+            )
+
+        if response_json["payload"]["exactMatch"] is not None:
+            target = response_json["payload"]["exactMatch"]
+        else:
+            target = response_json["payload"]["sections"][0]["rows"][0]
+
+        return target["id"].split("_")[1], get_region_type(target["type"])
+
+    def _parse_home(self, home: dict, single_search: bool = False) -> Property:
+        def get_value(key: str) -> Any | None:
+            if key in home and "value" in home[key]:
+                return home[key]["value"]
+
+        if not single_search:
+            address = Address(
+                street=get_value("streetLine"),
+                city=home.get("city"),
+                state=home.get("state"),
+                zip=home.get("zip"),
+            )
+        else:
+            address_info = home.get("streetAddress")
+
+            address = Address(
+                street=address_info.get("assembledAddress"),
+                city=home.get("city"),
+                state=home.get("state"),
+                zip=home.get("zip"),
+            )
+
+        url = "https://www.redfin.com{}".format(home["url"])
+        lot_size_data = home.get("lotSize")
+
+        if not isinstance(lot_size_data, int):
+            lot_size = (
+                lot_size_data.get("value", None)
+                if isinstance(lot_size_data, dict)
+                else None
+            )
+        else:
+            lot_size = lot_size_data
+
+        lat_long = get_value("latLong")
+
+        return Property(
+            status=self.listing_type,
+            address=address,
+            property_url=url,
+            beds=home["beds"] if "beds" in home else None,
+            baths_full=home["baths"] if "baths" in home else None,
+            list_price=get_value("price"),
+            est_sf=get_value("sqFt"),
+            stories=home["stories"] if "stories" in home else None,
+            yr_blt=get_value("yearBuilt")
+            if not single_search
+            else home.get("yearBuilt"),
+            lot_sf=lot_size,
+            prc_sqft=get_value("pricePerSqFt")
+            if type(home.get("pricePerSqFt")) != int
+            else home.get("pricePerSqFt"),
+            mls_id=get_value("mlsId"),
+            latitude=lat_long.get("latitude") if lat_long else None,
+            longitude=lat_long.get("longitude") if lat_long else None,
+            last_sold_date=datetime.fromtimestamp(home["soldDate"] / 1000)
+            if "soldDate" in home
+            else None,
+        )
+
+    def _handle_rentals(self, region_id, region_type):
+        url = f"https://www.redfin.com/stingray/api/v1/search/rentals?al=1&isRentals=true&region_id={region_id}&region_type={region_type}&num_homes=100000"
+
+        response = self.session.get(url)
+        response.raise_for_status()
+        homes = response.json()
+
+        properties_list = []
+
+        for home in homes["homes"]:
+            home_data = home["homeData"]
+            rental_data = home["rentalExtension"]
+
+            property_url = f"https://www.redfin.com{home_data.get('url', '')}"
+            address_info = home_data.get("addressInfo", {})
+            centroid = address_info.get("centroid", {}).get("centroid", {})
+            address = Address(
+                street=address_info.get("formattedStreetLine"),
+                city=address_info.get("city"),
+                state=address_info.get("state"),
+                zip=address_info.get("zip"),
+            )
+
+            price_range = rental_data.get("rentPriceRange", {"min": None, "max": None})
+            bed_range = rental_data.get("bedRange", {"min": None, "max": None})
+            bath_range = rental_data.get("bathRange", {"min": None, "max": None})
+            sqft_range = rental_data.get("sqftRange", {"min": None, "max": None})
+
+            property_ = Property(
+                property_url=property_url,
+                status=Status.FOR_RENT.value,
+                address=address,
+                latitude=centroid.get("latitude"),
+                longitude=centroid.get("longitude"),
+                baths_full=bath_range.get("min"),
+                beds=bed_range.get("min"),
+                list_price=price_range.get("min"),
+                est_sf=sqft_range.get("min"),
+            )
+
+            properties_list.append(property_)
+
+        if not properties_list:
+            raise NoResultsFound("No rentals found for the given location.")
+
+        return properties_list
+
+    def _parse_building(self, building: dict) -> Property:
+        street_address = " ".join(
+            [
+                building["address"]["streetNumber"],
+                building["address"]["directionalPrefix"],
+                building["address"]["streetName"],
+                building["address"]["streetType"],
+            ]
+        )
+        return Property(
+            status=self.status,
+            address=Address(
+                street=street_address,
+                city=building["address"]["city"],
+                state=building["address"]["stateOrProvinceCode"],
+                zip=building["address"]["postalCode"],
+            ),
+            property_url="https://www.redfin.com{}".format(building["url"]),
+        )
+
+    def handle_address(self, home_id: str):
+        """
+        EPs:
+        https://www.redfin.com/stingray/api/home/details/initialInfo?al=1&path=/TX/Austin/70-Rainey-St-78701/unit-1608/home/147337694
+        https://www.redfin.com/stingray/api/home/details/mainHouseInfoPanelInfo?propertyId=147337694&accessLevel=3
+        https://www.redfin.com/stingray/api/home/details/aboveTheFold?propertyId=147337694&accessLevel=3
+        https://www.redfin.com/stingray/api/home/details/belowTheFold?propertyId=147337694&accessLevel=3
+        """
+        url = "https://www.redfin.com/stingray/api/home/details/aboveTheFold?propertyId={}&accessLevel=3".format(
+            home_id
+        )
+
+        response = self.session.get(url)
+        response_json = json.loads(response.text.replace("{}&&", ""))
+
+        parsed_home = self._parse_home(
+            response_json["payload"]["addressSectionInfo"], single_search=True
+        )
+        return [parsed_home]
+
+    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)
+
+        if self.listing_type == Status.FOR_RENT:
+            return self._handle_rentals(region_id, region_type)
+        else:
+            if self.listing_type == Status.FOR_SALE:
+                url = f"https://www.redfin.com/stingray/api/gis?al=1&region_id={region_id}&region_type={region_type}&num_homes=100000"
+            else:
+                url = f"https://www.redfin.com/stingray/api/gis?al=1&region_id={region_id}&region_type={region_type}&sold_within_days=30&num_homes=100000"
+            response = self.session.get(url)
+            response_json = json.loads(response.text.replace("{}&&", ""))
+
+            if "payload" in response_json:
+                homes_list = response_json["payload"].get("homes", [])
+                buildings_list = response_json["payload"].get("buildings", {}).values()
+
+                homes = [self._parse_home(home) for home in homes_list] + [
+                    self._parse_building(building) for building in buildings_list
+                ]
+                return homes
+            else:
+                return []