docs: tryhomeharvest.com

Keep duplicates flag

.gitignore

@@ -3,4 +3,5 @@
 **/__pycache__/
 **/.pytest_cache/
 *.pyc
-/.ipynb_checkpoints/
+/.ipynb_checkpoints/
+*.csv

HomeHarvest_Demo.ipynb

@@ -31,8 +31,30 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# scrapes all 3 sites by default\n",
     "scrape_property(\n",
-    "    location=\"dallas\", site_name=\"zillow\", listing_type=\"for_sale\"\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",
     ")"
    ]
   },
@@ -43,8 +65,31 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# check rentals\n",
     "scrape_property(\n",
-    "    location=\"dallas\", site_name=\"redfin\", listing_type=\"for_sale\"\n",
+    "    location=\"chicago, illinois\",\n",
+    "    site_name=[\"redfin\", \"zillow\"],\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=\"90210\",\n",
+    "    site_name=[\"redfin\"],\n",
+    "    listing_type=\"sold\"\n",
     ")"
    ]
   }

README.md

@@ -1,33 +1,163 @@
-# 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.
+**Not technical?** Try out the web scraping tool on our site at [tryhomeharvest.com](https://tryhomeharvest.com).
 
-_**Under Consideration**: We're looking into the possibility of an Excel plugin to cater to a broader audience._
+
+**HomeHarvest** is a simple, yet comprehensive, real estate scraping library.
+
+[![Try with Replit](https://replit.com/badge?caption=Try%20with%20Replit)](https://replit.com/@ZacharyHampton/HomeHarvestDemo)
+
+*Looking to build a data-focused software product?* **[Book a call](https://calendly.com/zachary-products/15min)** *to work with us.*
+## Features
+
+- Scrapes properties from **Zillow**, **Realtor.com** & **Redfin** simultaneously
+- Aggregates the properties in a Pandas DataFrame
+
+[Video Guide for HomeHarvest](https://youtu.be/JnV7eR2Ve2o) - _updated for release v0.2.7_
+
+![homeharvest](https://github.com/ZacharyHampton/HomeHarvest/assets/78247585/b3d5d727-e67b-4a9f-85d8-1e65fd18620a)
 
 ## Installation
 
 ```bash
-pip install --upgrade homeharvest
+pip install homeharvest
+```
+  _Python version >= [3.10](https://www.python.org/downloads/release/python-3100/) required_ 
+
+## Usage
+
+### CLI 
+
+```bash
+homeharvest "San Francisco, CA" -s zillow realtor.com redfin -l for_rent -o excel -f HomeHarvest
 ```
 
-## Example Usage
-```
+This will scrape properties from the specified sites for the given location and listing type, and save the results to an Excel file named `HomeHarvest.xlsx`.
+
+By default:
+- If `-s` or `--site_name` is not provided, it will scrape from all available sites.
+- If `-l` or `--listing_type` is left blank, the default is `for_sale`. Other options are `for_rent` or `sold`.
+- The `-o` or `--output` default format is `excel`. Options are `csv` or `excel`.
+- If `-f` or `--filename` is left blank, the default is `HomeHarvest_<current_timestamp>`.
+- If `-p` or `--proxy` is not provided, the scraper uses the local IP.
+- Use `-k` or `--keep_duplicates` to keep duplicate properties based on address. If not provided, duplicates will be removed.
+### Python 
+
+```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)
 ```
 
-### Site Name Options
+## Output
+```py
+>>> properties.head()
+                                        property_url site_name listing_type  apt_min_price  apt_max_price   ...  
+0  https://www.redfin.com/AZ/Tempe/1003-W-Washing...    redfin     for_rent         1666.0         2750.0   ... 
+1  https://www.redfin.com/AZ/Tempe/VELA-at-Town-L...    redfin     for_rent         1665.0         3763.0   ...  
+2  https://www.redfin.com/AZ/Tempe/Camden-Tempe/a...    redfin     for_rent         1939.0         3109.0   ...  
+3  https://www.redfin.com/AZ/Tempe/Emerson-Park/a...    redfin     for_rent         1185.0         1817.0   ... 
+4  https://www.redfin.com/AZ/Tempe/Rio-Paradiso-A...    redfin     for_rent         1470.0         2235.0   ...   
+[5 rows x 41 columns]
+```
 
-- `zillow`
-- `redfin`
-- `realtor.com`
+### 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
+├── proxy (str): in format 'http://user:pass@host:port' or [https, socks]
+└── keep_duplicates (bool, default=False): whether to keep or remove duplicate properties based on address
+```
 
-### Listing Types
+### Property Schema
+```plaintext
+Property
+├── Basic Information:
+│   ├── property_url (str)
+│   ├── site_name (enum): zillow, redfin, realtor.com
+│   ├── listing_type (enum): for_sale, for_rent, sold
+│   └── 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)
+
+├── House for Sale Features:
+│   ├── tax_assessed_value (int)
+│   ├── lot_area_value (float)
+│   ├── lot_area_unit (str)
+│   ├── stories (int)
+│   ├── year_built (int)
+│   └── price_per_sqft (int)
+
+├── Building for Sale and Apartment Details:
+│   ├── bldg_name (str)
+│   ├── beds_min (int)
+│   ├── beds_max (int)
+│   ├── baths_min (float)
+│   ├── baths_max (float)
+│   ├── sqft_min (int)
+│   ├── sqft_max (int)
+│   ├── price_min (int)
+│   ├── price_max (int)
+│   ├── area_min (int)
+│   └── unit_count (int)
+
+├── Miscellaneous Details:
+│   ├── mls_id (str)
+│   ├── agent_name (str)
+│   ├── img_src (str)
+│   ├── description (str)
+│   ├── status_text (str)
+│   └── posted_time (str)
+
+└── Location Details:
+    ├── latitude (float)
+    └── longitude (float)
+```
+## 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 derive 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.
+
+---
 
-- `for_rent`
-- `for_sale`
-- `sold`

homeharvest/__init__.py

@@ -1,11 +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, SiteName
-from .core.scrapers import ScraperInput
+from .core.scrapers.models import ListingType, Property, SiteName
 from .exceptions import InvalidSite, InvalidListingType
-from typing import Union
-import pandas as pd
 
 
 _scrapers = {
@@ -15,103 +18,154 @@ _scrapers = {
 }
 
 
-def validate_input(site_name: str, listing_type: str) -> None:
+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.")
