turtlebasket
/
HomeHarvest
mirror of https://github.com/Bunsly/HomeHarvest.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

- data cleaning & CONDOP bug fixes

pull/82/head v0.3.24
Zachary Hampton 2024-05-12 21:12:12 -07:00
parent b23b55ca80
commit 803fd618e9
4 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
homeharvest/__init__.py
View File

@ -53,7 +53,9 @@ def scrape_property(
if not properties_dfs: if not properties_dfs:
return pd.DataFrame() return pd.DataFrame()
properties_dfs = [df for df in properties_dfs if not df.empty]
with warnings.catch_warnings(): with warnings.catch_warnings():
warnings.simplefilter("ignore", category=FutureWarning) 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})

1
homeharvest/core/scrapers/models.py
View File

@ -36,6 +36,7 @@ class PropertyType(Enum):
CONDO_TOWNHOME = "CONDO_TOWNHOME" CONDO_TOWNHOME = "CONDO_TOWNHOME"
CONDO_TOWNHOME_ROWHOME_COOP = "CONDO_TOWNHOME_ROWHOME_COOP" CONDO_TOWNHOME_ROWHOME_COOP = "CONDO_TOWNHOME_ROWHOME_COOP"
CONDO = "CONDO" CONDO = "CONDO"
CONDOP = "CONDOP"
CONDOS = "CONDOS" CONDOS = "CONDOS"
COOP = "COOP" COOP = "COOP"
DUPLEX_TRIPLEX = "DUPLEX_TRIPLEX" DUPLEX_TRIPLEX = "DUPLEX_TRIPLEX"

2
homeharvest/core/scrapers/realtor/__init__.py
View File

@ -806,7 +806,7 @@ class RealtorScraper(Scraper):
return Description( return Description(
primary_photo=primary_photo, primary_photo=primary_photo,
alt_photos=RealtorScraper.process_alt_photos(result.get("photos")), 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"), beds=description_data.get("beds"),
baths_full=description_data.get("baths_full"), baths_full=description_data.get("baths_full"),
baths_half=description_data.get("baths_half"), baths_half=description_data.get("baths_half"),

2
pyproject.toml
View File

@ -1,6 +1,6 @@
[tool.poetry] [tool.poetry]
name = "homeharvest" name = "homeharvest"
version = "0.3.23" version = "0.3.24"
description = "Real estate scraping library" description = "Real estate scraping library"
authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"] authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
homepage = "https://github.com/Bunsly/HomeHarvest" homepage = "https://github.com/Bunsly/HomeHarvest"