docs: add gif

Minor fixes

.gitignore

@@ -2,4 +2,5 @@
 **/dist/
 **/__pycache__/
 **/.pytest_cache/
-*.pyc
+*.pyc
+/.ipynb_checkpoints/

HomeHarvest_Demo.ipynb

@@ -0,0 +1,118 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cb48903e-5021-49fe-9688-45cd0bc05d0f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from homeharvest import scrape_property\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "156488ce-0d5f-43c5-87f4-c33e9c427860",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pd.set_option('display.max_columns', None)  # Show all columns\n",
+    "pd.set_option('display.max_rows', None)     # Show all rows\n",
+    "pd.set_option('display.width', None)        # Auto-adjust display width to fit console\n",
+    "pd.set_option('display.max_colwidth', 50)   # Limit max column width to 50 characters"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1c8b9744-8606-4e9b-8add-b90371a249a7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# scrapes all 3 sites by default\n",
+    "scrape_property(\n",
+    "    location=\"dallas\",\n",
+    "    listing_type=\"for_sale\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aaf86093",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# search a specific address\n",
+    "scrape_property(\n",
+    "    location=\"2530 Al Lipscomb Way\",\n",
+    "    site_name=\"zillow\",\n",
+    "    listing_type=\"for_sale\"\n",
+    "),"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ab7b4c21-da1d-4713-9df4-d7425d8ce21e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# check rentals\n",
+    "scrape_property(\n",
+    "    location=\"chicago\",\n",
+    "    site_name=[\"redfin\", \"realtor.com\"],\n",
+    "    listing_type=\"for_rent\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "af280cd3",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# check sold properties\n",
+    "scrape_property(\n",
+    "    location=\"chicago, illinois\",\n",
+    "    site_name=[\"redfin\"],\n",
+    "    listing_type=\"sold\"\n",
+    ")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

README.md

@@ -1,35 +1,137 @@
-# HomeHarvest
+<img src="https://github.com/ZacharyHampton/HomeHarvest/assets/78247585/d1a2bf8b-09f5-4c57-b33a-0ada8a34f12d" width="400">
 
-**HomeHarvest** aims to be the top Python real estate scraping library.
+**HomeHarvest** is a simple, yet comprehensive, real estate scraping library.
 
-## RoadMap
+[![Try with Replit](https://replit.com/badge?caption=Try%20with%20Replit)](https://replit.com/@ZacharyHampton/HomeHarvestDemo)
 
-- **Supported Sites**: Currently, we support scraping from sites such as `Zillow` and `RedFin`.
-- **Output**: Provides the option to return the scraped data as a Pandas dataframe.
-- **Under Consideration**: We're looking into the possibility of an Excel plugin to cater to a broader audience.
+*Looking to build a data-focused software product?* **[Book a call](https://calendly.com/zachary-products/15min)** *to work with us.*
+## Features
 
-## Site Name Options
+- Scrapes properties from **Zillow**, **Realtor.com** & **Redfin** simultaneously
+- Aggregates the properties in a Pandas DataFrame
+  
+![homeharvest](https://github.com/ZacharyHampton/HomeHarvest/assets/78247585/b3d5d727-e67b-4a9f-85d8-1e65fd18620a)
 
-- `zillow`
-- `redfin`
-
-## Listing Types
-
-- `for_rent`
-- `for_sale`
-
-### Installation
+## Installation
 
 ```bash
 pip install --upgrade homeharvest
 ```
-
-### Example Usage
-```
+  _Python version >= [3.10](https://www.python.org/downloads/release/python-3100/) required_ 
+  
+## Usage
+```py
 from homeharvest import scrape_property
+import pandas as pd
 
-properties = scrape_property(
-    location="85281", site_name="zillow", listing_type="for_rent"
+properties: pd.DataFrame = scrape_property(
+    site_name=["zillow", "realtor.com", "redfin"],
+    location="85281",
+    listing_type="for_rent" # for_sale / sold
 )
+
+#: Note, to export to CSV or Excel, use properties.to_csv() or properties.to_excel().
 print(properties)
 ```
+## Output
+```py
+>>> properties.head()
+                           street   city  ... mls_id description
+0                 420 N  Scottsdale Rd  Tempe  ...    NaN         NaN
+1                1255 E  University Dr  Tempe  ...    NaN         NaN
+2              1979 E  Rio Salado Pkwy  Tempe  ...    NaN         NaN
+3                      548 S Wilson St  Tempe  ...   None        None
+4  945 E  Playa Del Norte Dr Unit 4027  Tempe  ...    NaN         NaN
+[5 rows x 23 columns]
+```
+
+### Parameters for `scrape_properties()`
+```plaintext
+Required
+├── location (str): address in various formats e.g. just zip, full address, city/state, etc.
+└── listing_type (enum): for_rent, for_sale, sold
+Optional
+├── site_name (List[enum], default=all three sites): zillow, realtor.com, redfin
+```
+
+### Property Schema
+```plaintext
+Property
+├── Basic Information:
+│   ├── property_url (str)
+│   ├── site_name (enum): zillow, redfin, realtor.com
+│   ├── listing_type (enum: ListingType)
+│   └── property_type (enum): house, apartment, condo, townhouse, single_family, multi_family, building
+
+├── Address Details:
+│   ├── street_address (str)
+│   ├── city (str)
+│   ├── state (str)
+│   ├── zip_code (str)
+│   ├── unit (str)
+│   └── country (str)
+
+├── Property Features:
+│   ├── price (int)
+│   ├── tax_assessed_value (int)
+│   ├── currency (str)
+│   ├── square_feet (int)
+│   ├── beds (int)
+│   ├── baths (float)
+│   ├── lot_area_value (float)
+│   ├── lot_area_unit (str)
+│   ├── stories (int)
+│   └── year_built (int)
+
+├── Miscellaneous Details:
+│   ├── price_per_sqft (int)
+│   ├── mls_id (str)
+│   ├── agent_name (str)
+│   ├── img_src (str)
+│   ├── description (str)
+│   ├── status_text (str)
+│   ├── latitude (float)
+│   ├── longitude (float)
+│   └── posted_time (str) [Only for Zillow]
+
+├── Building Details (for property_type: building):
+│   ├── bldg_name (str)
+│   ├── bldg_unit_count (int)
+│   ├── bldg_min_beds (int)
+│   ├── bldg_min_baths (float)
+│   └── bldg_min_area (int)
+
+└── Apartment Details (for property type: apartment):
+    └── apt_min_price (int)
+```
+## Supported Countries for Property Scraping
+
+* **Zillow**: contains listings in the **US** & **Canada** 
+* **Realtor.com**: mainly from the **US** but also has international listings
+* **Redfin**: listings mainly in the **US**, **Canada**, & has expanded to some areas in **Mexico**
+
+### Exceptions
+The following exceptions may be raised when using HomeHarvest:
+
+- `InvalidSite` - valid options: `zillow`, `redfin`, `realtor.com`
+- `InvalidListingType` - valid options: `for_sale`, `for_rent`, `sold`
+- `NoResultsFound` - no properties found from your input
+- `GeoCoordsNotFound` - if Zillow scraper is not able to create geo-coordinates from the location you input
+
+## Frequently Asked Questions
+
+---
+
+**Q: Encountering issues with your queries?**  
+**A:** Try a single site and/or broaden the location. If problems persist, [submit an issue](https://github.com/ZacharyHampton/HomeHarvest/issues).
+
+---
+
+**Q: Received a Forbidden 403 response code?**  
+**A:** This indicates that you have been blocked by the real estate site for sending too many requests. Currently, **Zillow** is particularly aggressive with blocking. We recommend:
+
+- Waiting a few seconds between requests.
+- Trying a VPN to change your IP address.
+
+---
+

homeharvest/__init__.py

@@ -1,10 +1,14 @@
+import pandas as pd
+from typing import Union
+import concurrent.futures
+from concurrent.futures import ThreadPoolExecutor
+
+from .core.scrapers import ScraperInput
 from .core.scrapers.redfin import RedfinScraper
 from .core.scrapers.realtor import RealtorScraper
 from .core.scrapers.zillow import ZillowScraper
-from .core.scrapers.models import ListingType, Property, Building
-from .core.scrapers import ScraperInput
+from .core.scrapers.models import ListingType, Property, SiteName
 from .exceptions import InvalidSite, InvalidListingType
-from typing import Union
 
 
 _scrapers = {
@@ -13,12 +17,7 @@ _scrapers = {
     "zillow": ZillowScraper,
 }
 
-
-def scrape_property(
-    location: str,
-    site_name: str,
-    listing_type: str = "for_sale",  #: for_sale, for_rent, sold
-) -> Union[list[Building], list[Property]]:  #: eventually, return pandas dataframe
+def validate_input(site_name: str, listing_type: str) -> None:
     if site_name.lower() not in _scrapers:
         raise InvalidSite(f"Provided site, '{site_name}', does not exist.")
 
@@ -27,11 +26,136 @@ def scrape_property(
             f"Provided listing type, '{listing_type}', does not exist."
