- data cleaning & CONDOP bug fixes

homeharvest/__init__.py

@@ -53,7 +53,9 @@ def scrape_property(
     if not properties_dfs:
         return pd.DataFrame()
 
+    properties_dfs = [df for df in properties_dfs if not df.empty]
+
     with warnings.catch_warnings():
         warnings.simplefilter("ignore", category=FutureWarning)
 
-        return pd.concat(properties_dfs, ignore_index=True, axis=0)[ordered_properties].replace({"None": "", None: ""})
+        return pd.concat(properties_dfs, ignore_index=True, axis=0)[ordered_properties].replace({"None": pd.NA, None: pd.NA, "": pd.NA})

homeharvest/core/scrapers/models.py

@@ -36,6 +36,7 @@ class PropertyType(Enum):
     CONDO_TOWNHOME = "CONDO_TOWNHOME"
     CONDO_TOWNHOME_ROWHOME_COOP = "CONDO_TOWNHOME_ROWHOME_COOP"
     CONDO = "CONDO"
+    CONDOP = "CONDOP"
     CONDOS = "CONDOS"
     COOP = "COOP"
     DUPLEX_TRIPLEX = "DUPLEX_TRIPLEX"
@@ -52,6 +53,7 @@ class PropertyType(Enum):
 
 @dataclass
 class Address:
+    full_line: str | None = None
     street: str | None = None
     unit: str | None = None
     city: str | None = None
@@ -121,7 +123,8 @@ class Property:
     neighborhoods: Optional[str] = None
     county: Optional[str] = None
     fips_code: Optional[str] = None
-    agents: list[Agent] = None
+    agents: list[Agent] | None = None
+    brokers: list[Broker] | None = None
     nearby_schools: list[str] = None
     assessed_value: int | None = None
     estimated_value: int | None = None

homeharvest/core/scrapers/realtor/__init__.py

@@ -10,7 +10,7 @@ from datetime import datetime
 from typing import Dict, Union, Optional
 
 from .. import Scraper
-from ..models import Property, Address, ListingType, Description, PropertyType, Agent
+from ..models import Property, Address, ListingType, Description, PropertyType, Agent, Broker
 
 
 class RealtorScraper(Scraper):
@@ -52,6 +52,7 @@ class RealtorScraper(Scraper):
                             listing_id
                         }
                         address {
+                            line
                             street_direction
                             street_number
                             street_name
@@ -180,6 +181,7 @@ class RealtorScraper(Scraper):
             ),
             days_on_mls=days_on_mls,
             agents=prop_details.get("agents"),
+            brokers=prop_details.get("brokers"),
             nearby_schools=prop_details.get("schools"),
             assessed_value=prop_details.get("assessed_value"),
             estimated_value=prop_details.get("estimated_value"),
@@ -235,6 +237,7 @@ class RealtorScraper(Scraper):
                             stories
                         }
                         address {
+                            line
                             street_direction
                             street_number
                             street_name
@@ -295,6 +298,7 @@ class RealtorScraper(Scraper):
                 address=self._parse_address(property_info, search_type="handle_address"),
                 description=self._parse_description(property_info),
                 agents=prop_details.get("agents"),
+                brokers=prop_details.get("brokers"),
                 nearby_schools=prop_details.get("schools"),
                 assessed_value=prop_details.get("assessed_value"),
                 estimated_value=prop_details.get("estimated_value"),
@@ -350,6 +354,7 @@ class RealtorScraper(Scraper):
                                         street_number
                                         street_name
                                         street_suffix
+                                        line
                                         unit
                                         city
                                         state_code
@@ -553,6 +558,7 @@ class RealtorScraper(Scraper):
                 fips_code=result["location"]["county"].get("fips_code") if result["location"]["county"] else None,
                 days_on_mls=self.calculate_days_on_mls(result),
                 agents=prop_details.get("agents"),
+                brokers=prop_details.get("brokers"),
                 nearby_schools=prop_details.get("schools"),
                 assessed_value=prop_details.get("assessed_value"),
                 estimated_value=prop_details.get("estimated_value"),
@@ -654,6 +660,8 @@ class RealtorScraper(Scraper):
         if not self.extra_property_data:
             return {}
 
+        #: TODO: migrate "advertisers" and "estimates" to general query
+
         query = """query GetHome($property_id: ID!) {
                     home(property_id: $property_id) {
                         __typename
@@ -666,6 +674,12 @@ class RealtorScraper(Scraper):
                             phones { number type ext primary }
                         }
                         
