fix(zillow): test case

homeharvest/core/scrapers/realtor/__init__.py

@@ -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

@@ -27,8 +27,10 @@ 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 "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"]
@@ -98,8 +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, NoResultsFound
-from ..models import Property, Address, ListingType, PropertyType, SiteName
+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()