- redfin limiting bug fix

feat(redfin): rental support

.gitignore

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

HomeHarvest_Demo.ipynb

@@ -55,7 +55,7 @@
     "    location=\"2530 Al Lipscomb Way\",\n",
     "    site_name=\"zillow\",\n",
     "    listing_type=\"for_sale\"\n",
-    "),"
+    ")"
    ]
   },
   {
@@ -67,8 +67,8 @@
    "source": [
     "# check rentals\n",
     "scrape_property(\n",
-    "    location=\"chicago\",\n",
-    "    site_name=[\"redfin\", \"realtor.com\"],\n",
+    "    location=\"chicago, illinois\",\n",
+    "    site_name=[\"redfin\", \"zillow\"],\n",
     "    listing_type=\"for_rent\"\n",
     ")"
    ]
@@ -87,7 +87,7 @@
    "source": [
     "# check sold properties\n",
     "scrape_property(\n",
-    "    location=\"chicago, illinois\",\n",
+    "    location=\"90210\",\n",
     "    site_name=[\"redfin\"],\n",
     "    listing_type=\"sold\"\n",
     ")"

README.md

@@ -9,13 +9,15 @@
 
 - Scrapes properties from **Zillow**, **Realtor.com** & **Redfin** simultaneously
 - Aggregates the properties in a Pandas DataFrame
-  
+
+[Video Guide for HomeHarvest](https://www.youtube.com/watch?v=HCoHoiJdWQY)
+
 ![homeharvest](https://github.com/ZacharyHampton/HomeHarvest/assets/78247585/b3d5d727-e67b-4a9f-85d8-1e65fd18620a)
 
 ## Installation
 
 ```bash
-pip install --upgrade homeharvest
+pip install --force-reinstall homeharvest
 ```
   _Python version >= [3.10](https://www.python.org/downloads/release/python-3100/) required_ 
   

homeharvest/__init__.py

@@ -17,6 +17,7 @@ _scrapers = {
     "zillow": ZillowScraper,
 }
 
+
 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.")
@@ -26,6 +27,7 @@ def validate_input(site_name: str, listing_type: str) -> None:
             f"Provided listing type, '{listing_type}', does not exist."
         )
 
+
 def get_ordered_properties(result: Property) -> list[str]:
     return [
         "property_url",
@@ -36,6 +38,13 @@ def get_ordered_properties(result: Property) -> list[str]:
         "currency",
         "price",
         "apt_min_price",
+        "apt_max_price",
+        "apt_min_sqft",
+        "apt_max_sqft",
+        "apt_min_beds",
+        "apt_max_beds",
+        "apt_min_baths",
+        "apt_max_baths",
         "tax_assessed_value",
         "square_feet",
         "price_per_sqft",
@@ -65,6 +74,7 @@ def get_ordered_properties(result: Property) -> list[str]:
         "longitude",
     ]
 
+
 def process_result(result: Property) -> pd.DataFrame:
     prop_data = result.__dict__
 
@@ -90,6 +100,7 @@ def process_result(result: Property) -> pd.DataFrame:
 
     return properties_df
 
+
 def _scrape_single_site(
     location: str, site_name: str, listing_type: str
 ) -> pd.DataFrame:
@@ -108,7 +119,9 @@ def _scrape_single_site(
     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]
+    properties_dfs = [
+        df.dropna(axis=1, how="all") for df in properties_dfs if not df.empty
+    ]
     if not properties_dfs:
         return pd.DataFrame()
 
@@ -143,7 +156,9 @@ def scrape_property(
     else:
         with ThreadPoolExecutor() as executor:
             futures = {
-                executor.submit(_scrape_single_site, location, s_name, listing_type): s_name
+                executor.submit(
+                    _scrape_single_site, location, s_name, listing_type
+                ): s_name
                 for s_name in site_name
             }
 
@@ -157,5 +172,15 @@ def scrape_property(
         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
+
+    columns_to_track = ["street_address", "city", "unit"]
+
+    #: validate they exist, otherwise create them
+    for col in columns_to_track:
+        if col not in final_df.columns:
+            final_df[col] = None
+
+    final_df = final_df.drop_duplicates(
+        subset=["street_address", "city", "unit"], keep="first"
+    )
+    return final_df

homeharvest/core/scrapers/models.py

@@ -102,4 +102,11 @@ class Property:
     bldg_min_area: int | None = None
 
     # apt
+    apt_min_beds: int | None = None
+    apt_max_beds: int | None = None
+    apt_min_baths: float | None = None
+    apt_max_baths: float | None = None
     apt_min_price: int | None = None
+    apt_max_price: int | None = None
+    apt_min_sqft: int | None = None
+    apt_max_sqft: int | None = None