+                        consumer_advertisers {
+                            name
+                            phone
+                            href
+                            type
+                        }
                 
                         nearbySchools: nearby_schools(radius: 5.0, limit_per_level: 3) { 
                             __typename schools { district { __typename id name } } 
@@ -700,7 +714,9 @@ class RealtorScraper(Scraper):
             except (KeyError, TypeError, IndexError):
                 return {}
 
-        ads = get_key(["data", "home", "advertisers"])
+        agents = get_key(["data", "home", "advertisers"])
+        advertisers = get_key(["data", "home", "consumer_advertisers"])
+
         schools = get_key(["data", "home", "nearbySchools", "schools"])
         assessed_value = get_key(["data", "home", "taxHistory", 0, "assessment", "total"])
         estimated_value = get_key(["data", "home", "estimates", "currentValues", 0, "estimate"])
@@ -709,11 +725,18 @@ class RealtorScraper(Scraper):
             name=ad["name"],
             email=ad["email"],
             phones=ad["phones"]
-        ) for ad in ads]
+        ) for ad in agents]
+
+        brokers = [Broker(
+            name=ad["name"],
+            phone=ad["phone"],
+            website=ad["href"]
+        ) for ad in advertisers if ad.get("type") != "Agent"]
 
         schools = [school["district"]["name"] for school in schools if school['district'].get('name')]
         return {
             "agents": agents if agents else None,
+            "brokers": brokers if brokers else None,
             "schools": schools if schools else None,
             "assessed_value": assessed_value if assessed_value else None,
             "estimated_value": estimated_value if estimated_value else None,
@@ -747,6 +770,7 @@ class RealtorScraper(Scraper):
             address = result["address"]
 
         return Address(
+            full_line=address.get("line"),
             street=" ".join(
                 part for part in [
                     address.get("street_number"),
@@ -782,7 +806,7 @@ class RealtorScraper(Scraper):
         return Description(
             primary_photo=primary_photo,
             alt_photos=RealtorScraper.process_alt_photos(result.get("photos")),
-            style=PropertyType(style) if style else None,
+            style=PropertyType.__getitem__(style) if style and style in PropertyType.__members__ else None,
             beds=description_data.get("beds"),
             baths_full=description_data.get("baths_full"),
             baths_half=description_data.get("baths_half"),

homeharvest/utils.py

@@ -10,6 +10,7 @@ ordered_properties = [
     "status",
     "text",
     "style",
+    "full_street_line",
     "street",
     "unit",
     "city",
@@ -40,6 +41,9 @@ ordered_properties = [
     "agent",
     "agent_email",
     "agent_phones",
+    "broker",
+    "broker_phone",
+    "broker_website",
     "nearby_schools",
     "primary_photo",
     "alt_photos",
@@ -52,6 +56,7 @@ def process_result(result: Property) -> pd.DataFrame:
 
     if "address" in prop_data:
         address_data = prop_data["address"]
+        prop_data["full_street_line"] = address_data.full_line
         prop_data["street"] = address_data.street
         prop_data["unit"] = address_data.unit
         prop_data["city"] = address_data.city
@@ -65,6 +70,13 @@ def process_result(result: Property) -> pd.DataFrame:
             prop_data["agent_email"] = agents[0].email
             prop_data["agent_phones"] = agents[0].phones
 
+    if "brokers" in prop_data:
+        brokers = prop_data["brokers"]
+        if brokers:
+            prop_data["broker"] = brokers[0].name
+            prop_data["broker_phone"] = brokers[0].phone
+            prop_data["broker_website"] = brokers[0].website
+
     prop_data["price_per_sqft"] = prop_data["prc_sqft"]
     prop_data["nearby_schools"] = filter(None, prop_data["nearby_schools"]) if prop_data["nearby_schools"] else None
     prop_data["nearby_schools"] = ", ".join(set(prop_data["nearby_schools"])) if prop_data["nearby_schools"] else None

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.3.21"
+version = "0.3.24"
 description = "Real estate scraping library"
 authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
 homepage = "https://github.com/Bunsly/HomeHarvest"

tests/test_realtor.py

@@ -156,3 +156,12 @@ def test_realtor_without_extra_details():
     ]
 
     assert results[0] != results[1]
+
+
+def test_pr_zip_code():
+    results = scrape_property(
+        location="00741",
+        listing_type="for_sale",
+    )
+
+    assert results is not None and len(results) > 0