README.md

@@ -2,6 +2,10 @@
 
 **HomeHarvest** is a real estate scraping library that extracts and formats data in the style of MLS listings.
 
+**Not technical?** Try out the web scraping tool on our site at [tryhomeharvest.com](https://tryhomeharvest.com).
+
+*Looking to build a data-focused software product?* **[Book a call](https://bunsly.com)** *to work with us.*
+
 ## HomeHarvest Features
 
 - **Source**: Fetches properties directly from **Realtor.com**.
@@ -83,12 +87,7 @@ Optional
     - 'farm'
     - 'land'
     - 'mobile'
-│
+
-├── return_type (option): Choose the return type.
-│    - 'pandas' (default)
-│    - 'pydantic'
-│    - 'raw' (json)
-│
 ├── radius (decimal): Radius in miles to find comparable properties based on individual addresses.
 │    Example: 5.5 (fetches properties within a 5.5-mile radius if location is set to a specific address; otherwise, ignored)
 │

homeharvest/__init__.py

@@ -3,13 +3,12 @@ import pandas as pd
 from .core.scrapers import ScraperInput
 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, SearchPropertyType, ReturnType, Property
+from .core.scrapers.models import ListingType, SearchPropertyType
 
 
 def scrape_property(
     location: str,
     listing_type: str = "for_sale",
-    return_type: str = "pandas",
     property_type: list[str] | None = None,
     radius: float = None,
     mls_only: bool = False,
@@ -20,13 +19,12 @@ def scrape_property(
     foreclosure: bool = None,
     extra_property_data: bool = True,
     exclude_pending: bool = False,
-    limit: int = 10000
+    limit: int = 10000,
-) -> pd.DataFrame | list[dict] | list[Property]:
+) -> 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, pending)
-    :param return_type: Return type (pandas, pydantic, raw)
     :param property_type: Property Type (single_family, multi_family, condos, condo_townhome_rowhome_coop, condo_townhome, townhomes, duplex_triplex, farm, land, mobile)
     :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.
@@ -44,8 +42,7 @@ def scrape_property(
 
     scraper_input = ScraperInput(
         location=location,
-        listing_type=ListingType(listing_type.upper()),
+        listing_type=ListingType[listing_type.upper()],
-        return_type=ReturnType(return_type.lower()),
         property_type=[SearchPropertyType[prop.upper()] for prop in property_type] if property_type else None,
         proxy=proxy,
         radius=radius,
@@ -62,9 +59,6 @@ def scrape_property(
     site = RealtorScraper(scraper_input)
     results = site.search()
 
-    if scraper_input.return_type != ReturnType.pandas:
-        return results
-
     properties_dfs = [df for result in results if not (df := process_result(result)).empty]
     if not properties_dfs:
         return pd.DataFrame()

homeharvest/core/scrapers/__init__.py

@@ -1,13 +1,11 @@
 from __future__ import annotations
 from dataclasses import dataclass
-from typing import Union
-
 import requests
 from requests.adapters import HTTPAdapter
 from urllib3.util.retry import Retry
 import uuid
 from ...exceptions import AuthenticationError
-from .models import Property, ListingType, SiteName, SearchPropertyType, ReturnType
+from .models import Property, ListingType, SiteName, SearchPropertyType
 import json
 
 
@@ -26,7 +24,6 @@ class ScraperInput:
     extra_property_data: bool | None = True
     exclude_pending: bool | None = False
     limit: int = 10000
-    return_type: ReturnType = ReturnType.pandas
 
 
 class Scraper:
@@ -84,9 +81,8 @@ class Scraper:
         self.extra_property_data = scraper_input.extra_property_data
         self.exclude_pending = scraper_input.exclude_pending
         self.limit = scraper_input.limit
-        self.return_type = scraper_input.return_type
 
-    def search(self) -> list[Union[Property | dict]]: ...
+    def search(self) -> list[Property]: ...
 