         )
 
+def get_ordered_properties(result: Property) -> list[str]:
+    return [
+        "property_url",
+        "site_name",
+        "listing_type",
+        "property_type",
+        "status_text",
+        "currency",
+        "price",
+        "apt_min_price",
+        "tax_assessed_value",
+        "square_feet",
+        "price_per_sqft",
+        "beds",
+        "baths",
+        "lot_area_value",
+        "lot_area_unit",
+        "street_address",
+        "unit",
+        "city",
+        "state",
+        "zip_code",
+        "country",
+        "posted_time",
+        "bldg_min_beds",
+        "bldg_min_baths",
+        "bldg_min_area",
+        "bldg_unit_count",
+        "bldg_name",
+        "stories",
+        "year_built",
+        "agent_name",
+        "mls_id",
+        "description",
+        "img_src",
+        "latitude",
+        "longitude",
+    ]
+
+def process_result(result: Property) -> pd.DataFrame:
+    prop_data = result.__dict__
+
+    prop_data["site_name"] = prop_data["site_name"].value
+    prop_data["listing_type"] = prop_data["listing_type"].value.lower()
+    if "property_type" in prop_data and prop_data["property_type"] is not None:
+        prop_data["property_type"] = prop_data["property_type"].value.lower()
+    else:
+        prop_data["property_type"] = None
+    if "address" in prop_data:
+        address_data = prop_data["address"]
+        prop_data["street_address"] = address_data.street_address
+        prop_data["unit"] = address_data.unit
+        prop_data["city"] = address_data.city
+        prop_data["state"] = address_data.state
+        prop_data["zip_code"] = address_data.zip_code
+        prop_data["country"] = address_data.country
+
+        del prop_data["address"]
+
+    properties_df = pd.DataFrame([prop_data])
+    properties_df = properties_df[get_ordered_properties(result)]
+
+    return properties_df
+
+def _scrape_single_site(
+    location: str, site_name: str, listing_type: str
+) -> pd.DataFrame:
+    """
+    Helper function to scrape a single site.
+    """
+    validate_input(site_name, listing_type)
+
     scraper_input = ScraperInput(
         location=location,
         listing_type=ListingType[listing_type.upper()],
+        site_name=SiteName.get_by_value(site_name.lower()),
     )
 
     site = _scrapers[site_name.lower()](scraper_input)
+    results = site.search()
 
-    return site.search()
+    properties_dfs = [process_result(result) for result in results]
+    properties_dfs = [df.dropna(axis=1, how='all') for df in properties_dfs if not df.empty]
+    if not properties_dfs:
+        return pd.DataFrame()
+
+    return pd.concat(properties_dfs, ignore_index=True)
+
+
+def scrape_property(
+    location: str,
+    site_name: Union[str, list[str]] = None,
+    listing_type: str = "for_sale",
+) -> pd.DataFrame:
+    """
+    Scrape property from various sites from a given location and listing type.
+
+    :returns: pd.DataFrame
+    :param location: US Location (e.g. 'San Francisco, CA', 'Cook County, IL', '85281', '2530 Al Lipscomb Way')
+    :param site_name: Site name or list of site names (e.g. ['realtor.com', 'zillow'], 'redfin')
+    :param listing_type: Listing type (e.g. 'for_sale', 'for_rent', 'sold')
+    :return: pd.DataFrame containing properties
+    """
+    if site_name is None:
+        site_name = list(_scrapers.keys())
+
+    if not isinstance(site_name, list):
+        site_name = [site_name]
+
+    results = []
+
+    if len(site_name) == 1:
+        final_df = _scrape_single_site(location, site_name[0], listing_type)
+        results.append(final_df)
+    else:
+        with ThreadPoolExecutor() as executor:
+            futures = {
+                executor.submit(_scrape_single_site, location, s_name, listing_type): s_name
+                for s_name in site_name
+            }
+
+            for future in concurrent.futures.as_completed(futures):
+                result = future.result()
+                results.append(result)
+
+    results = [df for df in results if not df.empty and not df.isna().all().all()]
+
+    if not results:
+        return pd.DataFrame()
+
+    final_df = pd.concat(results, ignore_index=True)
+    final_df = final_df.drop_duplicates(subset=["street_address", "city", "unit"], keep="first")
+    return final_df

homeharvest/core/scrapers/__init__.py

@@ -1,22 +1,24 @@
 from dataclasses import dataclass
 import requests
-from .models import Property, ListingType
+from .models import Property, ListingType, SiteName
 
 
 @dataclass
 class ScraperInput:
     location: str
     listing_type: ListingType
+    site_name: SiteName
     proxy_url: str | None = None
 
 
 class Scraper:
-    listing_type = ListingType.FOR_SALE
-
     def __init__(self, scraper_input: ScraperInput):
         self.location = scraper_input.location
+        self.listing_type = scraper_input.listing_type
+
         self.session = requests.Session()
-        Scraper.listing_type = scraper_input.listing_type
+        self.listing_type = scraper_input.listing_type
+        self.site_name = scraper_input.site_name
 
         if scraper_input.proxy_url:
             self.session.proxies = {

homeharvest/core/scrapers/models.py

@@ -2,51 +2,104 @@ from dataclasses import dataclass
 from enum import Enum
 
 
+class SiteName(Enum):
+    ZILLOW = "zillow"
+    REDFIN = "redfin"
+    REALTOR = "realtor.com"
+
+    @classmethod
+    def get_by_value(cls, value):
+        for item in cls:
+            if item.value == value:
+                return item
+        raise ValueError(f"{value} not found in {cls}")
+
+
 class ListingType(Enum):
-    FOR_SALE = "for_sale"
-    FOR_RENT = "for_rent"
-    SOLD = "sold"
+    FOR_SALE = "FOR_SALE"
+    FOR_RENT = "FOR_RENT"
+    SOLD = "SOLD"
+
+
+class PropertyType(Enum):
+    HOUSE = "HOUSE"
+    BUILDING = "BUILDING"
+    CONDO = "CONDO"
+    TOWNHOUSE = "TOWNHOUSE"
+    SINGLE_FAMILY = "SINGLE_FAMILY"
+    MULTI_FAMILY = "MULTI_FAMILY"
+    MANUFACTURED = "MANUFACTURED"
+    NEW_CONSTRUCTION = "NEW_CONSTRUCTION"
+    APARTMENT = "APARTMENT"
+    APARTMENTS = "APARTMENTS"
+    LAND = "LAND"
+    LOT = "LOT"
+    OTHER = "OTHER"
+
+    BLANK = "BLANK"
+
+    @classmethod
+    def from_int_code(cls, code):
+        mapping = {
+            1: cls.HOUSE,
+            2: cls.CONDO,
+            3: cls.TOWNHOUSE,
+            4: cls.MULTI_FAMILY,
+            5: cls.LAND,
+            6: cls.OTHER,
+            8: cls.SINGLE_FAMILY,
+            13: cls.SINGLE_FAMILY,
+        }
+
+        return mapping.get(code, cls.BLANK)
 
 
 @dataclass
 class Address:
-    address_one: str
+    street_address: str
     city: str
     state: str
     zip_code: str
-
-    address_two: str | None = None
+    unit: str | None = None
+    country: str | None = None
 
 
 @dataclass
 class Property:
+    property_url: str
+    site_name: SiteName
+    listing_type: ListingType
     address: Address
-    url: str
+    property_type: PropertyType | None = None
 
+    # house for sale
+    price: int | None = None
+    tax_assessed_value: int | None = None
+    currency: str | None = None
+    square_feet: int | None = None
     beds: int | None = None
     baths: float | None = None
+    lot_area_value: float | None = None
+    lot_area_unit: str | None = None
     stories: int | None = None
-    agent_name: str | None = None
     year_built: int | None = None
-    square_feet: int | None = None
-    price_per_square_foot: int | None = None
-    year_built: int | None = None
-    price: int | None = None
+    price_per_sqft: int | None = None
     mls_id: str | None = None
 
-    listing_type: ListingType | None = None
-    lot_size: int | None = None
+    agent_name: str | None = None
+    img_src: str | None = None
     description: str | None = None
+    status_text: str | None = None
+    latitude: float | None = None
+    longitude: float | None = None
+    posted_time: str | None = None
 
+    # building for sale
+    bldg_name: str | None = None
+    bldg_unit_count: int | None = None
+    bldg_min_beds: int | None = None
+    bldg_min_baths: float | None = None
+    bldg_min_area: int | None = None
 
-@dataclass
-class Building:
-    address: Address
-    url: str
-
-    num_units: int | None = None
-    min_unit_price: int | None = None
-    max_unit_price: int | None = None
-    avg_unit_price: int | None = None
-
-    listing_type: str | None = None
+    # apt
+    apt_min_price: int | None = None

homeharvest/core/scrapers/realtor/__init__.py

@@ -1,12 +1,16 @@
 import json
 from ..models import Property, Address
 from .. import Scraper
-from typing import Any
+from typing import Any, Generator
+from ....exceptions import NoResultsFound
+from ....utils import parse_address_two, parse_unit
+from concurrent.futures import ThreadPoolExecutor, as_completed
 
 
 class RealtorScraper(Scraper):
     def __init__(self, scraper_input):
         super().__init__(scraper_input)
+        self.search_url = "https://www.realtor.com/api/v1/rdc_search_srp?client_id=rdc-search-new-communities&schema=vesta"
 
     def handle_location(self):
         headers = {
@@ -26,7 +30,7 @@ class RealtorScraper(Scraper):
 
         params = {
             "input": self.location,
-            "client_id": "for-sale",
+            "client_id": self.listing_type.value.lower().replace("_", "-"),
