Merge pull request #25 from ZacharyHampton/fix/recent-issues

Fix/recent issues

README.md

@@ -4,7 +4,13 @@
 
 [![Try with Replit](https://replit.com/badge?caption=Try%20with%20Replit)](https://replit.com/@ZacharyHampton/HomeHarvestDemo)
 
+\
+**Not technical?** Try out the web scraping tool on our site at [tryhomeharvest.com](https://tryhomeharvest.com).
+
 *Looking to build a data-focused software product?* **[Book a call](https://calendly.com/zachary-products/15min)** *to work with us.*
+
+Check out another project we wrote: ***[JobSpy](https://github.com/cullenwatson/JobSpy)** – a Python package for job scraping*
+
 ## Features
 
 - Scrapes properties from **Zillow**, **Realtor.com** & **Redfin** simultaneously

homeharvest/__init__.py

@@ -57,6 +57,10 @@ def _get_ordered_properties(result: Property) -> list[str]:
         "stories",
         "year_built",
         "agent_name",
+        "agent_phone",
+        "agent_email",
+        "days_on_market",
+        "sold_date",
         "mls_id",
         "img_src",
         "latitude",
@@ -84,6 +88,18 @@ def _process_result(result: Property) -> pd.DataFrame:
 
         del prop_data["address"]
 
+    if "agent" in prop_data and prop_data["agent"] is not None:
+        agent_data = prop_data["agent"]
+        prop_data["agent_name"] = agent_data.name
+        prop_data["agent_phone"] = agent_data.phone
+        prop_data["agent_email"] = agent_data.email
+
+        del prop_data["agent"]
+    else:
+        prop_data["agent_name"] = None
+        prop_data["agent_phone"] = None
+        prop_data["agent_email"] = None
+
     properties_df = pd.DataFrame([prop_data])
     properties_df = properties_df[_get_ordered_properties(result)]
 

homeharvest/core/scrapers/models.py

@@ -1,6 +1,7 @@
 from dataclasses import dataclass
 from enum import Enum
 from typing import Tuple
+from datetime import datetime
 
 
 class SiteName(Enum):
@@ -64,6 +65,13 @@ class Address:
     zip_code: str | None = None
 
 
+@dataclass
+class Agent:
+    name: str
+    phone: str | None = None
+    email: str | None = None
+
+
 @dataclass
 class Property:
     property_url: str
@@ -81,11 +89,11 @@ class Property:
     price_per_sqft: int | None = None
     mls_id: str | None = None
 
-    agent_name: str | None = None
+    agent: Agent | None = None
     img_src: str | None = None
     description: str | None = None
     status_text: str | None = None
-    posted_time: str | None = None
+    posted_time: datetime | None = None
 
     # building for sale
     bldg_name: str | None = None
@@ -107,3 +115,6 @@ class Property:
 
     latitude: float | None = None
     longitude: float | None = None
+
+    sold_date: datetime | None = None
+    days_on_market: int | None = None

homeharvest/core/scrapers/redfin/__init__.py

@@ -8,8 +8,9 @@ import json
 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
+from ..models import Property, Address, PropertyType, ListingType, SiteName, Agent
+from ....exceptions import NoResultsFound, SearchTooBroad
+from datetime import datetime
 
 
 class RedfinScraper(Scraper):
@@ -30,6 +31,8 @@ class RedfinScraper(Scraper):
                 return "6"  #: city
             elif match_type == "1":
                 return "address"  #: address, needs to be handled differently
+            elif match_type == "11":
+                return "state"
 
         if "exactMatch" not in response_json["payload"]:
             raise NoResultsFound("No results found for location: {}".format(self.location))
@@ -74,6 +77,8 @@ class RedfinScraper(Scraper):
         else:
             lot_size = lot_size_data
 
+        lat_long = get_value("latLong")
+
         return Property(
             site_name=self.site_name,
             listing_type=self.listing_type,
@@ -88,15 +93,20 @@ class RedfinScraper(Scraper):
             sqft_min=get_value("sqFt"),
             sqft_max=get_value("sqFt"),
             stories=home["stories"] if "stories" in home else None,
-            agent_name=get_value("listingAgent"),
+            agent=Agent(  #: listingAgent, some have sellingAgent as well
+                name=home['listingAgent'].get('name') if 'listingAgent' in home else None,
+                phone=home['listingAgent'].get('phone') if 'listingAgent' in home else None,
+            ),
             description=home["listingRemarks"] if "listingRemarks" in home else None,
-            year_built=get_value("yearBuilt") if not single_search else home["yearBuilt"],
+            year_built=get_value("yearBuilt") if not single_search else home.get("yearBuilt"),
             lot_area_value=lot_size,
             property_type=PropertyType.from_int_code(home.get("propertyType")),
-            price_per_sqft=get_value("pricePerSqFt"),
+            price_per_sqft=get_value("pricePerSqFt") if type(home.get("pricePerSqFt")) != int else home.get("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,
+            latitude=lat_long.get('latitude') if lat_long else None,
+            longitude=lat_long.get('longitude') if lat_long else None,
+            sold_date=datetime.fromtimestamp(home['soldDate'] / 1000) if 'soldDate' in home else None,
+            days_on_market=get_value("dom")
         )
 