 
     if listing_type.upper() not in ListingType.__members__:
-        raise InvalidListingType(
-            f"Provided listing type, '{listing_type}', does not exist."
-        )
+        raise InvalidListingType(f"Provided listing type, '{listing_type}', does not exist.")
 
 
-def get_ordered_properties(result: Union[Building, Property]) -> list[str]:
-    if isinstance(result, Property):
-        return [
-            "listing_type",
-            "address_one",
-            "city",
-            "state",
-            "zip_code",
-            "address_two",
-            "url",
-            "property_type",
-            "price",
-            "beds",
-            "baths",
-            "square_feet",
-            "price_per_square_foot",
-            "lot_size",
-            "stories",
-            "year_built",
-            "agent_name",
-            "mls_id",
-            "description",
-        ]
-    elif isinstance(result, Building):
-        return [
-            "address_one",
-            "city",
-            "state",
-            "zip_code",
-            "address_two",
-            "url",
-            "num_units",
-            "min_unit_price",
-            "max_unit_price",
-            "avg_unit_price",
-            "listing_type",
-        ]
-    return []
+def _get_ordered_properties(result: Property) -> list[str]:
+    return [
+        "property_url",
+        "site_name",
+        "listing_type",
+        "property_type",
+        "status_text",
+        "baths_min",
+        "baths_max",
+        "beds_min",
+        "beds_max",
+        "sqft_min",
+        "sqft_max",
+        "price_min",
+        "price_max",
+        "unit_count",
+        "tax_assessed_value",
+        "price_per_sqft",
+        "lot_area_value",
+        "lot_area_unit",
+        "address_one",
+        "address_two",
+        "city",
+        "state",
+        "zip_code",
+        "posted_time",
+        "area_min",
+        "bldg_name",
+        "stories",
+        "year_built",
+        "agent_name",
+        "mls_id",
+        "img_src",
+        "latitude",
+        "longitude",
+        "description",
+    ]
 
 
-def process_result(result: Union[Building, Property]) -> pd.DataFrame:
+def _process_result(result: Property) -> pd.DataFrame:
     prop_data = result.__dict__
 
-    address_data = prop_data["address"]
-    prop_data["site_name"] = prop_data["site_name"]
-    prop_data["listing_type"] = prop_data["listing_type"].value
-    prop_data["property_type"] = prop_data["property_type"].value.lower() if prop_data.get("property_type") else None
-    prop_data["address_one"] = address_data.address_one
-    prop_data["city"] = address_data.city
-    prop_data["state"] = address_data.state
-    prop_data["zip_code"] = address_data.zip_code
-    prop_data["address_two"] = address_data.address_two
+    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["address_one"] = address_data.address_one
+        prop_data["address_two"] = address_data.address_two
+        prop_data["city"] = address_data.city
+        prop_data["state"] = address_data.state
+        prop_data["zip_code"] = address_data.zip_code
 
-    del prop_data["address"]
+        del prop_data["address"]
 
     properties_df = pd.DataFrame([prop_data])
-    properties_df = properties_df[get_ordered_properties(result)]
+    properties_df = properties_df[_get_ordered_properties(result)]
 
     return properties_df
 
 
+def _scrape_single_site(location: str, site_name: str, listing_type: str, proxy: str = None) -> 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()),
+        proxy=proxy,
+    )
+
+    site = _scrapers[site_name.lower()](scraper_input)
+    results = 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: str,
-    listing_type: str = "for_sale",  #: for_sale, for_rent, sold
+    site_name: Union[str, list[str]] = None,
+    listing_type: str = "for_sale",
+    proxy: str = None,
+    keep_duplicates: bool = False
 ) -> 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 (e.g. 'realtor.com', 'zillow', 'redfin')
+    :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())
 
-    validate_input(site_name, listing_type)
+    if not isinstance(site_name, list):
+        site_name = [site_name]
 
-    scraper_input = ScraperInput(
-        location=location,
-        listing_type=ListingType[listing_type.upper()],
-        site_name=site_name.lower(),
-    )
+    results = []
 
-    site = _scrapers[site_name.lower()](scraper_input)
-    results = site.search()
+    if len(site_name) == 1:
+        final_df = _scrape_single_site(location, site_name[0], listing_type, proxy)
+        results.append(final_df)
+    else:
+        with ThreadPoolExecutor() as executor:
+            futures = {
+                executor.submit(_scrape_single_site, location, s_name, listing_type, proxy): s_name
+                for s_name in site_name
+            }
 
-    properties_dfs = [process_result(result) for result in results]
+            for future in concurrent.futures.as_completed(futures):
+                result = future.result()
+                results.append(result)
 
-    return pd.concat(properties_dfs, ignore_index=True)
+    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)
+
+    columns_to_track = ["address_one", "address_two", "city"]
+
+    #: validate they exist, otherwise create them
+    for col in columns_to_track:
+        if col not in final_df.columns:
+            final_df[col] = None
+
+    if not keep_duplicates:
+        final_df = final_df.drop_duplicates(subset=columns_to_track, keep="first")
+    return final_df

homeharvest/cli.py

@@ -0,0 +1,73 @@
+import argparse
+import datetime
+from homeharvest import scrape_property
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Home Harvest Property Scraper")
+    parser.add_argument("location", type=str, help="Location to scrape (e.g., San Francisco, CA)")
+
+    parser.add_argument(
+        "-s",
+        "--site_name",
+        type=str,
+        nargs="*",
+        default=None,
+        help="Site name(s) to scrape from (e.g., realtor, zillow)",
+    )
+
+    parser.add_argument(
+        "-l",
+        "--listing_type",
+        type=str,
+        default="for_sale",
+        choices=["for_sale", "for_rent", "sold"],
+        help="Listing type to scrape",
+    )
+
+    parser.add_argument(
+        "-o",
+        "--output",
+        type=str,
+        default="excel",
+        choices=["excel", "csv"],
+        help="Output format",
+    )
+
+    parser.add_argument(
+        "-f",
+        "--filename",
+        type=str,
+        default=None,
+        help="Name of the output file (without extension)",
+    )
+
+    parser.add_argument(
+        "-k",
+        "--keep_duplicates",
+        action="store_true",
+        help="Keep duplicate properties based on address"
+    )
+
+    parser.add_argument("-p", "--proxy", type=str, default=None, help="Proxy to use for scraping")
+
+    args = parser.parse_args()
+