             "limit": "1",
             "area_types": "city,state,county,postal_code,address,street,neighborhood,school,school_district,university,park",
         }
@@ -38,14 +42,265 @@ class RealtorScraper(Scraper):
         )
         response_json = response.json()
 
-        return response_json["autocomplete"][0]
+        result = response_json["autocomplete"]
+
+        if result is None:
+            raise NoResultsFound("No results found for location: " + self.location)
+
+        return result[0]
+
+    def handle_address(self, property_id: str) -> list[Property]:
+        query = """query Property($property_id: ID!) {
+                    property(id: $property_id) {
+                        property_id
+                        details {
+                            date_updated
+                            garage
+                            permalink
+                            year_built
+                            stories
+                        }
+                        address {
+                            address_validation_code
+                            city
+                            country
+                            county
+                            line
+                            postal_code
+                            state_code
+                            street_direction
+                            street_name
+                            street_number
+                            street_suffix
+                            street_post_direction
+                            unit_value
+                            unit
+                            unit_descriptor
+                            zip
+                        }
+                        basic {
+                            baths
+                            beds
+                            price
+                            sqft
+                            lot_sqft
+                            type
+                            sold_price
+                        }
+                        public_record {
+                            lot_size
+                            sqft
+                            stories
+                            units
+                            year_built
+                        }
+                    }
+                }"""
+
+        variables = {"property_id": property_id}
+
+        payload = {
+            "query": query,
+            "variables": variables,
+        }
+
+        response = self.session.post(self.search_url, json=payload)
+        response_json = response.json()
+
+        property_info = response_json["data"]["property"]
+        street_address, unit = parse_address_two(property_info["address"]["line"])
+
+        return [
+            Property(
+                site_name=self.site_name,
+                address=Address(
+                    street_address=street_address,
+                    city=property_info["address"]["city"],
+                    state=property_info["address"]["state_code"],
+                    zip_code=property_info["address"]["postal_code"],
+                    unit=unit,
+                    country="USA",
+                ),
+                property_url="https://www.realtor.com/realestateandhomes-detail/"
+                + property_info["details"]["permalink"],
+                beds=property_info["basic"]["beds"],
+                baths=property_info["basic"]["baths"],
+                stories=property_info["details"]["stories"],
+                year_built=property_info["details"]["year_built"],
+                square_feet=property_info["basic"]["sqft"],
+                price_per_sqft=property_info["basic"]["price"]
+                // property_info["basic"]["sqft"]
+                if property_info["basic"]["sqft"] is not None
+                and property_info["basic"]["price"] is not None
+                else None,
+                price=property_info["basic"]["price"],
+                mls_id=property_id,
+                listing_type=self.listing_type,
+                lot_area_value=property_info["public_record"]["lot_size"]
+                if property_info["public_record"] is not None
+                else None,
+            )
+        ]
+
+    def handle_area(
+        self, variables: dict, return_total: bool = False
+    ) -> list[Property] | int:
+        query = (
+            """query Home_search(
+                            $city: String,
+                            $county: [String],
+                            $state_code: String,
+                            $postal_code: String
+                            $offset: Int,
+                        ) {
+                            home_search(
+                                query: {
+                                    city: $city
+                                    county: $county
+                                    postal_code: $postal_code
+                                    state_code: $state_code
+                                    status: %s
+                                }
+                                limit: 200
+                                offset: $offset
+                            ) {
+                                count
+                                total
+                                results {
+                                    property_id
+                                    description {
+                                        baths
+                                        beds
+                                        lot_sqft
+                                        sqft
+                                        text
+                                        sold_price
+                                        stories
+                                        year_built
+                                        garage
+                                        unit_number
+                                        floor_number
+                                    }
+                                    location {
+                                        address {
+                                            city
+                                            country
+                                            line
+                                            postal_code
+                                            state_code
+                                            state
+                                            street_direction
+                                            street_name
+                                            street_number
+                                            street_post_direction
+                                            street_suffix
+                                            unit
+                                            coordinate {
+                                                lon
+                                                lat
+                                            }
+                                        }
+                                    }
+                                    list_price
+                                    price_per_sqft
+                                    source {
+                                        id
+                                    }
+                                }
+                            }
+                        }"""
+            % self.listing_type.value.lower()
+        )
+
+        payload = {
+            "query": query,
+            "variables": variables,
+        }
+
+        response = self.session.post(self.search_url, json=payload)
+        response.raise_for_status()
+        response_json = response.json()
+
+        if return_total:
+            return response_json["data"]["home_search"]["total"]
+
+        properties: list[Property] = []
+
+        if (
+            response_json is None
+            or "data" not in response_json
+            or response_json["data"] is None
+            or "home_search" not in response_json["data"]
+            or response_json["data"]["home_search"] is None
+            or "results" not in response_json["data"]["home_search"]
+        ):
+            return []
+
+        for result in response_json["data"]["home_search"]["results"]:
+            street_address, unit = parse_address_two(
+                result["location"]["address"]["line"]
+            )
+            realty_property = Property(
+                address=Address(
+                    street_address=street_address,
+                    city=result["location"]["address"]["city"],
+                    state=result["location"]["address"]["state_code"],
+                    zip_code=result["location"]["address"]["postal_code"],
+                    unit=parse_unit(result["location"]["address"]["unit"]),
+                    country="USA",
+                ),
+                latitude=result["location"]["address"]["coordinate"]["lat"] if result and result.get("location") and result["location"].get("address") and result["location"]["address"].get("coordinate") and "lat" in result["location"]["address"]["coordinate"] else None,
+                longitude=result["location"]["address"]["coordinate"]["lon"] if result and result.get("location") and result["location"].get("address") and result["location"]["address"].get("coordinate") and "lon" in result["location"]["address"]["coordinate"] else None,
