Compare commits

...

2 Commits

Author SHA1 Message Date
Cullen
c5b15e9be5 chore: version 2024-04-20 17:45:29 -05:00
joecryptotoo
7a525caeb8 added county, fips, and text desciption fields (#72) 2024-04-20 17:44:28 -05:00
4 changed files with 23 additions and 2 deletions

View File

@@ -73,6 +73,7 @@ class Description:
year_built: int | None = None
garage: float | None = None
stories: int | None = None
text: str | None = None
@dataclass
@@ -101,6 +102,7 @@ class Property:
latitude: float | None = None
longitude: float | None = None
neighborhoods: Optional[str] = None
county: Optional[str] = None
fips_code: Optional[str] = None
agents: list[Agent] = None
nearby_schools: list[str] = None

View File

@@ -176,6 +176,7 @@ class RealtorScraper(Scraper):
year_built=property_info["details"].get("year_built"),
garage=property_info["details"].get("garage"),
stories=property_info["details"].get("stories"),
text=property_info["description"].get("text"),
),
days_on_mls=days_on_mls,
agents=agents_schools["agents"],
@@ -330,6 +331,7 @@ class RealtorScraper(Scraper):
type
name
stories
text
}
source {
id
@@ -353,10 +355,17 @@ class RealtorScraper(Scraper):
lat
}
}
county {
name
fips_code
}
neighborhoods {
name
}
}
tax_record {
public_record_id
}
primary_photo {
href
}
@@ -536,6 +545,9 @@ class RealtorScraper(Scraper):
longitude=result["location"]["address"]["coordinate"].get("lon") if able_to_get_lat_long else None,
address=self._parse_address(result, search_type="general_search"),
description=self._parse_description(result),
neighborhoods=self._parse_neighborhoods(result),
county=result["location"]["county"].get("name"),
fips_code=result["location"]["county"].get("fips_code"),
days_on_mls=self.calculate_days_on_mls(result),
agents=agents_schools["agents"],
nearby_schools=agents_schools["schools"],
@@ -725,6 +737,7 @@ class RealtorScraper(Scraper):
year_built=description_data.get("year_built"),
garage=description_data.get("garage"),
stories=description_data.get("stories"),
text=description_data.get("text"),
)
@staticmethod

View File

@@ -8,6 +8,7 @@ ordered_properties = [
"mls",
"mls_id",
"status",
"text",
"style",
"street",
"unit",
@@ -28,6 +29,9 @@ ordered_properties = [
"price_per_sqft",
"latitude",
"longitude",
"neighborhoods",
"county",
"fips_code",
"stories",
"hoa_fee",
"parking_garage",
@@ -77,6 +81,8 @@ def process_result(result: Property) -> pd.DataFrame:
prop_data["year_built"] = description.year_built
prop_data["parking_garage"] = description.garage
prop_data["stories"] = description.stories
prop_data["text"] = description.text
properties_df = pd.DataFrame([prop_data])
properties_df = properties_df.reindex(columns=ordered_properties)

View File

@@ -1,6 +1,6 @@
[tool.poetry]
name = "homeharvest"
version = "0.3.18"
version = "0.3.19"
description = "Real estate scraping library"
authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
homepage = "https://github.com/Bunsly/HomeHarvest"