+    result = scrape_property(args.location, args.site_name, args.listing_type, proxy=args.proxy, keep_duplicates=args.keep_duplicates)
+
+    if not args.filename:
+        timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
+        args.filename = f"HomeHarvest_{timestamp}"
+
+    if args.output == "excel":
+        output_filename = f"{args.filename}.xlsx"
+        result.to_excel(output_filename, index=False)
+        print(f"Excel file saved as {output_filename}")
+    elif args.output == "csv":
+        output_filename = f"{args.filename}.csv"
+        result.to_csv(output_filename, index=False)
+        print(f"CSV file saved as {output_filename}")
+
+
+if __name__ == "__main__":
+    main()

homeharvest/core/scrapers/__init__.py

@@ -7,8 +7,8 @@ from .models import Property, ListingType, SiteName
 class ScraperInput:
     location: str
     listing_type: ListingType
-    site_name: str
-    proxy_url: str | None = None
+    site_name: SiteName
+    proxy: str | None = None
 
 
 class Scraper:
@@ -17,15 +17,13 @@ class Scraper:
         self.listing_type = scraper_input.listing_type
 
         self.session = requests.Session()
+        if scraper_input.proxy:
+            proxy_url = scraper_input.proxy
+            proxies = {"http": proxy_url, "https": proxy_url}
+            self.session.proxies.update(proxies)
         self.listing_type = scraper_input.listing_type
         self.site_name = scraper_input.site_name
 
-        if scraper_input.proxy_url:
-            self.session.proxies = {
-                "http": scraper_input.proxy_url,
-                "https": scraper_input.proxy_url,
-            }
-
     def search(self) -> list[Property]:
         ...
 

homeharvest/core/scrapers/models.py

@@ -1,5 +1,6 @@
 from dataclasses import dataclass
 from enum import Enum
+from typing import Tuple
 
 
 class SiteName(Enum):
@@ -7,24 +8,37 @@ class SiteName(Enum):
     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 = {
@@ -38,47 +52,58 @@ class PropertyType(Enum):
             13: cls.SINGLE_FAMILY,
         }
 
-        return mapping.get(code, cls.OTHER)
+        return mapping.get(code, cls.BLANK)
 
 
 @dataclass
 class Address:
-    address_one: str
-    city: str
-    state: str
-    zip_code: str
-
-    address_two: str | None = None
-
-
-@dataclass()
-class Realty:
-    site_name: str
-    address: Address
-    url: str
-    listing_type: ListingType | None = None
+    address_one: str | None = None
+    address_two: str | None = "#"
+    city: str | None = None
+    state: str | None = None
+    zip_code: str | None = None
 
 
 @dataclass
-class Property(Realty):
-    price: int | None = None
-    beds: int | None = None
-    baths: float | None = None
+class Property:
+    property_url: str
+    site_name: SiteName
+    listing_type: ListingType
+    address: Address
+    property_type: PropertyType | None = None
+
+    # house for sale
+    tax_assessed_value: int | None = None
+    lot_area_value: float | None = None
+    lot_area_unit: str | None = None
     stories: int | None = None
     year_built: int | None = None
-    square_feet: int | None = None
-    price_per_square_foot: int | None = None
+    price_per_sqft: int | None = None
     mls_id: str | None = None
 
     agent_name: str | None = None
-    property_type: PropertyType | None = None
-    lot_size: int | None = None
+    img_src: str | None = None
     description: str | None = None
+    status_text: str | None = None
+    posted_time: str | None = None
 
+    # building for sale
+    bldg_name: str | None = None
+    area_min: int | None = None
 
-@dataclass
-class Building(Realty):
-    num_units: int | None = None
-    min_unit_price: int | None = None
-    max_unit_price: int | None = None
-    avg_unit_price: int | None = None
+    beds_min: int | None = None
+    beds_max: int | None = None
+
+    baths_min: float | None = None
+    baths_max: float | None = None
+
+    sqft_min: int | None = None
+    sqft_max: int | None = None
+
+    price_min: int | None = None
+    price_max: int | None = None
+
+    unit_count: int | None = None
+
+    latitude: float | None = None
+    longitude: float | None = None

homeharvest/core/scrapers/realtor/__init__.py

@@ -1,15 +1,23 @@
-import json
+"""
+homeharvest.realtor.__init__
+~~~~~~~~~~~~
+
+This module implements the scraper for relator.com
+"""
 from ..models import Property, Address
 from .. import Scraper
-from typing import Any, Generator
 from ....exceptions import NoResultsFound
+from ....utils import parse_address_one, parse_address_two
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
 
 class RealtorScraper(Scraper):
     def __init__(self, scraper_input):
+        self.counter = 1
         super().__init__(scraper_input)
-        self.search_url = "https://www.realtor.com/api/v1/rdc_search_srp?client_id=rdc-search-new-communities&schema=vesta"
+        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 = {
@@ -29,7 +37,7 @@ class RealtorScraper(Scraper):
 
         params = {
             "input": self.location,
-            "client_id": self.listing_type.value.replace('_', '-'),
+            "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",
         }
@@ -43,12 +51,15 @@ class RealtorScraper(Scraper):
 
         result = response_json["autocomplete"]
 
-        if result is None:
+        if not result:
             raise NoResultsFound("No results found for location: " + self.location)
 
         return result[0]
 
     def handle_address(self, property_id: str) -> list[Property]:
+        """
+        Handles a specific address & returns one property
+        """
         query = """query Property($property_id: ID!) {
                     property(id: $property_id) {
                         property_id
@@ -96,46 +107,58 @@ class RealtorScraper(Scraper):
                     }
                 }"""
 
-        variables = {
-            'property_id': property_id
-        }
+        variables = {"property_id": property_id}
 
         payload = {
-            'query': query,
-            'variables': variables,
+            "query": query,
+            "variables": variables,
         }
 
         response = self.session.post(self.search_url, json=payload)
         response_json = response.json()
 
-        property_info = response_json['data']['property']
+        property_info = response_json["data"]["property"]
+        address_one, address_two = parse_address_one(property_info["address"]["line"])
 
-        return [Property(
-            site_name=self.site_name,
-            address=Address(
-                address_one=property_info['address']['line'],
-                city=property_info['address']['city'],
-                state=property_info['address']['state_code'],
-                zip_code=property_info['address']['postal_code'],
-            ),
-            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_square_foot=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_size=property_info['public_record']['lot_size'] if property_info['public_record'] is not None else None,