+                site_name=self.site_name,
+                property_url="https://www.realtor.com/realestateandhomes-detail/"
+                + result["property_id"],
+                beds=result["description"]["beds"],
+                baths=result["description"]["baths"],
+                stories=result["description"]["stories"],
+                year_built=result["description"]["year_built"],
+                square_feet=result["description"]["sqft"],
+                price_per_sqft=result["price_per_sqft"],
+                price=result["list_price"],
+                mls_id=result["property_id"],
+                listing_type=self.listing_type,
+                lot_area_value=result["description"]["lot_sqft"],
+            )
+
+            properties.append(realty_property)
+
+        return properties
 
     def search(self):
         location_info = self.handle_location()
         location_type = location_info["area_type"]
 
-        """
-        property types:
-        apartment + building + commercial + condo_townhome + condo_townhome_rowhome_coop + condos + coop + duplex_triplex + farm + investment + land + mobile + multi_family + rental + single_family + townhomes
-        """
-        print("a")
+        if location_type == "address":
+            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,
+        }
+
+        total = self.handle_area(search_variables, return_total=True)
+
+        homes = []
+        with ThreadPoolExecutor(max_workers=10) as executor:
+            futures = [
+                executor.submit(
+                    self.handle_area,
+                    variables=search_variables | {"offset": i},
+                    return_total=False,
+                )
+                for i in range(0, total, 200)
+            ]
+
+            for future in as_completed(futures):
+                homes.extend(future.result())
+
+        return homes

homeharvest/core/scrapers/redfin/__init__.py

@@ -1,12 +1,14 @@
 import json
-from ..models import Property, Address
-from .. import Scraper
 from typing import Any
+from .. import Scraper
+from ....utils import parse_address_two, parse_unit
+from ..models import Property, Address, PropertyType
 
 
 class RedfinScraper(Scraper):
     def __init__(self, scraper_input):
         super().__init__(scraper_input)
+        self.listing_type = scraper_input.listing_type
 
     def _handle_location(self):
         url = "https://www.redfin.com/stingray/do/location-autocomplete?v=2&al=1&location={}".format(
@@ -31,34 +33,53 @@ class RedfinScraper(Scraper):
 
         return target["id"].split("_")[1], get_region_type(target["type"])
 
-    @staticmethod
-    def _parse_home(home: dict, single_search: bool = False) -> Property:
+    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:
+            street_address, unit = parse_address_two(get_value("streetLine"))
+            unit = parse_unit(get_value("streetLine"))
             address = Address(
-                address_one=get_value("streetLine"),
+                street_address=street_address,
                 city=home["city"],
                 state=home["state"],
                 zip_code=home["zip"],
+                unit=unit,
+                country="USA",
             )
         else:
             address_info = home["streetAddress"]
+            street_address, unit = parse_address_two(address_info["assembledAddress"])
 
             address = Address(
-                address_one=address_info["assembledAddress"],
+                street_address=street_address,
                 city=home["city"],
                 state=home["state"],
                 zip_code=home["zip"],
+                unit=unit,
+                country="USA",
             )
 
         url = "https://www.redfin.com{}".format(home["url"])
+        #: property_type = home["propertyType"] if "propertyType" in home else None
+        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
 
         return Property(
+            site_name=self.site_name,
+            listing_type=self.listing_type,
             address=address,
-            url=url,
+            property_url=url,
             beds=home["beds"] if "beds" in home else None,
             baths=home["baths"] if "baths" in home else None,
             stories=home["stories"] if "stories" in home else None,
@@ -68,9 +89,45 @@ class RedfinScraper(Scraper):
             if not single_search
             else home["yearBuilt"],
             square_feet=get_value("sqFt"),
-            price_per_square_foot=get_value("pricePerSqFt"),
+            lot_area_value=lot_size,
+            property_type=PropertyType.from_int_code(home.get("propertyType")),
+            price_per_sqft=get_value("pricePerSqFt"),
             price=get_value("price"),
             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
+        )
+
+    def _parse_building(self, building: dict) -> Property:
+        street_address = " ".join(
+            [
+                building["address"]["streetNumber"],
+                building["address"]["directionalPrefix"],
+                building["address"]["streetName"],
+                building["address"]["streetType"],
+            ]
+        )
+        street_address, unit = parse_address_two(street_address)
+        return Property(
+            site_name=self.site_name,
+            property_type=PropertyType("BUILDING"),
+            address=Address(
+                street_address=street_address,
+                city=building["address"]["city"],
+                state=building["address"]["stateOrProvinceCode"],
+                zip_code=building["address"]["postalCode"],
+                unit=parse_unit(
+                    " ".join(
+                        [
+                            building["address"]["unitType"],
+                            building["address"]["unitValue"],
+                        ]
+                    )
+                ),
+            ),
+            property_url="https://www.redfin.com{}".format(building["url"]),
+            listing_type=self.listing_type,
+            bldg_unit_count=building["numUnitsForSale"],
         )
 
     def handle_address(self, home_id: str):
@@ -110,5 +167,9 @@ class RedfinScraper(Scraper):
 
         homes = [
             self._parse_home(home) for home in response_json["payload"]["homes"]
-        ]  #: support buildings
+        ] + [
+            self._parse_building(building)
+            for building in response_json["payload"]["buildings"].values()
+        ]
+
         return homes

homeharvest/core/scrapers/zillow/__init__.py

@@ -1,19 +1,21 @@
 import re
 import json
-from ..models import Property, Address, Building, ListingType
-from ....exceptions import NoResultsFound, PropertyNotFound
 from .. import Scraper
+from ....utils import parse_address_two, parse_unit
+from ....exceptions import GeoCoordsNotFound
+from ..models import Property, Address, ListingType, PropertyType, SiteName
 
 
 class ZillowScraper(Scraper):
-    listing_type: ListingType.FOR_SALE
-
     def __init__(self, scraper_input):
         super().__init__(scraper_input)
+        self.listing_type = scraper_input.listing_type
         if self.listing_type == ListingType.FOR_SALE:
             self.url = f"https://www.zillow.com/homes/for_sale/{self.location}_rb/"
         elif self.listing_type == ListingType.FOR_RENT:
             self.url = f"https://www.zillow.com/homes/for_rent/{self.location}_rb/"
+        else:
+            self.url = f"https://www.zillow.com/homes/recently_sold/{self.location}_rb/"
 
     def search(self):
         resp = self.session.get(self.url, headers=self._get_headers())
@@ -34,10 +36,17 @@ class ZillowScraper(Scraper):
         data = json.loads(json_str)
 
         if "searchPageState" in data["props"]["pageProps"]:
-            houses = data["props"]["pageProps"]["searchPageState"]["cat1"][
-                "searchResults"
-            ]["listResults"]
-            return [self._parse_home(house) for house in houses]
+            pattern = r'window\.mapBounds = \{\s*"west":\s*(-?\d+\.\d+),\s*"east":\s*(-?\d+\.\d+),\s*"south":\s*(-?\d+\.\d+),\s*"north":\s*(-?\d+\.\d+)\s*\};'
+
+            match = re.search(pattern, content)
+
+            if match:
+                coords = [float(coord) for coord in match.groups()]
+                return self._fetch_properties_backend(coords)
+
+            else:
+                raise GeoCoordsNotFound("Box bounds could not be located.")
+
         elif "gdpClientCache" in data["props"]["pageProps"]:
             gdp_client_cache = json.loads(data["props"]["pageProps"]["gdpClientCache"])
             main_key = list(gdp_client_cache.keys())[0]
@@ -46,47 +55,167 @@ class ZillowScraper(Scraper):
             property = self._get_single_property_page(property_data)
 
             return [property]
-        raise PropertyNotFound("Specific property data not found in the response.")
+        raise NoResultsFound("Specific property data not found in the response.")
 
-    @classmethod
-    def _parse_home(cls, home: dict):
-        """
-        This method is used when a user enters a generic location & zillow returns more than one property
-        """
-        url = (
-            f"https://www.zillow.com{home['detailUrl']}"
-            if "zillow.com" not in home["detailUrl"]