     @staticmethod
     def _parse_home(home) -> Property: ...

homeharvest/core/scrapers/models.py

@@ -4,12 +4,6 @@ from enum import Enum
 from typing import Optional
 
 
-class ReturnType(Enum):
-    pydantic = "pydantic"
-    pandas = "pandas"
-    raw = "raw"
-
-
 class SiteName(Enum):
     ZILLOW = "zillow"
     REDFIN = "redfin"
@@ -25,7 +19,6 @@ class SiteName(Enum):
 
 class SearchPropertyType(Enum):
     SINGLE_FAMILY = "single_family"
-    APARTMENT = "apartment"
     CONDOS = "condos"
     CONDO_TOWNHOME_ROWHOME_COOP = "condo_townhome_rowhome_coop"
     CONDO_TOWNHOME = "condo_townhome"
@@ -155,9 +148,6 @@ class Property:
     property_url: str
 
     property_id: str
-    #: allows_cats: bool
-    #: allows_dogs: bool
-
     listing_id: str | None = None
 
     mls: str | None = None
@@ -177,8 +167,6 @@ class Property:
     hoa_fee: int | None = None
     days_on_mls: int | None = None
     description: Description | None = None
-    tags: list[str] | None = None
-    details: list[dict] | None = None
 
     latitude: float | None = None
     longitude: float | None = None

homeharvest/core/scrapers/realtor/__init__.py

@@ -32,9 +32,8 @@ from ..models import (
     Builder,
     Advertisers,
     Office,
-    ReturnType
 )
-from .queries import GENERAL_RESULTS_QUERY, SEARCH_HOMES_DATA, HOMES_DATA, HOME_FRAGMENT
+from .queries import GENERAL_RESULTS_QUERY, SEARCH_HOMES_DATA, HOMES_DATA
 
 
 class RealtorScraper(Scraper):
@@ -121,7 +120,7 @@ class RealtorScraper(Scraper):
 
         property_info = response_json["data"]["home"]
 
-        return [self.process_property(property_info)]
+        return [self.process_property(property_info, "home")]
 
     @staticmethod
     def process_advertisers(advertisers: list[dict] | None) -> Advertisers | None:
@@ -169,7 +168,7 @@ class RealtorScraper(Scraper):
 
         return processed_advertisers
 
-    def process_property(self, result: dict) -> Property | None:
+    def process_property(self, result: dict, query_name: str) -> Property | None:
         mls = result["source"].get("id") if "source" in result and isinstance(result["source"], dict) else None
 
         if not mls and self.mls_only:
@@ -189,7 +188,9 @@ class RealtorScraper(Scraper):
             return
 
         property_id = result["property_id"]
-        prop_details = self.process_extra_property_details(result) if self.extra_property_data else {}
+        prop_details = self.get_prop_details(property_id) if self.extra_property_data and query_name != "home" else {}
+        if not prop_details:
+            prop_details = self.process_extra_property_details(result)
 
         property_estimates_root = result.get("current_estimates") or result.get("estimates", {}).get("currentValues")
         estimated_value = self.get_key(property_estimates_root, [0, "estimate"])
@@ -232,7 +233,7 @@ class RealtorScraper(Scraper):
         )
         return realty_property
 
-    def general_search(self, variables: dict, search_type: str) -> Dict[str, Union[int, Union[list[Property], list[dict]]]]:
+    def general_search(self, variables: dict, search_type: str) -> Dict[str, Union[int, list[Property]]]:
         """
         Handles a location area & returns a list of properties
         """
@@ -257,7 +258,7 @@ class RealtorScraper(Scraper):
         sort_param = (
             "sort: [{ field: sold_date, direction: desc }]"
             if self.listing_type == ListingType.SOLD
-            else ""  #: "sort: [{ field: list_date, direction: desc }]"  #: prioritize normal fractal sort from realtor
+            else "sort: [{ field: list_date, direction: desc }]"
         )
 