-        )]
+        return [
+            Property(
+                site_name=self.site_name,
+                address=Address(
+                    address_one=address_one,
+                    address_two=address_two,
+                    city=property_info["address"]["city"],
+                    state=property_info["address"]["state_code"],
+                    zip_code=property_info["address"]["postal_code"],
+                ),
+                property_url="https://www.realtor.com/realestateandhomes-detail/"
+                + property_info["details"]["permalink"],
+                stories=property_info["details"]["stories"],
+                year_built=property_info["details"]["year_built"],
+                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,
+                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,
+                beds_min=property_info["basic"]["beds"],
+                beds_max=property_info["basic"]["beds"],
+                baths_min=property_info["basic"]["baths"],
+                baths_max=property_info["basic"]["baths"],
+                sqft_min=property_info["basic"]["sqft"],
+                sqft_max=property_info["basic"]["sqft"],
+                price_min=property_info["basic"]["price"],
+                price_max=property_info["basic"]["price"],
+            )
+        ]
 
     def handle_area(self, variables: dict, return_total: bool = False) -> list[Property] | int:
-        query = """query Home_search(
+        """
+        Handles a location area & returns a list of properties
+        """
+        query = (
+            """query Home_search(
                             $city: String,
                             $county: [String],
                             $state_code: String,
@@ -184,6 +207,10 @@ class RealtorScraper(Scraper):
                                             street_post_direction
                                             street_suffix
                                             unit
+                                            coordinate {
+                                                lon
+                                                lat
+                                            }
                                         }
                                     }
                                     list_price
@@ -193,44 +220,76 @@ class RealtorScraper(Scraper):
                                     }
                                 }
                             }
-                        }""" % self.listing_type.value
+                        }"""
+            % self.listing_type.value.lower()
+        )
 
         payload = {
-            'query': query,
-            'variables': variables,
+            "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']
+            return response_json["data"]["home_search"]["total"]
 
         properties: list[Property] = []
 
-        for result in response_json['data']['home_search']['results']:
+        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"]:
+            self.counter += 1
+            address_one, _ = parse_address_one(result["location"]["address"]["line"])
             realty_property = Property(
                 address=Address(
-                    address_one=result['location']['address']['line'],
-                    city=result['location']['address']['city'],
-                    state=result['location']['address']['state_code'],
-                    zip_code=result['location']['address']['postal_code'],
-                    address_two=result['location']['address']['unit'],
+                    address_one=address_one,
+                    city=result["location"]["address"]["city"],
+                    state=result["location"]["address"]["state_code"],
+                    zip_code=result["location"]["address"]["postal_code"],
+                    address_two=parse_address_two(result["location"]["address"]["unit"]),
                 ),
+                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,
-                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_square_foot=result['price_per_sqft'],
-                price=result['list_price'],
-                mls_id=result['property_id'],
+                property_url="https://www.realtor.com/realestateandhomes-detail/" + result["property_id"],
+                stories=result["description"]["stories"],
+                year_built=result["description"]["year_built"],
+                price_per_sqft=result["price_per_sqft"],
+                mls_id=result["property_id"],
                 listing_type=self.listing_type,
-                lot_size=result['description']['lot_sqft'],
+                lot_area_value=result["description"]["lot_sqft"],
+                beds_min=result["description"]["beds"],
+                beds_max=result["description"]["beds"],
+                baths_min=result["description"]["baths"],
+                baths_max=result["description"]["baths"],
+                sqft_min=result["description"]["sqft"],
+                sqft_max=result["description"]["sqft"],
+                price_min=result["list_price"],
+                price_max=result["list_price"],
             )
-
             properties.append(realty_property)
 
         return properties
@@ -239,17 +298,17 @@ class RealtorScraper(Scraper):
         location_info = self.handle_location()
         location_type = location_info["area_type"]
 
-        if location_type == 'address':
-            property_id = location_info['mpr_id']
+        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,
+            "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)
@@ -258,8 +317,11 @@ class RealtorScraper(Scraper):
         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)
+                    self.handle_area,
+                    variables=search_variables | {"offset": i},
+                    return_total=False,
+                )
+                for i in range(0, total, 200)
             ]
 
             for future in as_completed(futures):

homeharvest/core/scrapers/redfin/__init__.py

@@ -1,7 +1,15 @@
+"""
+homeharvest.redfin.__init__
+~~~~~~~~~~~~
+
+This module implements the scraper for redfin.com
+"""
 import json
-from ..models import Property, Address, PropertyType, Building
-from .. import Scraper
 from typing import Any
+from .. import Scraper
+from ....utils import parse_address_two, parse_address_one
+from ..models import Property, Address, PropertyType, ListingType, SiteName
+from ....exceptions import NoResultsFound
 
 
 class RedfinScraper(Scraper):
@@ -10,9 +18,7 @@ class RedfinScraper(Scraper):
         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(
-            self.location
-        )
+        url = "https://www.redfin.com/stingray/do/location-autocomplete?v=2&al=1&location={}".format(self.location)
 
         response = self.session.get(url)
         response_json = json.loads(response.text.replace("{}&&", ""))
@@ -25,6 +31,9 @@ class RedfinScraper(Scraper):