-            else home["detailUrl"]
+    def _fetch_properties_backend(self, coords):
+        url = "https://www.zillow.com/async-create-search-page-state"
+
+        filter_state_for_sale = {
+            "sortSelection": {
+                # "value": "globalrelevanceex"
+                "value": "days"
+            },
+            "isAllHomes": {"value": True},
+        }
+
+        filter_state_for_rent = {
+            "isForRent": {"value": True},
+            "isForSaleByAgent": {"value": False},
+            "isForSaleByOwner": {"value": False},
+            "isNewConstruction": {"value": False},
+            "isComingSoon": {"value": False},
+            "isAuction": {"value": False},
+            "isForSaleForeclosure": {"value": False},
+            "isAllHomes": {"value": True},
+        }
+
+        filter_state_sold = {
+            "isRecentlySold": {"value": True},
+            "isForSaleByAgent": {"value": False},
+            "isForSaleByOwner": {"value": False},
+            "isNewConstruction": {"value": False},
+            "isComingSoon": {"value": False},
+            "isAuction": {"value": False},
+            "isForSaleForeclosure": {"value": False},
+            "isAllHomes": {"value": True},
+        }
+
+        selected_filter = (
+            filter_state_for_rent
+            if self.listing_type == ListingType.FOR_RENT
+            else filter_state_for_sale
+            if self.listing_type == ListingType.FOR_SALE
+            else filter_state_sold
         )
 
-        if "hdpData" in home and "homeInfo" in home["hdpData"]:
-            price_data = cls._extract_price(home)
-            address = cls._extract_address(home)
-            agent_name = cls._extract_agent_name(home)
-            beds = home["hdpData"]["homeInfo"]["bedrooms"]
-            baths = home["hdpData"]["homeInfo"]["bathrooms"]
-            listing_type = home["hdpData"]["homeInfo"].get("homeType")
+        payload = {
+            "searchQueryState": {
+                "pagination": {},
+                "isMapVisible": True,
+                "mapBounds": {
+                    "west": coords[0],
+                    "east": coords[1],
+                    "south": coords[2],
+                    "north": coords[3],
+                },
+                "filterState": selected_filter,
+                "isListVisible": True,
+                "mapZoom": 11,
+            },
+            "wants": {"cat1": ["mapResults"]},
+            "isDebugRequest": False,
+        }
+        resp = self.session.put(url, headers=self._get_headers(), json=payload)
+        resp.raise_for_status()
+        a = resp.json()
+        return self._parse_properties(resp.json())
 
-            return Property(
-                address=address,
-                agent_name=agent_name,
-                url=url,
-                beds=beds,
-                baths=baths,
-                listing_type=listing_type,
-                **price_data,
-            )
-        else:
-            keys = ("addressStreet", "addressCity", "addressState", "addressZipcode")
-            address_one, city, state, zip_code = (home[key] for key in keys)
-            address_one, address_two = cls._parse_address_two(address_one)
-            address = Address(address_one, city, state, zip_code, address_two)
+    def _parse_properties(self, property_data: dict):
+        mapresults = property_data["cat1"]["searchResults"]["mapResults"]
 
-            building_info = cls._extract_building_info(home)
-            return Building(address=address, url=url, **building_info)
+        properties_list = []
 
-    @classmethod
-    def _get_single_property_page(cls, property_data: dict):
+        for result in mapresults:
+            if "hdpData" in result:
+                home_info = result["hdpData"]["homeInfo"]
+                address_data = {
+                    "street_address": parse_address_two(home_info["streetAddress"])[0],
+                    "unit": parse_unit(home_info["unit"])
+                    if "unit" in home_info
+                    else None,
+                    "city": home_info["city"],
+                    "state": home_info["state"],
+                    "zip_code": home_info["zipcode"],
+                    "country": home_info["country"],
+                }
+                property_data = {
+                    "site_name": self.site_name,
+                    "address": Address(**address_data),
+                    "property_url": f"https://www.zillow.com{result['detailUrl']}",
+                    "beds": int(home_info["bedrooms"])
+                    if "bedrooms" in home_info
+                    else None,
+                    "baths": home_info.get("bathrooms"),
+                    "square_feet": int(home_info["livingArea"])
+                    if "livingArea" in home_info
+                    else None,
+                    "currency": home_info["currency"],
+                    "price": home_info.get("price"),
+                    "square_feet": int(home_info["livingArea"])
+                    if "livingArea" in home_info
+                    else None,
+                    "tax_assessed_value": int(home_info["taxAssessedValue"])
+                    if "taxAssessedValue" in home_info
+                    else None,
+                    "property_type": PropertyType(home_info["homeType"]),
+                    "listing_type": ListingType(
+                        home_info["statusType"]
+                        if "statusType" in home_info
+                        else self.listing_type
+                    ),
+                    "lot_area_value": round(home_info["lotAreaValue"], 2)
+                    if "lotAreaValue" in home_info
+                    else None,
+                    "lot_area_unit": home_info.get("lotAreaUnit"),
+                    "latitude": result["latLong"]["latitude"],
+                    "longitude": result["latLong"]["longitude"],
+                    "status_text": result.get("statusText"),
+                    "posted_time": result["variableData"]["text"]
+                    if "variableData" in result
+                    and "text" in result["variableData"]
+                    and result["variableData"]["type"] == "TIME_ON_INFO"
+                    else None,
+                    "img_src": result.get("imgSrc"),
+                    "price_per_sqft": int(home_info["price"] // home_info["livingArea"])
+                    if "livingArea" in home_info and "price" in home_info
+                    else None,
+                }
+                property_obj = Property(**property_data)
+                properties_list.append(property_obj)
+
+            elif "isBuilding" in result:
+                price = result["price"]
+                building_data = {
+                    "property_url": f"https://www.zillow.com{result['detailUrl']}",
+                    "site_name": self.site_name,
+                    "property_type": PropertyType("BUILDING"),
+                    "listing_type": ListingType(result["statusType"]),
+                    "img_src": result["imgSrc"],
+                    "price": int(price.replace("From $", "").replace(",", ""))
+                    if "From $" in price
+                    else None,
+                    "apt_min_price": int(
+                        price.replace("$", "").replace(",", "").replace("+/mo", "")
+                    )
+                    if "+/mo" in price
+                    else None,
+                    "address": self._extract_address(result["address"]),
+                    "bldg_min_beds": result["minBeds"],
+                    "currency": "USD",
+                    "bldg_min_baths": result["minBaths"],
+                    "bldg_min_area": result.get("minArea"),
+                    "bldg_unit_count": result["unitCount"],
+                    "bldg_name": result.get("communityName"),
+                    "status_text": result["statusText"],
+                    "latitude": result["latLong"]["latitude"],
+                    "longitude": result["latLong"]["longitude"],
+                }
+                building_obj = Property(**building_data)
+                properties_list.append(building_obj)
+
+        return properties_list
+
+    def _get_single_property_page(self, property_data: dict):
         """
         This method is used when a user enters the exact location & zillow returns just one property
         """
@@ -96,110 +225,93 @@ class ZillowScraper(Scraper):
             else property_data["hdpUrl"]
         )
         address_data = property_data["address"]
-        address_one, address_two = cls._parse_address_two(address_data["streetAddress"])
+        street_address, unit = parse_address_two(address_data["streetAddress"])
         address = Address(
-            address_one=address_one,
-            address_two=address_two,
+            street_address=street_address,
+            unit=unit,
             city=address_data["city"],
             state=address_data["state"],
             zip_code=address_data["zipcode"],
+            country=property_data.get("country"),
         )
-
+        property_type = property_data.get("homeType", None)
         return Property(
+            site_name=self.site_name,
             address=address,
-            url=url,