     def _handle_rentals(self, region_id, region_type):
@@ -183,7 +193,7 @@ class RedfinScraper(Scraper):
             ),
             property_url="https://www.redfin.com{}".format(building["url"]),
             listing_type=self.listing_type,
-            unit_count=building["numUnitsForSale"],
+            unit_count=building.get("numUnitsForSale"),
         )
 
     def handle_address(self, home_id: str):
@@ -207,6 +217,9 @@ class RedfinScraper(Scraper):
     def search(self):
         region_id, region_type = self._handle_location()
 
+        if region_type == "state":
+            raise SearchTooBroad("State searches are not supported, please use a more specific location.")
+
         if region_type == "address":
             home_id = region_id
             return self.handle_address(home_id)
@@ -220,7 +233,14 @@ class RedfinScraper(Scraper):
                 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
+
+            if "payload" in response_json:
+                homes_list = response_json["payload"].get("homes", [])
+                buildings_list = response_json["payload"].get("buildings", {}).values()
+
+                homes = [self._parse_home(home) for home in homes_list] + [
+                    self._parse_building(building) for building in buildings_list
+                ]
+                return homes
+            else:
+                return []

homeharvest/core/scrapers/zillow/__init__.py

@@ -6,15 +6,40 @@ This module implements the scraper for zillow.com
 """
 import re
 import json
+
+import tls_client
+
 from .. import Scraper
+from requests.exceptions import HTTPError
 from ....utils import parse_address_one, parse_address_two
 from ....exceptions import GeoCoordsNotFound, NoResultsFound
-from ..models import Property, Address, ListingType, PropertyType
+from ..models import Property, Address, ListingType, PropertyType, Agent
+import urllib.parse
+from datetime import datetime, timedelta
 
 
 class ZillowScraper(Scraper):
     def __init__(self, scraper_input):
         super().__init__(scraper_input)
+        self.session = tls_client.Session(
+            client_identifier="chrome112", random_tls_extension_order=True
+        )
+
+        self.session.headers.update({
+            'authority': 'www.zillow.com',
+            'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
+            'accept-language': 'en-US,en;q=0.9',
+            'cache-control': 'max-age=0',
+            'sec-ch-ua': '"Chromium";v="117", "Not)A;Brand";v="24", "Google Chrome";v="117"',
+            'sec-ch-ua-mobile': '?0',
+            'sec-ch-ua-platform': '"Windows"',
+            'sec-fetch-dest': 'document',
+            'sec-fetch-mode': 'navigate',
+            'sec-fetch-site': 'same-origin',
+            'sec-fetch-user': '?1',
+            'upgrade-insecure-requests': '1',
+            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36',
+        })
 
         if not self.is_plausible_location(self.location):
             raise NoResultsFound("Invalid location input: {}".format(self.location))
@@ -31,15 +56,18 @@ class ZillowScraper(Scraper):
         url = (
             "https://www.zillowstatic.com/autocomplete/v3/suggestions?q={"
             "}&abKey=6666272a-4b99-474c-b857-110ec438732b&clientId=homepage-render"
-        ).format(location)
+        ).format(urllib.parse.quote(location))
 
-        response = self.session.get(url)
+        resp = self.session.get(url)
 
-        return response.json()["results"] != []
+        return resp.json()["results"] != []
 
     def search(self):
-        resp = self.session.get(self.url, headers=self._get_headers())
-        resp.raise_for_status()
+        resp = self.session.get(self.url)
+        if resp.status_code != 200:
+            raise HTTPError(
+                f"bad response status code: {resp.status_code}"
+            )
         content = resp.text
 
         match = re.search(
@@ -133,11 +161,23 @@ class ZillowScraper(Scraper):
             "wants": {"cat1": ["mapResults"]},
             "isDebugRequest": False,
         }
-        resp = self.session.put(url, headers=self._get_headers(), json=payload)
-        resp.raise_for_status()
-        a = resp.json()
+        resp = self.session.put(url, json=payload)
+        if resp.status_code != 200:
+            raise HTTPError(
+                f"bad response status code: {resp.status_code}"
+            )
         return self._parse_properties(resp.json())
 
+    @staticmethod
+    def parse_posted_time(time: str) -> datetime:
+        int_time = int(time.split(" ")[0])
+
+        if "hour" in time:
+            return datetime.now() - timedelta(hours=int_time)
+
+        if "day" in time:
+            return datetime.now() - timedelta(days=int_time)
+
     def _parse_properties(self, property_data: dict):
         mapresults = property_data["cat1"]["searchResults"]["mapResults"]
 