             elif match_type == "1":
                 return "address"  #: address, needs to be handled differently
 
+        if "exactMatch" not in response_json["payload"]:
+            raise NoResultsFound("No results found for location: {}".format(self.location))
+
         if response_json["payload"]["exactMatch"] is not None:
             target = response_json["payload"]["exactMatch"]
         else:
@@ -39,29 +48,29 @@ class RedfinScraper(Scraper):
 
         if not single_search:
             address = Address(
-                address_one=get_value("streetLine"),
-                city=home["city"],
-                state=home["state"],
-                zip_code=home["zip"],
+                address_one=parse_address_one(get_value("streetLine"))[0],
+                address_two=parse_address_one(get_value("streetLine"))[1],
+                city=home.get("city"),
+                state=home.get("state"),
+                zip_code=home.get("zip"),
             )
         else:
-            address_info = home["streetAddress"]
+            address_info = home.get("streetAddress")
+            address_one, address_two = parse_address_one(address_info.get("assembledAddress"))
 
             address = Address(
-                address_one=address_info["assembledAddress"],
-                city=home["city"],
-                state=home["state"],
-                zip_code=home["zip"],
+                address_one=address_one,
+                address_two=address_two,
+                city=home.get("city"),
+                state=home.get("state"),
+                zip_code=home.get("zip"),
             )
+
         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
-            )
+            lot_size = lot_size_data.get("value", None) if isinstance(lot_size_data, dict) else None
         else:
             lot_size = lot_size_data
 
@@ -69,51 +78,114 @@ class RedfinScraper(Scraper):
             site_name=self.site_name,
             listing_type=self.listing_type,
             address=address,
-            url=url,
-            beds=home["beds"] if "beds" in home else None,
-            baths=home["baths"] if "baths" in home else None,
+            property_url=url,
+            beds_min=home["beds"] if "beds" in home else None,
+            beds_max=home["beds"] if "beds" in home else None,
+            baths_min=home["baths"] if "baths" in home else None,
+            baths_max=home["baths"] if "baths" in home else None,
+            price_min=get_value("price"),
+            price_max=get_value("price"),
+            sqft_min=get_value("sqFt"),
+            sqft_max=get_value("sqFt"),
             stories=home["stories"] if "stories" in home else None,
             agent_name=get_value("listingAgent"),
             description=home["listingRemarks"] if "listingRemarks" in home else None,
-            year_built=get_value("yearBuilt")
-            if not single_search
-            else home["yearBuilt"],
-            square_feet=get_value("sqFt"),
-            lot_size=lot_size,
+            year_built=get_value("yearBuilt") if not single_search else home["yearBuilt"],
+            lot_area_value=lot_size,
             property_type=PropertyType.from_int_code(home.get("propertyType")),
-            price_per_square_foot=get_value("pricePerSqFt"),
-            price=get_value("price"),
+            price_per_sqft=get_value("pricePerSqFt"),
             mls_id=get_value("mlsId"),
+            latitude=home["latLong"]["latitude"] if "latLong" in home and "latitude" in home["latLong"] else None,
+            longitude=home["latLong"]["longitude"] if "latLong" in home and "longitude" in home["latLong"] else None,
         )
 
-    def _parse_building(self, building: dict) -> Building:
-        return Building(
-            address=Address(
-                address_one=" ".join(
-                    [
-                        building['address']['streetNumber'],
-                        building['address']['directionalPrefix'],
-                        building['address']['streetName'],
-                        building['address']['streetType'],
-                    ]
-                ),
-                city=building['address']['city'],
-                state=building['address']['stateOrProvinceCode'],
-                zip_code=building['address']['postalCode'],
-                address_two=" ".join(
-                    [
-                        building['address']['unitType'],
-                        building['address']['unitValue'],
-                    ]
-                )
-            ),
+    def _handle_rentals(self, region_id, region_type):
+        url = f"https://www.redfin.com/stingray/api/v1/search/rentals?al=1&isRentals=true&region_id={region_id}&region_type={region_type}&num_homes=100000"
+
+        response = self.session.get(url)
+        response.raise_for_status()
+        homes = response.json()
+
+        properties_list = []
+
+        for home in homes["homes"]:
+            home_data = home["homeData"]
+            rental_data = home["rentalExtension"]
+
+            property_url = f"https://www.redfin.com{home_data.get('url', '')}"
+            address_info = home_data.get("addressInfo", {})
+            centroid = address_info.get("centroid", {}).get("centroid", {})
+            address = Address(
+                address_one=parse_address_one(address_info.get("formattedStreetLine"))[0],
+                city=address_info.get("city"),
+                state=address_info.get("state"),
+                zip_code=address_info.get("zip"),
+            )
+
+            price_range = rental_data.get("rentPriceRange", {"min": None, "max": None})
+            bed_range = rental_data.get("bedRange", {"min": None, "max": None})
+            bath_range = rental_data.get("bathRange", {"min": None, "max": None})
+            sqft_range = rental_data.get("sqftRange", {"min": None, "max": None})
+
+            property_ = Property(
+                property_url=property_url,
+                site_name=SiteName.REDFIN,
+                listing_type=ListingType.FOR_RENT,
+                address=address,
+                description=rental_data.get("description"),
+                latitude=centroid.get("latitude"),
+                longitude=centroid.get("longitude"),
+                baths_min=bath_range.get("min"),
+                baths_max=bath_range.get("max"),
+                beds_min=bed_range.get("min"),
+                beds_max=bed_range.get("max"),
+                price_min=price_range.get("min"),
+                price_max=price_range.get("max"),
+                sqft_min=sqft_range.get("min"),
+                sqft_max=sqft_range.get("max"),
+                img_src=home_data.get("staticMapUrl"),
+                posted_time=rental_data.get("lastUpdated"),
+                bldg_name=rental_data.get("propertyName"),
+            )
+
+            properties_list.append(property_)
+
+        if not properties_list:
+            raise NoResultsFound("No rentals found for the given location.")