+            property_url=url,
             beds=property_data.get("bedrooms", None),
             baths=property_data.get("bathrooms", None),
             year_built=property_data.get("yearBuilt", None),
             price=property_data.get("price", None),
-            lot_size=property_data.get("lotSize", None),
+            tax_assessed_value=property_data.get("taxAssessedValue", None),
+            latitude=property_data.get("latitude"),
+            longitude=property_data.get("longitude"),
+            img_src=property_data.get("streetViewTileImageUrlMediumAddress"),
+            currency=property_data.get("currency", None),
+            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", None),
             stories=property_data.get("resoFacts", {}).get("stories", None),
             description=property_data.get("description", None),
             mls_id=property_data.get("attributionInfo", {}).get("mlsId", None),
-            price_per_square_foot=property_data.get("resoFacts", {}).get(
+            price_per_sqft=property_data.get("resoFacts", {}).get(
                 "pricePerSquareFoot", None
             ),
             square_feet=property_data.get("livingArea", None),
-            listing_type=property_data.get("homeType", None),
+            property_type=PropertyType(property_type),
+            listing_type=self.listing_type,
         )
 
-    @classmethod
-    def _extract_building_info(cls, home: dict) -> dict:
-        num_units = len(home["units"])
-        prices = [
-            int(unit["price"].replace("$", "").replace(",", "").split("+")[0])
-            for unit in home["units"]
-        ]
-        return {
-            "listing_type": cls.listing_type,
-            "num_units": len(home["units"]),
-            "min_unit_price": min(
-                (
-                    int(unit["price"].replace("$", "").replace(",", "").split("+")[0])
-                    for unit in home["units"]
-                )
-            ),
-            "max_unit_price": max(
-                (
-                    int(unit["price"].replace("$", "").replace(",", "").split("+")[0])
-                    for unit in home["units"]
-                )
-            ),
-            "avg_unit_price": sum(prices) // len(prices) if num_units else None,
-        }
+    def _extract_address(self, address_str):
+        """
+        Extract address components from a string formatted like '555 Wedglea Dr, Dallas, TX',
+        and return an Address object.
+        """
+        parts = address_str.split(", ")
 
-    @staticmethod
-    def _extract_price(home: dict) -> dict:
-        price = int(home["hdpData"]["homeInfo"]["priceForHDP"])
-        square_feet = home["hdpData"]["homeInfo"].get("livingArea")
+        if len(parts) != 3:
+            raise ValueError(f"Unexpected address format: {address_str}")
 
-        lot_size = home["hdpData"]["homeInfo"].get("lotAreaValue")
-        price_per_square_foot = price // square_feet if square_feet and price else None
+        street_address = parts[0].strip()
+        city = parts[1].strip()
+        state_zip = parts[2].split(" ")
 
-        return {
-            k: v
-            for k, v in locals().items()
-            if k in ["price", "square_feet", "lot_size", "price_per_square_foot"]
-        }
+        if len(state_zip) == 1:
+            state = state_zip[0].strip()
+            zip_code = None
+        elif len(state_zip) == 2:
+            state = state_zip[0].strip()
+            zip_code = state_zip[1].strip()
+        else:
+            raise ValueError(f"Unexpected state/zip format in address: {address_str}")
 
-    @staticmethod
-    def _extract_agent_name(home: dict) -> str | None:
-        broker_str = home.get("brokerName", "")
-        match = re.search(r"Listing by: (.+)", broker_str)
-        return match.group(1) if match else None
-
-    @staticmethod
-    def _parse_address_two(address_one: str):
-        apt_match = re.search(r"(APT\s*.+|#[\s\S]+)$", address_one, re.I)
-        address_two = apt_match.group().strip() if apt_match else None
-        address_one = (
-            address_one.replace(address_two, "").strip() if address_two else address_one
+        street_address, unit = parse_address_two(street_address)
+        return Address(
+            street_address=street_address,
+            city=city,
+            unit=unit,
+            state=state,
+            zip_code=zip_code,
+            country="USA",
         )
-        return address_one, address_two
-
-    @staticmethod
-    def _extract_address(home: dict) -> Address:
-        keys = ("streetAddress", "city", "state", "zipcode")
-        address_one, city, state, zip_code = (
-            home["hdpData"]["homeInfo"][key] for key in keys
-        )
-        address_one, address_two = ZillowScraper._parse_address_two(address_one)
-        return Address(address_one, city, state, zip_code, address_two=address_two)
 
     @staticmethod
     def _get_headers():
         return {
-            "authority": "parser-external.geo.moveaws.com",
+            "authority": "www.zillow.com",
             "accept": "*/*",
             "accept-language": "en-US,en;q=0.9",
+            "content-type": "application/json",
+            "cookie": 'zjs_user_id=null; zg_anonymous_id=%220976ab81-2950-4013-98f0-108b15a554d2%22; zguid=24|%246b1bc625-3955-4d1e-a723-e59602e4ed08; g_state={"i_p":1693611172520,"i_l":1}; zgsession=1|d48820e2-1659-4d2f-b7d2-99a8127dd4f3; zjs_anonymous_id=%226b1bc625-3955-4d1e-a723-e59602e4ed08%22; JSESSIONID=82E8274D3DC8AF3AB9C8E613B38CF861; search=6|1697585860120%7Crb%3DDallas%252C-TX%26rect%3D33.016646%252C-96.555516%252C32.618763%252C-96.999347%26disp%3Dmap%26mdm%3Dauto%26sort%3Ddays%26listPriceActive%3D1%26fs%3D1%26fr%3D0%26mmm%3D0%26rs%3D0%26ah%3D0%26singlestory%3D0%26abo%3D0%26garage%3D0%26pool%3D0%26ac%3D0%26waterfront%3D0%26finished%3D0%26unfinished%3D0%26cityview%3D0%26mountainview%3D0%26parkview%3D0%26waterview%3D0%26hoadata%3D1%263dhome%3D0%26commuteMode%3Ddriving%26commuteTimeOfDay%3Dnow%09%0938128%09%7B%22isList%22%3Atrue%2C%22isMap%22%3Atrue%7D%09%09%09%09%09; AWSALB=gAlFj5Ngnd4bWP8k7CME/+YlTtX9bHK4yEkdPHa3VhL6K523oGyysFxBEpE1HNuuyL+GaRPvt2i/CSseAb+zEPpO4SNjnbLAJzJOOO01ipnWN3ZgPaa5qdv+fAki; AWSALBCORS=gAlFj5Ngnd4bWP8k7CME/+YlTtX9bHK4yEkdPHa3VhL6K523oGyysFxBEpE1HNuuyL+GaRPvt2i/CSseAb+zEPpO4SNjnbLAJzJOOO01ipnWN3ZgPaa5qdv+fAki; search=6|1697587741808%7Crect%3D33.37188814545521%2C-96.34484483007813%2C32.260490641365685%2C-97.21001816992188%26disp%3Dmap%26mdm%3Dauto%26p%3D1%26sort%3Ddays%26z%3D1%26listPriceActive%3D1%26fs%3D1%26fr%3D0%26mmm%3D0%26rs%3D0%26ah%3D0%26singlestory%3D0%26housing-connector%3D0%26abo%3D0%26garage%3D0%26pool%3D0%26ac%3D0%26waterfront%3D0%26finished%3D0%26unfinished%3D0%26cityview%3D0%26mountainview%3D0%26parkview%3D0%26waterview%3D0%26hoadata%3D1%26zillow-owned%3D0%263dhome%3D0%26featuredMultiFamilyBuilding%3D0%26commuteMode%3Ddriving%26commuteTimeOfDay%3Dnow%09%09%09%7B%22isList%22%3Atrue%2C%22isMap%22%3Atrue%7D%09%09%09%09%09',
             "origin": "https://www.zillow.com",
-            "referer": "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": "cross-site",
+            "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",
         }

homeharvest/exceptions.py

@@ -10,5 +10,5 @@ class NoResultsFound(Exception):
     """Raised when no results are found for the given location"""
 
 
-class PropertyNotFound(Exception):
+class GeoCoordsNotFound(Exception):
     """Raised when no property is found for the given address"""

homeharvest/utils.py

@@ -0,0 +1,48 @@
+import re
+
+
+def parse_address_two(street_address: str) -> tuple:
+    if not street_address:
+        return street_address, None
+
+    apt_match = re.search(
+        r"(APT\s*[\dA-Z]+|#[\dA-Z]+|UNIT\s*[\dA-Z]+|LOT\s*[\dA-Z]+|SUITE\s*[\dA-Z]+)$",
+        street_address,
+        re.I,
+    )
+
+    if apt_match:
+        apt_str = apt_match.group().strip()
+        cleaned_apt_str = re.sub(
+            r"(APT\s*|UNIT\s*|LOT\s*|SUITE\s*)", "#", apt_str, flags=re.I
+        )
+
+        main_address = street_address.replace(apt_str, "").strip()
+        return main_address, cleaned_apt_str
+    else:
+        return street_address, None
+
+
+def parse_unit(street_address: str):
+    if not street_address:
+        return None
+    apt_match = re.search(
+        r"(APT\s*[\dA-Z]+|#[\dA-Z]+|UNIT\s*[\dA-Z]+|LOT\s*[\dA-Z]+)$",
+        street_address,
+        re.I,
+    )
+
+    if apt_match:
+        apt_str = apt_match.group().strip()
+        apt_str = re.sub(r"(APT\s*|UNIT\s*|LOT\s*)", "#", apt_str, flags=re.I)
+        return apt_str
+    else:
+        return None
+
+
+if __name__ == "__main__":
+    print(parse_address_two("4303 E Cactus Rd Apt 126"))
+    print(parse_address_two("1234 Elm Street apt 2B"))
+    print(parse_address_two("1234 Elm Street UNIT 3A"))
+    print(parse_address_two("1234 Elm Street unit 3A"))
+    print(parse_address_two("1234 Elm Street SuIte 3A"))

poetry.lock

@@ -142,6 +142,81 @@ files = [
     {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
 ]
 
+[[package]]
+name = "numpy"
+version = "1.25.2"
+description = "Fundamental package for array computing in Python"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "numpy-1.25.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:db3ccc4e37a6873045580d413fe79b68e47a681af8db2e046f1dacfa11f86eb3"},