         pending_or_contingent_param = (
@@ -305,20 +306,24 @@ class RealtorScraper(Scraper):
             )
         elif search_type == "area":  #: general search, came from a general location
             query = """query Home_search(
-                                $location: String!,
+                                $city: String,
+                                $county: [String],
+                                $state_code: String,
+                                $postal_code: String
                                 $offset: Int,
                             ) {
                                 home_search(
                                     query: {
                                         %s
-                                        search_location: {location: $location}
+                                        city: $city
+                                        county: $county
+                                        postal_code: $postal_code
+                                        state_code: $state_code
                                         status: %s
-                                        unique: true
                                         %s
                                         %s
                                         %s
                                     }
-                                    bucket: { sort: "fractal_v1.1.3_fr" }
                                     %s
                                     limit: 200
                                     offset: $offset
@@ -358,7 +363,7 @@ class RealtorScraper(Scraper):
         response_json = response.json()
         search_key = "home_search" if "home_search" in query else "property_search"
 
-        properties: list[Union[Property, dict]] = []
+        properties: list[Property] = []
 
         if (
             response_json is None
@@ -376,25 +381,15 @@ class RealtorScraper(Scraper):
 
         #: limit the number of properties to be processed
         #: example, if your offset is 200, and your limit is 250, return 50
-        properties_list: list[dict] = properties_list[: self.limit - offset]
+        properties_list = properties_list[: self.limit - offset]
 
-        if self.extra_property_data:
-            property_ids = [data["property_id"] for data in properties_list]
-            extra_property_details = self.get_bulk_prop_details(property_ids) or {}
-
-            for result in properties_list:
-                result.update(extra_property_details.get(result["property_id"], {}))
-
-        if self.return_type != ReturnType.raw:
         with ThreadPoolExecutor(max_workers=self.NUM_PROPERTY_WORKERS) as executor:
-                futures = [executor.submit(self.process_property, result) for result in properties_list]
+            futures = [executor.submit(self.process_property, result, search_key) for result in properties_list]
 
             for future in as_completed(futures):
                 result = future.result()
                 if result:
                     properties.append(result)
-        else:
-            properties = properties_list
 
         return {
             "total": total_properties,
@@ -439,7 +434,10 @@ class RealtorScraper(Scraper):
 
         else:  #: general search, location
             search_variables |= {
-                "location": self.location,
+                "city": location_info.get("city"),
+                "county": location_info.get("county"),
+                "state_code": location_info.get("state_code"),
+                "postal_code": location_info.get("postal_code"),
             }
 
         if self.foreclosure:
@@ -522,35 +520,28 @@ class RealtorScraper(Scraper):
         wait=wait_exponential(min=4, max=10),
         stop=stop_after_attempt(3),
     )
-    def get_bulk_prop_details(self, property_ids: list[str]) -> dict:
+    def get_prop_details(self, property_id: str) -> dict:
-        """
+        if not self.extra_property_data:
-        Fetch extra property details for multiple properties in a single GraphQL query.
-        Returns a map of property_id to its details.
-        """
-        if not self.extra_property_data or not property_ids:
             return {}
 
-        property_ids = list(set(property_ids))
+        query = """query GetHome($property_id: ID!) {
+                    home(property_id: $property_id) {
+                        __typename
 
-        # Construct the bulk query
+                        nearbySchools: nearby_schools(radius: 5.0, limit_per_level: 3) {
-        fragments = "\n".join(
+                            __typename schools { district { __typename id name } }
-            f'home_{property_id}: home(property_id: {property_id}) {{ ...HomeData }}'
+                        }
-            for property_id in property_ids
+                        taxHistory: tax_history { __typename tax year assessment { __typename building land total } }
-        )
+                    }
-        query = f"""{HOME_FRAGMENT}
+                }"""
 
-        query GetHomes {{
+        variables = {"property_id": property_id}
-            {fragments}
+        response = self.session.post(self.SEARCH_GQL_URL, json={"query": query, "variables": variables})
-        }}"""
 
-        response = self.session.post(self.SEARCH_GQL_URL, json={"query": query})
         data = response.json()
+        property_details = data["data"]["home"]
 
-        if "data" not in data:
+        return self.process_extra_property_details(property_details)
-            return {}
-
-        properties = data["data"]
-        return {data.replace('home_', ''): properties[data] for data in properties if properties[data]}
 
