- data cleaning & CONDOP bug fixes

Bunsly · May 13, 2024 · 803fd61 · 803fd61
1 parent b23b55c
commit 803fd61
Show file tree

Hide file tree

Showing 4 changed files with 6 additions and 3 deletions.
diff --git a/homeharvest/__init__.py b/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})
diff --git a/homeharvest/core/scrapers/models.py b/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"

diff --git a/homeharvest/core/scrapers/realtor/__init__.py b/homeharvest/core/scrapers/realtor/__init__.py
@@ -806,7 +806,7 @@ def _parse_description(result: dict) -> Description:
         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"),

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.3.23"
+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"