+    {file = "numpy-1.25.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:90319e4f002795ccfc9050110bbbaa16c944b1c37c0baeea43c5fb881693ae1f"},
+    {file = "numpy-1.25.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dfe4a913e29b418d096e696ddd422d8a5d13ffba4ea91f9f60440a3b759b0187"},
+    {file = "numpy-1.25.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f08f2e037bba04e707eebf4bc934f1972a315c883a9e0ebfa8a7756eabf9e357"},
+    {file = "numpy-1.25.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:bec1e7213c7cb00d67093247f8c4db156fd03075f49876957dca4711306d39c9"},
+    {file = "numpy-1.25.2-cp310-cp310-win32.whl", hash = "sha256:7dc869c0c75988e1c693d0e2d5b26034644399dd929bc049db55395b1379e044"},
+    {file = "numpy-1.25.2-cp310-cp310-win_amd64.whl", hash = "sha256:834b386f2b8210dca38c71a6e0f4fd6922f7d3fcff935dbe3a570945acb1b545"},
+    {file = "numpy-1.25.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c5462d19336db4560041517dbb7759c21d181a67cb01b36ca109b2ae37d32418"},
+    {file = "numpy-1.25.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:c5652ea24d33585ea39eb6a6a15dac87a1206a692719ff45d53c5282e66d4a8f"},
+    {file = "numpy-1.25.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0d60fbae8e0019865fc4784745814cff1c421df5afee233db6d88ab4f14655a2"},
+    {file = "numpy-1.25.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:60e7f0f7f6d0eee8364b9a6304c2845b9c491ac706048c7e8cf47b83123b8dbf"},
+    {file = "numpy-1.25.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:bb33d5a1cf360304754913a350edda36d5b8c5331a8237268c48f91253c3a364"},
+    {file = "numpy-1.25.2-cp311-cp311-win32.whl", hash = "sha256:5883c06bb92f2e6c8181df7b39971a5fb436288db58b5a1c3967702d4278691d"},
+    {file = "numpy-1.25.2-cp311-cp311-win_amd64.whl", hash = "sha256:5c97325a0ba6f9d041feb9390924614b60b99209a71a69c876f71052521d42a4"},
+    {file = "numpy-1.25.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:b79e513d7aac42ae918db3ad1341a015488530d0bb2a6abcbdd10a3a829ccfd3"},
+    {file = "numpy-1.25.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:eb942bfb6f84df5ce05dbf4b46673ffed0d3da59f13635ea9b926af3deb76926"},
+    {file = "numpy-1.25.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e0746410e73384e70d286f93abf2520035250aad8c5714240b0492a7302fdca"},
+    {file = "numpy-1.25.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d7806500e4f5bdd04095e849265e55de20d8cc4b661b038957354327f6d9b295"},
+    {file = "numpy-1.25.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:8b77775f4b7df768967a7c8b3567e309f617dd5e99aeb886fa14dc1a0791141f"},
+    {file = "numpy-1.25.2-cp39-cp39-win32.whl", hash = "sha256:2792d23d62ec51e50ce4d4b7d73de8f67a2fd3ea710dcbc8563a51a03fb07b01"},
+    {file = "numpy-1.25.2-cp39-cp39-win_amd64.whl", hash = "sha256:76b4115d42a7dfc5d485d358728cdd8719be33cc5ec6ec08632a5d6fca2ed380"},
+    {file = "numpy-1.25.2-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:1a1329e26f46230bf77b02cc19e900db9b52f398d6722ca853349a782d4cff55"},
+    {file = "numpy-1.25.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4c3abc71e8b6edba80a01a52e66d83c5d14433cbcd26a40c329ec7ed09f37901"},
+    {file = "numpy-1.25.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:1b9735c27cea5d995496f46a8b1cd7b408b3f34b6d50459d9ac8fe3a20cc17bf"},
+    {file = "numpy-1.25.2.tar.gz", hash = "sha256:fd608e19c8d7c55021dffd43bfe5492fab8cc105cc8986f813f8c3c048b38760"},
+]
+
+[[package]]
+name = "numpy"
+version = "1.26.0"
+description = "Fundamental package for array computing in Python"
+optional = false
+python-versions = "<3.13,>=3.9"
+files = [
+    {file = "numpy-1.26.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f8db2f125746e44dce707dd44d4f4efeea8d7e2b43aace3f8d1f235cfa2733dd"},
+    {file = "numpy-1.26.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:0621f7daf973d34d18b4e4bafb210bbaf1ef5e0100b5fa750bd9cde84c7ac292"},
+    {file = "numpy-1.26.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:51be5f8c349fdd1a5568e72713a21f518e7d6707bcf8503b528b88d33b57dc68"},
+    {file = "numpy-1.26.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:767254ad364991ccfc4d81b8152912e53e103ec192d1bb4ea6b1f5a7117040be"},
+    {file = "numpy-1.26.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:436c8e9a4bdeeee84e3e59614d38c3dbd3235838a877af8c211cfcac8a80b8d3"},
+    {file = "numpy-1.26.0-cp310-cp310-win32.whl", hash = "sha256:c2e698cb0c6dda9372ea98a0344245ee65bdc1c9dd939cceed6bb91256837896"},
+    {file = "numpy-1.26.0-cp310-cp310-win_amd64.whl", hash = "sha256:09aaee96c2cbdea95de76ecb8a586cb687d281c881f5f17bfc0fb7f5890f6b91"},
+    {file = "numpy-1.26.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:637c58b468a69869258b8ae26f4a4c6ff8abffd4a8334c830ffb63e0feefe99a"},
+    {file = "numpy-1.26.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:306545e234503a24fe9ae95ebf84d25cba1fdc27db971aa2d9f1ab6bba19a9dd"},
+    {file = "numpy-1.26.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8c6adc33561bd1d46f81131d5352348350fc23df4d742bb246cdfca606ea1208"},
+    {file = "numpy-1.26.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e062aa24638bb5018b7841977c360d2f5917268d125c833a686b7cbabbec496c"},
+    {file = "numpy-1.26.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:546b7dd7e22f3c6861463bebb000646fa730e55df5ee4a0224408b5694cc6148"},
+    {file = "numpy-1.26.0-cp311-cp311-win32.whl", hash = "sha256:c0b45c8b65b79337dee5134d038346d30e109e9e2e9d43464a2970e5c0e93229"},
+    {file = "numpy-1.26.0-cp311-cp311-win_amd64.whl", hash = "sha256:eae430ecf5794cb7ae7fa3808740b015aa80747e5266153128ef055975a72b99"},
+    {file = "numpy-1.26.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:166b36197e9debc4e384e9c652ba60c0bacc216d0fc89e78f973a9760b503388"},
+    {file = "numpy-1.26.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:f042f66d0b4ae6d48e70e28d487376204d3cbf43b84c03bac57e28dac6151581"},
+    {file = "numpy-1.26.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e5e18e5b14a7560d8acf1c596688f4dfd19b4f2945b245a71e5af4ddb7422feb"},
+    {file = "numpy-1.26.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7f6bad22a791226d0a5c7c27a80a20e11cfe09ad5ef9084d4d3fc4a299cca505"},
+    {file = "numpy-1.26.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4acc65dd65da28060e206c8f27a573455ed724e6179941edb19f97e58161bb69"},
+    {file = "numpy-1.26.0-cp312-cp312-win32.whl", hash = "sha256:bb0d9a1aaf5f1cb7967320e80690a1d7ff69f1d47ebc5a9bea013e3a21faec95"},
+    {file = "numpy-1.26.0-cp312-cp312-win_amd64.whl", hash = "sha256:ee84ca3c58fe48b8ddafdeb1db87388dce2c3c3f701bf447b05e4cfcc3679112"},
+    {file = "numpy-1.26.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:4a873a8180479bc829313e8d9798d5234dfacfc2e8a7ac188418189bb8eafbd2"},
+    {file = "numpy-1.26.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:914b28d3215e0c721dc75db3ad6d62f51f630cb0c277e6b3bcb39519bed10bd8"},
+    {file = "numpy-1.26.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c78a22e95182fb2e7874712433eaa610478a3caf86f28c621708d35fa4fd6e7f"},
+    {file = "numpy-1.26.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:86f737708b366c36b76e953c46ba5827d8c27b7a8c9d0f471810728e5a2fe57c"},
+    {file = "numpy-1.26.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b44e6a09afc12952a7d2a58ca0a2429ee0d49a4f89d83a0a11052da696440e49"},
+    {file = "numpy-1.26.0-cp39-cp39-win32.whl", hash = "sha256:5671338034b820c8d58c81ad1dafc0ed5a00771a82fccc71d6438df00302094b"},
+    {file = "numpy-1.26.0-cp39-cp39-win_amd64.whl", hash = "sha256:020cdbee66ed46b671429c7265cf00d8ac91c046901c55684954c3958525dab2"},
+    {file = "numpy-1.26.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:0792824ce2f7ea0c82ed2e4fecc29bb86bee0567a080dacaf2e0a01fe7654369"},
+    {file = "numpy-1.26.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7d484292eaeb3e84a51432a94f53578689ffdea3f90e10c8b203a99be5af57d8"},
+    {file = "numpy-1.26.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:186ba67fad3c60dbe8a3abff3b67a91351100f2661c8e2a80364ae6279720299"},
+    {file = "numpy-1.26.0.tar.gz", hash = "sha256:f93fc78fe8bf15afe2b8d6b6499f1c73953169fad1e9a8dd086cdff3190e7fdf"},
+]
+
 [[package]]
 name = "packaging"
 version = "23.1"
@@ -153,6 +228,67 @@ files = [
     {file = "packaging-23.1.tar.gz", hash = "sha256:a392980d2b6cffa644431898be54b0045151319d1e7ec34f0cfed48767dd334f"},
 ]
 
+[[package]]
+name = "pandas"
+version = "2.1.0"
+description = "Powerful data structures for data analysis, time series, and statistics"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "pandas-2.1.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:40dd20439ff94f1b2ed55b393ecee9cb6f3b08104c2c40b0cb7186a2f0046242"},
+    {file = "pandas-2.1.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d4f38e4fedeba580285eaac7ede4f686c6701a9e618d8a857b138a126d067f2f"},
+    {file = "pandas-2.1.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6e6a0fe052cf27ceb29be9429428b4918f3740e37ff185658f40d8702f0b3e09"},
+    {file = "pandas-2.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9d81e1813191070440d4c7a413cb673052b3b4a984ffd86b8dd468c45742d3cc"},
+    {file = "pandas-2.1.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:eb20252720b1cc1b7d0b2879ffc7e0542dd568f24d7c4b2347cb035206936421"},