     @staticmethod
     def _parse_neighborhoods(result: dict) -> Optional[str]:

homeharvest/core/scrapers/realtor/queries.py

@@ -11,34 +11,6 @@ _SEARCH_HOMES_DATA_BASE = """{
     list_price_max
     list_price_min
     price_per_sqft
-    tags
-    details {
-        category
-        text
-        parent_category
-    }
-    pet_policy {
-        cats
-        dogs
-        dogs_small
-        dogs_large
-        __typename
-    }
-    units {
-        availability {
-          date
-          __typename
-        }
-        description {
-          baths_consolidated
-          baths
-          beds
-          sqft
-          __typename
-        }
-        list_price
-        __typename
-    }
     flags {
         is_contingent
         is_pending
@@ -92,14 +64,11 @@ _SEARCH_HOMES_DATA_BASE = """{
     tax_record {
         public_record_id
     }
-    primary_photo(https: true) {
+    primary_photo {
         href
     }
-    photos(https: true) {
+    photos {
         href
-        tags {
-            label
-        }
     }
     advertisers {
         email
@@ -147,63 +116,15 @@ _SEARCH_HOMES_DATA_BASE = """{
         }
         rental_management {
             name
-            href
             fulfillment_id
         }
     }
     """
 
-
-HOME_FRAGMENT = """
-fragment HomeData on Home {
-    property_id
-    nearbySchools: nearby_schools(radius: 5.0, limit_per_level: 3) {
-        __typename schools { district { __typename id name } }
-    }
-    taxHistory: tax_history { __typename tax year assessment { __typename building land total } }
-    monthly_fees {
-        description
-        display_amount
-    }
-    one_time_fees {
-        description
-        display_amount
-    }
-    parking {
-        unassigned_space_rent
-        assigned_spaces_available
-        description
-        assigned_space_rent
-    }
-    terms {
-        text
-        category
-    }
-}
-"""
-
 HOMES_DATA = """%s
                 nearbySchools: nearby_schools(radius: 5.0, limit_per_level: 3) {
                             __typename schools { district { __typename id name } }
                         }
-                monthly_fees {
-                    description
-                    display_amount
-                }
-                one_time_fees {
-                    description
-                    display_amount
-                }
-                parking {
-                    unassigned_space_rent
-                    assigned_spaces_available
-                    description
-                    assigned_space_rent
-                }
-                terms {
-                    text
-                    category
-                }
                 taxHistory: tax_history { __typename tax year assessment { __typename building land total } }
                 estimates {
                     __typename
@@ -220,7 +141,7 @@ HOMES_DATA = """%s
 }""" % _SEARCH_HOMES_DATA_BASE
 
 SEARCH_HOMES_DATA = """%s
-current_estimates {
+                    current_estimates {
                             __typename
                             source {
                                 __typename
@@ -232,7 +153,7 @@ current_estimates {
                             estimateLow: estimate_low
                             date
                             isBestHomeValue: isbest_homevalue
-}
+                        }
 }""" % _SEARCH_HOMES_DATA_BASE
 
 GENERAL_RESULTS_QUERY = """{

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.4.7"
+version = "0.4.5"
 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

@@ -1,5 +1,4 @@
-from homeharvest import scrape_property, Property
+from homeharvest import scrape_property
-import pandas as pd
 
 
 def test_realtor_pending_or_contingent():
@@ -288,15 +287,3 @@ def test_phone_number_matching():
 
     #: assert phone numbers are the same
     assert row["agent_phones"].values[0] == matching_row["agent_phones"].values[0]
-
-
-def test_return_type():
-    results = {
-        "pandas": scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100),
-        "pydantic": scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100, return_type="pydantic"),
-        "raw": scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100, return_type="raw"),
-    }
-
-    assert isinstance(results["pandas"], pd.DataFrame)
-    assert isinstance(results["pydantic"][0], Property)
-    assert isinstance(results["raw"][0], dict)