homeharvest/core/scrapers/realtor/__init__.py

@@ -44,7 +44,7 @@ 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]
@@ -249,8 +249,20 @@ class RealtorScraper(Scraper):
                     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,
+                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"],

homeharvest/core/scrapers/redfin/__init__.py

@@ -2,7 +2,8 @@ import json
 from typing import Any
 from .. import Scraper
 from ....utils import parse_address_two, parse_unit
-from ..models import Property, Address, PropertyType
+from ..models import Property, Address, PropertyType, ListingType, SiteName
+from ....exceptions import NoResultsFound
 
 
 class RedfinScraper(Scraper):
@@ -26,6 +27,11 @@ 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:
@@ -94,10 +100,72 @@ class RedfinScraper(Scraper):
             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
+            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 _handle_rentals(self, region_id, region_type):
+        url = f"https://www.redfin.com/stingray/api/v1/search/rentals?al=1&isRentals=true&region_id={region_id}&region_type={region_type}&num_homes=100000"
+
+        response = self.session.get(url)
+        response.raise_for_status()
+        homes = response.json()
+
+        properties_list = []
+
+        for home in homes["homes"]:
+            home_data = home["homeData"]
+            rental_data = home["rentalExtension"]
+
+            property_url = f"https://www.redfin.com{home_data.get('url', '')}"
+            address_info = home_data.get("addressInfo", {})
+            centroid = address_info.get("centroid", {}).get("centroid", {})
+            address = Address(
+                street_address=address_info.get("formattedStreetLine", None),
+                city=address_info.get("city", None),
+                state=address_info.get("state", None),
+                zip_code=address_info.get("zip", None),
+                unit=None,
+                country="US" if address_info.get("countryCode", None) == 1 else None,
+            )
+
+            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,
+                apt_min_beds=bed_range.get("min", None),
+                apt_min_baths=bath_range.get("min", None),
+                apt_max_beds=bed_range.get("max", None),
+                apt_max_baths=bath_range.get("max", None),
+                description=rental_data.get("description", None),
+                latitude=centroid.get("latitude", None),
+                longitude=centroid.get("longitude", None),
+                apt_min_price=price_range.get("min", None),
+                apt_max_price=price_range.get("max", None),
+                apt_min_sqft=sqft_range.get("min", None),
+                apt_max_sqft=sqft_range.get("max", None),
+                img_src=home_data.get("staticMapUrl", None),
+                posted_time=rental_data.get("lastUpdated", None),
+                bldg_name=rental_data.get("propertyName", None),
+            )
+
+            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(
             [
@@ -158,18 +226,19 @@ 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

@@ -1,15 +1,19 @@
 import re
 import json
+import string
 from .. import Scraper
 from ....utils import parse_address_two, parse_unit
-from ....exceptions import GeoCoordsNotFound
-from ..models import Property, Address, ListingType, PropertyType, SiteName
+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 not self.is_plausible_location(self.location):
+            raise NoResultsFound("Invalid location input: {}".format(self.location))
+
         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:
@@ -17,6 +21,16 @@ class ZillowScraper(Scraper):
         else:
             self.url = f"https://www.zillow.com/homes/recently_sold/{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())
         resp.raise_for_status()
@@ -151,9 +165,6 @@ class ZillowScraper(Scraper):
                     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,

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

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.2.0"
+version = "0.2.2"
 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"
@@ -10,6 +10,7 @@ readme = "README.md"
 python = "^3.10"
 requests = "^2.31.0"
 pandas = "^2.1.0"
+openpyxl = "^3.1.2"
 
 
 [tool.poetry.group.dev.dependencies]

tests/test_realtor.py

@@ -1,4 +1,10 @@
 from homeharvest import scrape_property
+from homeharvest.exceptions import (
+    InvalidSite,
+    InvalidListingType,
+    NoResultsFound,
+    GeoCoordsNotFound,
+)
 
 
 def test_realtor():
@@ -18,3 +24,17 @@ def test_realtor():
     ]
 
     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

@@ -1,4 +1,10 @@
 from homeharvest import scrape_property
+from homeharvest.exceptions import (
+    InvalidSite,
+    InvalidListingType,
+    NoResultsFound,
+    GeoCoordsNotFound,
+)
 
 
 def test_redfin():
@@ -16,3 +22,17 @@ def test_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_zillow.py

@@ -1,4 +1,10 @@
 from homeharvest import scrape_property
+from homeharvest.exceptions import (
+    InvalidSite,
+    InvalidListingType,
+    NoResultsFound,
+    GeoCoordsNotFound,
+)
 
 
 def test_zillow():
@@ -16,3 +22,17 @@ def test_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])