+    {file = "pandas-2.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:38f74ef7ebc0ffb43b3d633e23d74882bce7e27bfa09607f3c5d3e03ffd9a4a5"},
+    {file = "pandas-2.1.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cda72cc8c4761c8f1d97b169661f23a86b16fdb240bdc341173aee17e4d6cedd"},
+    {file = "pandas-2.1.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d97daeac0db8c993420b10da4f5f5b39b01fc9ca689a17844e07c0a35ac96b4b"},
+    {file = "pandas-2.1.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8c58b1113892e0c8078f006a167cc210a92bdae23322bb4614f2f0b7a4b510f"},
+    {file = "pandas-2.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:629124923bcf798965b054a540f9ccdfd60f71361255c81fa1ecd94a904b9dd3"},
+    {file = "pandas-2.1.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:70cf866af3ab346a10debba8ea78077cf3a8cd14bd5e4bed3d41555a3280041c"},
+    {file = "pandas-2.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:d53c8c1001f6a192ff1de1efe03b31a423d0eee2e9e855e69d004308e046e694"},
+    {file = "pandas-2.1.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:86f100b3876b8c6d1a2c66207288ead435dc71041ee4aea789e55ef0e06408cb"},
+    {file = "pandas-2.1.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:28f330845ad21c11db51e02d8d69acc9035edfd1116926ff7245c7215db57957"},
+    {file = "pandas-2.1.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b9a6ccf0963db88f9b12df6720e55f337447aea217f426a22d71f4213a3099a6"},
+    {file = "pandas-2.1.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d99e678180bc59b0c9443314297bddce4ad35727a1a2656dbe585fd78710b3b9"},
+    {file = "pandas-2.1.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b31da36d376d50a1a492efb18097b9101bdbd8b3fbb3f49006e02d4495d4c644"},
+    {file = "pandas-2.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:0164b85937707ec7f70b34a6c3a578dbf0f50787f910f21ca3b26a7fd3363437"},
+    {file = "pandas-2.1.0.tar.gz", hash = "sha256:62c24c7fc59e42b775ce0679cfa7b14a5f9bfb7643cfbe708c960699e05fb918"},
+]
+
+[package.dependencies]
+numpy = [
+    {version = ">=1.22.4", markers = "python_version < \"3.11\""},
+    {version = ">=1.23.2", markers = "python_version >= \"3.11\""},
+]
+python-dateutil = ">=2.8.2"
+pytz = ">=2020.1"
+tzdata = ">=2022.1"
+
+[package.extras]
+all = ["PyQt5 (>=5.15.6)", "SQLAlchemy (>=1.4.36)", "beautifulsoup4 (>=4.11.1)", "bottleneck (>=1.3.4)", "dataframe-api-compat (>=0.1.7)", "fastparquet (>=0.8.1)", "fsspec (>=2022.05.0)", "gcsfs (>=2022.05.0)", "html5lib (>=1.1)", "hypothesis (>=6.46.1)", "jinja2 (>=3.1.2)", "lxml (>=4.8.0)", "matplotlib (>=3.6.1)", "numba (>=0.55.2)", "numexpr (>=2.8.0)", "odfpy (>=1.4.1)", "openpyxl (>=3.0.10)", "pandas-gbq (>=0.17.5)", "psycopg2 (>=2.9.3)", "pyarrow (>=7.0.0)", "pymysql (>=1.0.2)", "pyreadstat (>=1.1.5)", "pytest (>=7.3.2)", "pytest-asyncio (>=0.17.0)", "pytest-xdist (>=2.2.0)", "pyxlsb (>=1.0.9)", "qtpy (>=2.2.0)", "s3fs (>=2022.05.0)", "scipy (>=1.8.1)", "tables (>=3.7.0)", "tabulate (>=0.8.10)", "xarray (>=2022.03.0)", "xlrd (>=2.0.1)", "xlsxwriter (>=3.0.3)", "zstandard (>=0.17.0)"]
+aws = ["s3fs (>=2022.05.0)"]
+clipboard = ["PyQt5 (>=5.15.6)", "qtpy (>=2.2.0)"]
+compression = ["zstandard (>=0.17.0)"]
+computation = ["scipy (>=1.8.1)", "xarray (>=2022.03.0)"]
+consortium-standard = ["dataframe-api-compat (>=0.1.7)"]
+excel = ["odfpy (>=1.4.1)", "openpyxl (>=3.0.10)", "pyxlsb (>=1.0.9)", "xlrd (>=2.0.1)", "xlsxwriter (>=3.0.3)"]
+feather = ["pyarrow (>=7.0.0)"]
+fss = ["fsspec (>=2022.05.0)"]
+gcp = ["gcsfs (>=2022.05.0)", "pandas-gbq (>=0.17.5)"]
+hdf5 = ["tables (>=3.7.0)"]
+html = ["beautifulsoup4 (>=4.11.1)", "html5lib (>=1.1)", "lxml (>=4.8.0)"]
+mysql = ["SQLAlchemy (>=1.4.36)", "pymysql (>=1.0.2)"]
+output-formatting = ["jinja2 (>=3.1.2)", "tabulate (>=0.8.10)"]
+parquet = ["pyarrow (>=7.0.0)"]
+performance = ["bottleneck (>=1.3.4)", "numba (>=0.55.2)", "numexpr (>=2.8.0)"]
+plot = ["matplotlib (>=3.6.1)"]
+postgresql = ["SQLAlchemy (>=1.4.36)", "psycopg2 (>=2.9.3)"]
+spss = ["pyreadstat (>=1.1.5)"]
+sql-other = ["SQLAlchemy (>=1.4.36)"]
+test = ["hypothesis (>=6.46.1)", "pytest (>=7.3.2)", "pytest-asyncio (>=0.17.0)", "pytest-xdist (>=2.2.0)"]
+xml = ["lxml (>=4.8.0)"]
+
 [[package]]
 name = "pluggy"
 version = "1.3.0"
@@ -190,6 +326,31 @@ tomli = {version = ">=1.0.0", markers = "python_version < \"3.11\""}
 [package.extras]
 testing = ["argcomplete", "attrs (>=19.2.0)", "hypothesis (>=3.56)", "mock", "nose", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
 
+[[package]]
+name = "python-dateutil"
+version = "2.8.2"
+description = "Extensions to the standard Python datetime module"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
+files = [
+    {file = "python-dateutil-2.8.2.tar.gz", hash = "sha256:0123cacc1627ae19ddf3c27a5de5bd67ee4586fbdd6440d9748f8abb483d3e86"},
+    {file = "python_dateutil-2.8.2-py2.py3-none-any.whl", hash = "sha256:961d03dc3453ebbc59dbdea9e4e11c5651520a876d0f4db161e8674aae935da9"},
+]
+
+[package.dependencies]
+six = ">=1.5"
+
+[[package]]
+name = "pytz"
+version = "2023.3.post1"
+description = "World timezone definitions, modern and historical"
+optional = false
+python-versions = "*"
+files = [
+    {file = "pytz-2023.3.post1-py2.py3-none-any.whl", hash = "sha256:ce42d816b81b68506614c11e8937d3aa9e41007ceb50bfdcb0749b921bf646c7"},
+    {file = "pytz-2023.3.post1.tar.gz", hash = "sha256:7b4fddbeb94a1eba4b557da24f19fdf9db575192544270a9101d8509f9f43d7b"},
+]
+
 [[package]]
 name = "requests"
 version = "2.31.0"
@@ -211,6 +372,17 @@ urllib3 = ">=1.21.1,<3"
 socks = ["PySocks (>=1.5.6,!=1.5.7)"]
 use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
 
+[[package]]
+name = "six"
+version = "1.16.0"
+description = "Python 2 and 3 compatibility utilities"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*"
+files = [
+    {file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"},
+    {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
+]
+
 [[package]]
 name = "tomli"
 version = "2.0.1"
@@ -222,6 +394,17 @@ files = [
     {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
 ]
 
+[[package]]
+name = "tzdata"
+version = "2023.3"
+description = "Provider of IANA time zone data"
+optional = false
+python-versions = ">=2"
+files = [
+    {file = "tzdata-2023.3-py2.py3-none-any.whl", hash = "sha256:7e65763eef3120314099b6939b5546db7adce1e7d6f2e179e3df563c70511eda"},
+    {file = "tzdata-2023.3.tar.gz", hash = "sha256:11ef1e08e54acb0d4f95bdb1be05da659673de4acbd21bf9c69e94cc5e907a3a"},
+]
+
 [[package]]
 name = "urllib3"
 version = "2.0.4"
@@ -242,4 +425,4 @@ zstd = ["zstandard (>=0.18.0)"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "bc3567f9501f9e18bf9f53d8b4efe1e7e3fc2d750ceda2fbab165bfa22d49c64"
+content-hash = "eede625d6d45085e143b0af246cb2ce00cff8579c667be3b63387c8594a5570d"

pyproject.toml

@@ -1,7 +1,7 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.1.2"
-description = "Real estate scraping library"
+version = "0.2.0"
+description = "Real estate scraping library supporting Zillow, Realtor.com & Redfin."
 authors = ["Zachary Hampton <zachary@zacharysproducts.com>", "Cullen Watson <cullen@cullen.ai>"]
 homepage = "https://github.com/ZacharyHampton/HomeHarvest"
 readme = "README.md"
@@ -9,6 +9,7 @@ readme = "README.md"
 [tool.poetry.dependencies]
 python = "^3.10"
 requests = "^2.31.0"
+pandas = "^2.1.0"
 
 
 [tool.poetry.group.dev.dependencies]

tests/test_realtor.py

@@ -3,6 +3,17 @@ from homeharvest import scrape_property
 
 def test_realtor():
     results = [
+        scrape_property(
+            location="2530 Al Lipscomb Way",
+            site_name="realtor.com",
+            listing_type="for_sale",
+        ),
+        scrape_property(
+            location="Phoenix, AZ", site_name=["realtor.com"], listing_type="for_rent"
+        ),  #: does not support "city, state, USA" format
+        scrape_property(
+            location="Dallas, TX", site_name="realtor.com", listing_type="sold"
+        ),  #: does not support "city, state, USA" format
         scrape_property(location="85281", site_name="realtor.com"),
     ]
 

tests/test_redfin.py

@@ -3,9 +3,15 @@ from homeharvest import scrape_property
 
 def test_redfin():
     results = [
-        scrape_property(location="2530 Al Lipscomb Way", site_name="redfin"),
-        scrape_property(location="Phoenix, AZ, USA", site_name="redfin"),
-        scrape_property(location="Dallas, TX, USA", site_name="redfin"),
+        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"
+        ),
         scrape_property(location="85281", site_name="redfin"),
     ]
 

tests/test_zillow.py

@@ -3,9 +3,15 @@ from homeharvest import scrape_property
 
 def test_zillow():
     results = [
-        scrape_property(location="2530 Al Lipscomb Way", site_name="zillow"),
-        scrape_property(location="Phoenix, AZ, USA", site_name="zillow"),
-        scrape_property(location="Dallas, TX, USA", site_name="zillow"),
+        scrape_property(
+            location="2530 Al Lipscomb Way", site_name="zillow", listing_type="for_sale"
+        ),
+        scrape_property(
+            location="Phoenix, AZ, USA", site_name=["zillow"], listing_type="for_rent"
+        ),
+        scrape_property(
+            location="Dallas, TX, USA", site_name="zillow", listing_type="sold"
+        ),
         scrape_property(location="85281", site_name="zillow"),
     ]