fix: use enum value (#65)

- alt photos bug fix (#57)

README.md

@@ -124,6 +124,7 @@ Property
 │ ├── days_on_mls
 │ ├── list_price
 │ ├── list_date
+│ ├── pending_date
 │ ├── sold_price
 │ ├── last_sold_date
 │ ├── price_per_sqft

homeharvest/core/scrapers/models.py

@@ -23,6 +23,27 @@ class ListingType(Enum):
     SOLD = "SOLD"
 
 
+class PropertyType(Enum):
+    APARTMENT = "APARTMENT"
+    BUILDING = "BUILDING"
+    COMMERCIAL = "COMMERCIAL"
+    CONDO_TOWNHOME = "CONDO_TOWNHOME"
+    CONDO_TOWNHOME_ROWHOME_COOP = "CONDO_TOWNHOME_ROWHOME_COOP"
+    CONDO = "CONDO"
+    CONDOS = "CONDOS"
+    COOP = "COOP"
+    DUPLEX_TRIPLEX = "DUPLEX_TRIPLEX"
+    FARM = "FARM"
+    INVESTMENT = "INVESTMENT"
+    LAND = "LAND"
+    MOBILE = "MOBILE"
+    MULTI_FAMILY = "MULTI_FAMILY"
+    RENTAL = "RENTAL"
+    SINGLE_FAMILY = "SINGLE_FAMILY"
+    TOWNHOMES = "TOWNHOMES"
+    OTHER = "OTHER"
+
+
 @dataclass
 class Address:
     street: str | None = None
@@ -36,7 +57,7 @@ class Address:
 class Description:
     primary_photo: str | None = None
     alt_photos: list[str] | None = None
-    style: str | None = None
+    style: PropertyType | None = None
     beds: int | None = None
     baths_full: int | None = None
     baths_half: int | None = None
@@ -58,6 +79,7 @@ class Property:
 
     list_price: int | None = None
     list_date: str | None = None
+    pending_date: str | None = None
     last_sold_date: str | None = None
     prc_sqft: int | None = None
     hoa_fee: int | None = None

homeharvest/core/scrapers/realtor/__init__.py

@@ -9,7 +9,7 @@ from typing import Dict, Union, Optional
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
 from .. import Scraper
-from ..models import Property, Address, ListingType, Description
+from ..models import Property, Address, ListingType, Description, PropertyType
 
 
 class RealtorScraper(Scraper):
@@ -84,11 +84,10 @@ class RealtorScraper(Scraper):
                             garage
                             permalink
                         }
-                        primary_photo {
+                        media {
-                            href
+                            photos {
-                        }
+                                href
-                        photos {
+                            }
-                            href
                         }
                     }
                 }"""
@@ -120,9 +119,11 @@ class RealtorScraper(Scraper):
             "list_date") else None
         last_sold_date_str = property_info["basic"]["sold_date"].split("T")[0] if property_info["basic"].get(
             "sold_date") else None
+        pending_date_str = property_info["pending_date"].split("T")[0] if property_info.get("pending_date") else None
 
         list_date = datetime.strptime(list_date_str, "%Y-%m-%d") if list_date_str else None
         last_sold_date = datetime.strptime(last_sold_date_str, "%Y-%m-%d") if last_sold_date_str else None
+        pending_date = datetime.strptime(pending_date_str, "%Y-%m-%d") if pending_date_str else None
         today = datetime.now()
 
         days_on_mls = None
@@ -150,6 +151,7 @@ class RealtorScraper(Scraper):
                and property_info["basic"].get("sqft")
             else None,
             last_sold_date=last_sold_date,
+            pending_date=pending_date,
             latitude=property_info["address"]["location"]["coordinate"].get("lat")
             if able_to_get_lat_long
             else None,
@@ -158,9 +160,7 @@ class RealtorScraper(Scraper):
             else None,
             address=self._parse_address(property_info, search_type="handle_listing"),
             description=Description(
-                primary_photo=property_info["primary_photo"].get("href", "").replace("s.jpg",
+                alt_photos=self.process_alt_photos(property_info.get("media", {}).get("photos", [])),
-                                                                                     "od-w480_h360_x2.webp?w=1080&q=75"),
-                alt_photos=self.process_alt_photos(property_info.get("photos", [])),
                 style=property_info["basic"].get("type", "").upper(),
                 beds=property_info["basic"].get("beds"),
                 baths_full=property_info["basic"].get("baths_full"),
@@ -298,6 +298,7 @@ class RealtorScraper(Scraper):
                             count
                             total
                             results {
+                                pending_date
                                 property_id
                                 list_date
                                 status
@@ -310,6 +311,7 @@ class RealtorScraper(Scraper):
                                     is_pending
                                 }
                                 description {
+                                    type
                                     sqft
                                     beds
                                     baths_full
@@ -663,7 +665,6 @@ class RealtorScraper(Scraper):
 
     @staticmethod
     def _parse_description(result: dict) -> Description:
-
         description_data = result.get("description", {})
 
         if description_data is None or not isinstance(description_data, dict):
@@ -683,7 +684,7 @@ class RealtorScraper(Scraper):
         return Description(
             primary_photo=primary_photo,
             alt_photos=RealtorScraper.process_alt_photos(result.get("photos")),
-            style=style,
+            style=PropertyType(style) if style else None,
             beds=description_data.get("beds"),
             baths_full=description_data.get("baths_full"),
             baths_half=description_data.get("baths_half"),

homeharvest/utils.py

@@ -53,7 +53,7 @@ def process_result(result: Property) -> pd.DataFrame:
     description = result.description
     prop_data["primary_photo"] = description.primary_photo
     prop_data["alt_photos"] = ", ".join(description.alt_photos)
-    prop_data["style"] = description.style
+    prop_data["style"] = description.style.value
     prop_data["beds"] = description.beds
     prop_data["full_baths"] = description.baths_full
     prop_data["half_baths"] = description.baths_half

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.6.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand.
 
 [[package]]
 name = "certifi"
@@ -121,17 +121,6 @@ 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"
@@ -209,20 +198,6 @@ 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 = "23.2"
@@ -438,4 +413,4 @@ zstd = ["zstandard (>=0.18.0)"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<3.13"
-content-hash = "09ad811d74a42363ff4c3ccd012d8f73c89d7d978e5a6445b0f3d2e231922f1b"
+content-hash = "018a1a6afb2d7f4c764b9e1926145d7d8d630ffa43f7786e062cbfd9a9a845a0"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.3.13"
+version = "0.3.15"
 description = "Real estate scraping library"
 authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
 homepage = "https://github.com/Bunsly/HomeHarvest"