fix(zillow): test case

# Conflicts:
#	homeharvest/__init__.py

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",
@@ -65,6 +67,7 @@ def get_ordered_properties(result: Property) -> list[str]:
         "longitude",
     ]
 
+
 def process_result(result: Property) -> pd.DataFrame:
     prop_data = result.__dict__
 
@@ -90,6 +93,7 @@ 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 +112,9 @@ 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 +149,9 @@ 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 +165,15 @@ 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/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

@@ -3,6 +3,7 @@ from typing import Any
 from .. import Scraper
 from ....utils import parse_address_two, parse_unit
 from ..models import Property, Address, PropertyType
+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:
@@ -94,8 +100,12 @@ 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 _parse_building(self, building: dict) -> Property:

homeharvest/core/scrapers/zillow/__init__.py

@@ -1,15 +1,18 @@
 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 +20,18 @@ class ZillowScraper(Scraper):
         else:
             self.url = f"https://www.zillow.com/homes/recently_sold/{self.location}_rb/"
 
+    @staticmethod
+    def is_plausible_location(location: str) -> bool:
+        blocks = location.split()
+        for block in blocks:
+            if (
+                any(char.isdigit() for char in block)
+                and any(char.isalpha() for char in block)
+                and len(block) > 6
+            ):
+                return False
+        return True
+
     def search(self):
         resp = self.session.get(self.url, headers=self._get_headers())
         resp.raise_for_status()
@@ -151,9 +166,6 @@ 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,

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])