+
+        return properties_list
+
+    def _parse_building(self, building: dict) -> Property:
+        street_address = " ".join(
+            [
+                building["address"]["streetNumber"],
+                building["address"]["directionalPrefix"],
+                building["address"]["streetName"],
+                building["address"]["streetType"],
+            ]
+        )
+        return Property(
             site_name=self.site_name,
-            url="https://www.redfin.com{}".format(building["url"]),
+            property_type=PropertyType("BUILDING"),
+            address=Address(
+                address_one=parse_address_one(street_address)[0],
+                city=building["address"]["city"],
+                state=building["address"]["stateOrProvinceCode"],
+                zip_code=building["address"]["postalCode"],
+                address_two=parse_address_two(
+                    " ".join(
+                        [
+                            building["address"]["unitType"],
+                            building["address"]["unitValue"],
+                        ]
+                    )
+                ),
+            ),
+            property_url="https://www.redfin.com{}".format(building["url"]),
             listing_type=self.listing_type,
-            num_units=building["numUnitsForSale"],
+            unit_count=building["numUnitsForSale"],
         )
 
-
     def handle_address(self, home_id: str):
         """
         EPs:
@@ -122,7 +194,6 @@ class RedfinScraper(Scraper):
         https://www.redfin.com/stingray/api/home/details/aboveTheFold?propertyId=147337694&accessLevel=3
         https://www.redfin.com/stingray/api/home/details/belowTheFold?propertyId=147337694&accessLevel=3
         """
-
         url = "https://www.redfin.com/stingray/api/home/details/aboveTheFold?propertyId={}&accessLevel=3".format(
             home_id
         )
@@ -130,9 +201,7 @@ class RedfinScraper(Scraper):
         response = self.session.get(url)
         response_json = json.loads(response.text.replace("{}&&", ""))
 
-        parsed_home = self._parse_home(
-            response_json["payload"]["addressSectionInfo"], single_search=True
-        )
+        parsed_home = self._parse_home(response_json["payload"]["addressSectionInfo"], single_search=True)
         return [parsed_home]
 
     def search(self):
@@ -142,17 +211,16 @@ class RedfinScraper(Scraper):
             home_id = region_id
             return self.handle_address(home_id)
 
-        url = "https://www.redfin.com/stingray/api/gis?al=1&region_id={}&region_type={}".format(
-            region_id, region_type
-        )
-
-        response = self.session.get(url)
-        response_json = json.loads(response.text.replace("{}&&", ""))
-
-        homes = [
-            self._parse_home(home) for home in response_json["payload"]["homes"]
-        ] + [
-            self._parse_building(building) for building in response_json["payload"]["buildings"].values()
-        ]
-
-        return homes
+        if self.listing_type == ListingType.FOR_RENT:
+            return self._handle_rentals(region_id, region_type)
+        else:
+            if self.listing_type == ListingType.FOR_SALE:
+                url = f"https://www.redfin.com/stingray/api/gis?al=1&region_id={region_id}&region_type={region_type}&num_homes=100000"
+            else:
+                url = f"https://www.redfin.com/stingray/api/gis?al=1&region_id={region_id}&region_type={region_type}&sold_within_days=30&num_homes=100000"
+            response = self.session.get(url)
+            response_json = json.loads(response.text.replace("{}&&", ""))
+            homes = [self._parse_home(home) for home in response_json["payload"]["homes"]] + [
+                self._parse_building(building) for building in response_json["payload"]["buildings"].values()
+            ]
+            return homes

homeharvest/core/scrapers/zillow/__init__.py

@@ -1,18 +1,41 @@
+"""
+homeharvest.zillow.__init__
+~~~~~~~~~~~~
+
+This module implements the scraper for zillow.com
+"""
 import re
 import json
-from ..models import Property, Address, Building, ListingType, PropertyType
-from ....exceptions import NoResultsFound, PropertyNotFound
 from .. import Scraper
+from ....utils import parse_address_one, parse_address_two
+from ....exceptions import GeoCoordsNotFound, NoResultsFound
+from ..models import Property, Address, ListingType, PropertyType
 
 
 class ZillowScraper(Scraper):
     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/"
+
+        if not self.is_plausible_location(self.location):
+            raise NoResultsFound("Invalid location input: {}".format(self.location))
+
+        listing_type_to_url_path = {
+            ListingType.FOR_SALE: "for_sale",
+            ListingType.FOR_RENT: "for_rent",
+            ListingType.SOLD: "recently_sold",
+        }
+
+        self.url = f"https://www.zillow.com/homes/{listing_type_to_url_path[self.listing_type]}/{self.location}_rb/"
+
+    def is_plausible_location(self, location: str) -> bool:
+        url = (
+            "https://www.zillowstatic.com/autocomplete/v3/suggestions?q={"
+            "}&abKey=6666272a-4b99-474c-b857-110ec438732b&clientId=homepage-render"
+        ).format(location)
+
+        response = self.session.get(url)
+
+        return response.json()["results"] != []
 
     def search(self):
         resp = self.session.get(self.url, headers=self._get_headers())
@@ -25,18 +48,23 @@ class ZillowScraper(Scraper):
             re.DOTALL,
         )
         if not match:
-            raise NoResultsFound(
-                "No results were found for Zillow with the given Location."
-            )
+            raise NoResultsFound("No results were found for Zillow with the given Location.")
 
         json_str = match.group(1)
         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]
@@ -45,47 +73,148 @@ 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.")