@@ -147,26 +187,26 @@ class ZillowScraper(Scraper):
             if "hdpData" in result:
                 home_info = result["hdpData"]["homeInfo"]
                 address_data = {
-                    "address_one": parse_address_one(home_info["streetAddress"])[0],
+                    "address_one": parse_address_one(home_info.get("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"],
+                    "city": home_info.get("city"),
+                    "state": home_info.get("state"),
+                    "zip_code": home_info.get("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"]),
+                    property_type=PropertyType(home_info.get("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"]
+                    posted_time=self.parse_posted_time(result["variableData"]["text"])
                     if "variableData" in result
-                    and "text" in result["variableData"]
-                    and result["variableData"]["type"] == "TIME_ON_INFO"
+                       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"),
@@ -198,18 +238,17 @@ class ZillowScraper(Scraper):
                     site_name=self.site_name,
                     property_type=PropertyType("BUILDING"),
                     listing_type=ListingType(result["statusType"]),
-                    img_src=result["imgSrc"],
+                    img_src=result.get("imgSrc"),
                     address=self._extract_address(result["address"]),
-                    baths_min=result["minBaths"],
+                    baths_min=result.get("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"],
+                    status_text=result.get("statusText"),
+                    price_min=price_value if "+/mo" in result.get("price") else None,
+                    price_max=price_value if "+/mo" in result.get("price") else None,
+                    latitude=result.get("latLong", {}).get("latitude"),
+                    longitude=result.get("latLong", {}).get("longitude"),
+                    unit_count=result.get("unitCount"),
                 )
 
                 properties_list.append(building_obj)
@@ -238,14 +277,16 @@ class ZillowScraper(Scraper):
         return Property(
             site_name=self.site_name,
             property_url=url,
-            property_type=PropertyType(property_type),
+            property_type=PropertyType(property_type) if property_type in PropertyType.__members__ else None,
             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"),
+            agent=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"),
@@ -294,22 +335,3 @@ class ZillowScraper(Scraper):
             state=state,
             zip_code=zip_code,
         )
-
-    @staticmethod
-    def _get_headers():
-        return {
-            "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",
-            "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": "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

@@ -12,3 +12,7 @@ class NoResultsFound(Exception):
 
 class GeoCoordsNotFound(Exception):
     """Raised when no property is found for the given address"""
+
+
+class SearchTooBroad(Exception):
+    """Raised when the search is too broad"""

poetry.lock

@@ -408,6 +408,17 @@ files = [
     {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
 ]
 
+[[package]]
+name = "tls-client"
+version = "0.2.2"
+description = "Advanced Python HTTP Client."
+optional = false
+python-versions = "*"
+files = [
+    {file = "tls_client-0.2.2-py3-none-any.whl", hash = "sha256:30934871397cdad6862e00b5634f382666314a452ddd3d774e18323a0ad9b765"},
+    {file = "tls_client-0.2.2.tar.gz", hash = "sha256:78bc0e291e3aadc6c5e903b62bb26c01374577691f2a9e5e17899900a5927a13"},
+]
+
 [[package]]
 name = "tomli"
 version = "2.0.1"
@@ -450,4 +461,4 @@ zstd = ["zstandard (>=0.18.0)"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "3647d568f5623dd762f19029230626a62e68309fa2ef8be49a36382c19264a5f"
+content-hash = "9b77e1a09fcf2cf5e7e6be53f304cd21a6a51ea51680d661a178afe5e5343670"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.2.8"
+version = "0.2.17"
 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"
@@ -14,6 +14,7 @@ python = "^3.10"
 requests = "^2.31.0"
 pandas = "^2.1.0"
 openpyxl = "^3.1.2"
+tls-client = "^0.2.2"
 
 
 [tool.poetry.group.dev.dependencies]

tests/test_redfin.py

@@ -4,11 +4,13 @@ from homeharvest.exceptions import (
     InvalidListingType,
     NoResultsFound,
     GeoCoordsNotFound,
+    SearchTooBroad,
 )
 
 
 def test_redfin():
     results = [
+        scrape_property(location="San Diego", site_name="redfin", listing_type="for_sale"),
         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"),
@@ -24,9 +26,10 @@ def test_redfin():
                 location="abceefg ju098ot498hh9",
                 site_name="redfin",
                 listing_type="for_sale",
-            )
+            ),
+            scrape_property(location="Florida", site_name="redfin", listing_type="for_rent"),
         ]
-    except (InvalidSite, InvalidListingType, NoResultsFound, GeoCoordsNotFound):
+    except (InvalidSite, InvalidListingType, NoResultsFound, GeoCoordsNotFound, SearchTooBroad):
         assert True
 
     assert all([result is None for result in bad_results])

tests/test_zillow.py

@@ -11,8 +11,10 @@ def test_zillow():
     results = [
         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="Surprise, AZ", site_name=["zillow"], listing_type="for_sale"),
         scrape_property(location="Dallas, TX, USA", site_name="zillow", listing_type="sold"),
         scrape_property(location="85281", site_name="zillow"),
+        scrape_property(location="3268 88th st s, Lakewood", site_name="zillow", listing_type="for_rent"),
     ]
 
     assert all([result is not None for result in results])