Merge pull request #8 from ZacharyHampton/fix/zillow-location-validation

- zillow location validation

homeharvest/core/scrapers/zillow/__init__.py

@@ -10,9 +10,10 @@ 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:
@@ -20,17 +21,15 @@ 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 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())

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 = "0.2.1"
+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]