 
-    def _parse_home(self, 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 = self._extract_price(home)
-            address = self._extract_address(home)
-            agent_name = self._extract_agent_name(home)
-            beds = home["hdpData"]["homeInfo"]["bedrooms"]
-            baths = home["hdpData"]["homeInfo"]["bathrooms"]
-            property_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(
-                site_name=self.site_name,
-                address=address,
-                agent_name=agent_name,
-                url=url,
-                beds=beds,
-                baths=baths,
-                listing_type=self.listing_type,
-                property_type=PropertyType(property_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 = self._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 = self._extract_building_info(home)
-            return Building(
-                site_name=self.site_name, address=address, url=url, **building_info
-            )
+        properties_list = []
+
+        for result in mapresults:
+            if "hdpData" in result:
+                home_info = result["hdpData"]["homeInfo"]
+                address_data = {
+                    "address_one": parse_address_one(home_info["streetAddress"])[0],
+                    "address_two": parse_address_two(home_info["unit"]) if "unit" in home_info else "#",
+                    "city": home_info["city"],
+                    "state": home_info["state"],
+                    "zip_code": home_info["zipcode"],
+                }
+                property_obj = Property(
+                    site_name=self.site_name,
+                    address=Address(**address_data),
+                    property_url=f"https://www.zillow.com{result['detailUrl']}",
+                    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
+                    ),
+                    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,
+                    price_min=home_info.get("price"),
+                    price_max=home_info.get("price"),
+                    beds_min=int(home_info["bedrooms"]) if "bedrooms" in home_info else None,
+                    beds_max=int(home_info["bedrooms"]) if "bedrooms" in home_info else None,
+                    baths_min=home_info.get("bathrooms"),
+                    baths_max=home_info.get("bathrooms"),
+                    sqft_min=int(home_info["livingArea"]) if "livingArea" in home_info else None,
+                    sqft_max=int(home_info["livingArea"]) if "livingArea" in home_info else None,
+                    price_per_sqft=int(home_info["price"] // home_info["livingArea"])
+                    if "livingArea" in home_info and home_info["livingArea"] != 0 and "price" in home_info
+                    else None,
+                    latitude=result["latLong"]["latitude"],
+                    longitude=result["latLong"]["longitude"],
+                    lot_area_value=round(home_info["lotAreaValue"], 2) if "lotAreaValue" in home_info else None,
+                    lot_area_unit=home_info.get("lotAreaUnit"),
+                    img_src=result.get("imgSrc"),
+                )
+
+                properties_list.append(property_obj)
+
+            elif "isBuilding" in result:
+                price_string = result["price"].replace("$", "").replace(",", "").replace("+/mo", "")
+
+                match = re.search(r"(\d+)", price_string)
+                price_value = int(match.group(1)) if match else None
+                building_obj = Property(
+                    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"],
+                    address=self._extract_address(result["address"]),
+                    baths_min=result["minBaths"],
+                    area_min=result.get("minArea"),
+                    bldg_name=result.get("communityName"),
+                    status_text=result["statusText"],
+                    beds_min=result["minBeds"],
+                    price_min=price_value if "+/mo" in result["price"] else None,
+                    price_max=price_value if "+/mo" in result["price"] else None,
+                    latitude=result["latLong"]["latitude"],
+                    longitude=result["latLong"]["longitude"],
+                    unit_count=result["unitCount"],
+                )
+
+                properties_list.append(building_obj)
+
+        return properties_list
 
     def _get_single_property_page(self, property_data: dict):
         """
@@ -97,114 +226,90 @@ class ZillowScraper(Scraper):
             else property_data["hdpUrl"]
         )
         address_data = property_data["address"]
-        address_one, address_two = self._parse_address_two(
-            address_data["streetAddress"]
-        )
+        address_one, address_two = parse_address_one(address_data["streetAddress"])
         address = Address(
             address_one=address_one,
-            address_two=address_two,
+            address_two=address_two if address_two else "#",
             city=address_data["city"],
             state=address_data["state"],
             zip_code=address_data["zipcode"],
         )
         property_type = property_data.get("homeType", None)
-
         return Property(
             site_name=self.site_name,
-            address=address,
-            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),
-            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(
-                "pricePerSquareFoot", None
-            ),
-            square_feet=property_data.get("livingArea", None),
+            property_url=url,
             property_type=PropertyType(property_type),
             listing_type=self.listing_type,
+            address=address,
+            year_built=property_data.get("yearBuilt"),
+            tax_assessed_value=property_data.get("taxAssessedValue"),
+            lot_area_value=property_data.get("lotAreaValue"),
+            lot_area_unit=property_data["lotAreaUnits"].lower() if "lotAreaUnits" in property_data else None,
+            agent_name=property_data.get("attributionInfo", {}).get("agentName"),
+            stories=property_data.get("resoFacts", {}).get("stories"),
+            mls_id=property_data.get("attributionInfo", {}).get("mlsId"),
+            beds_min=property_data.get("bedrooms"),
+            beds_max=property_data.get("bedrooms"),
+            baths_min=property_data.get("bathrooms"),
+            baths_max=property_data.get("bathrooms"),
+            price_min=property_data.get("price"),
+            price_max=property_data.get("price"),
+            sqft_min=property_data.get("livingArea"),
+            sqft_max=property_data.get("livingArea"),
+            price_per_sqft=property_data.get("resoFacts", {}).get("pricePerSquareFoot"),
+            latitude=property_data.get("latitude"),
+            longitude=property_data.get("longitude"),
+            img_src=property_data.get("streetViewTileImageUrlMediumAddress"),
+            description=property_data.get("description"),
         )
 
-    def _extract_building_info(self, home: dict) -> dict:
-        num_units = len(home["units"])
-        prices = [
-            int(unit["price"].replace("$", "").replace(",", "").split("+")[0])
-            for unit in home["units"]
-        ]
-        return {
-            "listing_type": self.listing_type,
-            "num_units": len(home["units"]),
-            "min_unit_price": min(
-                (
-                    int(unit["price"].replace("$", "").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
+        address_one = 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
+        address_one, address_two = parse_address_one(address_one)
+        return Address(
+            address_one=address_one,
+            address_two=address_two if address_two else "#",
+            city=city,
+            state=state,
+            zip_code=zip_code,
         )
-        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 +1,38 @@
+import re
+
+
+def parse_address_one(street_address: str) -> tuple:
+    if not street_address:
+        return street_address, "#"
+
+    apt_match = re.search(
+        r"(APT\s*[\dA-Z]+|#[\dA-Z]+|UNIT\s*[\dA-Z]+|LOT\s*[\dA-Z]+|SUITE\s*[\dA-Z]+)$",
+        street_address,
+        re.I,
+    )
+
+    if apt_match:
+        apt_str = apt_match.group().strip()
+        cleaned_apt_str = re.sub(r"(APT\s*|UNIT\s*|LOT\s*|SUITE\s*)", "#", apt_str, flags=re.I)
+
+        main_address = street_address.replace(apt_str, "").strip()
+        return main_address, cleaned_apt_str
+    else:
+        return street_address, "#"
+
+
+def parse_address_two(street_address: str):
+    if not street_address:
+        return "#"
+    apt_match = re.search(
+        r"(APT\s*[\dA-Z]+|#[\dA-Z]+|UNIT\s*[\dA-Z]+|LOT\s*[\dA-Z]+|SUITE\s*[\dA-Z]+)$",
+        street_address,
+        re.I,
+    )
+
+    if apt_match:
+        apt_str = apt_match.group().strip()
+        apt_str = re.sub(r"(APT\s*|UNIT\s*|LOT\s*|SUITE\s*)", "#", apt_str, flags=re.I)
+        return apt_str
+    else:
+        return "#"

poetry.lock

@@ -106,6 +106,17 @@ files = [
     {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
 ]
 
+[[package]]
+name = "et-xmlfile"
+version = "1.1.0"
+description = "An implementation of lxml.xmlfile for the standard library"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "et_xmlfile-1.1.0-py3-none-any.whl", hash = "sha256:a2ba85d1d6a74ef63837eed693bcb89c3f752169b0e3e7ae5b16ca5e1b3deada"},
+    {file = "et_xmlfile-1.1.0.tar.gz", hash = "sha256:8eb9e2bc2f8c97e37a2dc85a09ecdcdec9d8a396530a6d5a33b30b9a92da0c5c"},
+]
+
 [[package]]
 name = "exceptiongroup"
 version = "1.1.3"
@@ -217,6 +228,20 @@ files = [
     {file = "numpy-1.26.0.tar.gz", hash = "sha256:f93fc78fe8bf15afe2b8d6b6499f1c73953169fad1e9a8dd086cdff3190e7fdf"},
 ]
 
+[[package]]
+name = "openpyxl"
+version = "3.1.2"
+description = "A Python library to read/write Excel 2010 xlsx/xlsm files"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "openpyxl-3.1.2-py2.py3-none-any.whl", hash = "sha256:f91456ead12ab3c6c2e9491cf33ba6d08357d802192379bb482f1033ade496f5"},
+    {file = "openpyxl-3.1.2.tar.gz", hash = "sha256:a6f5977418eff3b2d5500d54d9db50c8277a368436f4e4f8ddb1be3422870184"},
+]
+
+[package.dependencies]
+et-xmlfile = "*"
+
 [[package]]
 name = "packaging"
 version = "23.1"
@@ -425,4 +450,4 @@ zstd = ["zstandard (>=0.18.0)"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "eede625d6d45085e143b0af246cb2ce00cff8579c667be3b63387c8594a5570d"
+content-hash = "3647d568f5623dd762f19029230626a62e68309fa2ef8be49a36382c19264a5f"

pyproject.toml

@@ -1,15 +1,19 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.1.3"
-description = "Real estate scraping library"
+version = "0.2.9"
+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"
 
+[tool.poetry.scripts]
+homeharvest = "homeharvest.cli:main"
+
 [tool.poetry.dependencies]
 python = "^3.10"
 requests = "^2.31.0"
 pandas = "^2.1.0"
+openpyxl = "^3.1.2"
 
 
 [tool.poetry.group.dev.dependencies]

tests/test_realtor.py

@@ -1,12 +1,40 @@
 from homeharvest import scrape_property
+from homeharvest.exceptions import (
+    InvalidSite,
+    InvalidListingType,
+    NoResultsFound,
+    GeoCoordsNotFound,
+)
 
 
 def test_realtor():
     results = [
-        scrape_property(location="2530 Al Lipscomb Way", site_name="realtor.com"),
-        scrape_property(location="Phoenix, AZ", site_name="realtor.com"),  #: does not support "city, state, USA" format
-        scrape_property(location="Dallas, TX", site_name="realtor.com"),  #: does not support "city, state, USA" format
+        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"),
     ]
 
     assert all([result is not None for result in results])
+
+    bad_results = []
+    try:
+        bad_results += [
+            scrape_property(
+                location="abceefg ju098ot498hh9",
+                site_name="realtor.com",
+                listing_type="for_sale",
+            )
+        ]
+    except (InvalidSite, InvalidListingType, NoResultsFound, GeoCoordsNotFound):
+        assert True
+
+    assert all([result is None for result in bad_results])

tests/test_redfin.py

@@ -1,12 +1,32 @@
 from homeharvest import scrape_property
+from homeharvest.exceptions import (
+    InvalidSite,
+    InvalidListingType,
+    NoResultsFound,
+    GeoCoordsNotFound,
+)
 
 
 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"),
     ]
 
     assert all([result is not None for result in results])
+
+    bad_results = []
+    try:
+        bad_results += [
+            scrape_property(
+                location="abceefg ju098ot498hh9",
+                site_name="redfin",
+                listing_type="for_sale",
+            )
+        ]
+    except (InvalidSite, InvalidListingType, NoResultsFound, GeoCoordsNotFound):
+        assert True
+
+    assert all([result is None for result in bad_results])

tests/test_utils.py

@@ -0,0 +1,24 @@
+from homeharvest.utils import parse_address_one, parse_address_two
+
+
+def test_parse_address_one():
+    test_data = [
+        ("4303 E Cactus Rd Apt 126", ("4303 E Cactus Rd", "#126")),
+        ("1234 Elm Street apt 2B", ("1234 Elm Street", "#2B")),
+        ("1234 Elm Street UNIT 3A", ("1234 Elm Street", "#3A")),
+        ("1234 Elm Street unit 3A", ("1234 Elm Street", "#3A")),
+        ("1234 Elm Street SuIte 3A", ("1234 Elm Street", "#3A")),
+    ]
+
+    for input_data, (exp_addr_one, exp_addr_two) in test_data:
+        address_one, address_two = parse_address_one(input_data)
+        assert address_one == exp_addr_one
+        assert address_two == exp_addr_two
+
+
+def test_parse_address_two():
+    test_data = [("Apt 126", "#126"), ("apt 2B", "#2B"), ("UNIT 3A", "#3A"), ("unit 3A", "#3A"), ("SuIte 3A", "#3A")]
+
+    for input_data, expected in test_data:
+        output = parse_address_two(input_data)
+        assert output == expected

tests/test_zillow.py

@@ -1,12 +1,32 @@
 from homeharvest import scrape_property
+from homeharvest.exceptions import (
+    InvalidSite,
+    InvalidListingType,
+    NoResultsFound,
+    GeoCoordsNotFound,
+)
 
 
 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"),
     ]
 
     assert all([result is not None for result in results])
+
+    bad_results = []
+    try:
+        bad_results += [
+            scrape_property(
+                location="abceefg ju098ot498hh9",
+                site_name="zillow",
+                listing_type="for_sale",
+            )
+        ]
+    except (InvalidSite, InvalidListingType, NoResultsFound, GeoCoordsNotFound):
+        assert True
+
+    assert all([result is None for result in bad_results])