Compare commits

...

8 Commits

Author SHA1 Message Date
Cullen Watson
f7e74cf535 Merge pull request #44 from Bunsly/fix_postal_search
fix postal search to search just by zip
2023-12-02 00:40:13 -06:00
Cullen Watson
e17b976923 fix postal search to search just by zip 2023-12-02 00:39:28 -06:00
Zachary Hampton
ad13b55ea6 Update README.md 2023-11-30 11:48:48 -07:00
Cullen Watson
19f23c95c4 Merge pull request #43 from Bunsly/add_photos
Add photos
2023-11-24 21:40:34 -06:00
Cullen
4676ec9839 chore: remove test file 2023-11-24 13:42:52 -06:00
Cullen
6dd0b058d3 chore: version 2023-11-24 13:41:46 -06:00
Cullen
a74c1a9950 enh: add photos 2023-11-24 13:40:57 -06:00
Cullen Watson
fa507dbc72 docs: typo 2023-11-20 01:05:10 -06:00
5 changed files with 58 additions and 7 deletions

View File

@@ -2,14 +2,10 @@
**HomeHarvest** is a simple, yet comprehensive, real estate scraping library that extracts and formats data in the style of MLS listings.
[![Try with Replit](https://replit.com/badge?caption=Try%20with%20Replit)](https://replit.com/@ZacharyHampton/HomeHarvestDemo)
**Not technical?** Try out the web scraping tool on our site at [tryhomeharvest.com](https://tryhomeharvest.com).
*Looking to build a data-focused software product?* **[Book a call](https://bunsly.com)** *to work with us.*
Check out another project we wrote: ***[JobSpy](https://github.com/Bunsly/JobSpy)** a Python package for job scraping*
## HomeHarvest Features
- **Source**: Fetches properties directly from **Realtor.com**.
@@ -92,7 +88,7 @@ Optional
│ Example: 30 (fetches properties listed/sold in the last 30 days)
├── date_from, date_to (string): Start and end dates to filter properties listed or sold, both dates are required.
} (use this to get properties in chunks as there's a 10k result limit)
| (use this to get properties in chunks as there's a 10k result limit)
│ Format for both must be "YYYY-MM-DD".
│ Example: "2023-05-01", "2023-05-15" (fetches properties listed/sold between these dates)
@@ -193,7 +189,7 @@ The following exceptions may be raised when using HomeHarvest:
**A:** This indicates that you have been blocked by Realtor.com for sending too many requests. We recommend:
- Waiting a few seconds between requests.
- Trying a VPN or useing a proxy as a parameter to scrape_property() to change your IP address.
- Trying a VPN or using a proxy as a parameter to scrape_property() to change your IP address.
---

View File

@@ -34,6 +34,8 @@ class Address:
@dataclass
class Description:
primary_photo: str | None = None
alt_photos: list[str] | None = None
style: str | None = None
beds: int | None = None
baths_full: int | None = None

View File

@@ -84,6 +84,12 @@ class RealtorScraper(Scraper):
garage
permalink
}
primary_photo {
href
}
photos {
href
}
}
}"""
@@ -152,6 +158,8 @@ 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", "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"),
@@ -247,6 +255,12 @@ class RealtorScraper(Scraper):
units
year_built
}
primary_photo {
href
}
photos {
href
}
}
}"""
@@ -334,6 +348,12 @@ class RealtorScraper(Scraper):
name
}
}
primary_photo {
href
}
photos {
href
}
}
}
}"""
@@ -553,6 +573,11 @@ class RealtorScraper(Scraper):
"radius": "{}mi".format(self.radius),
}
elif location_type == "postal_code":
search_variables |= {
"postal_code": location_info.get("postal_code"),
}
else: #: general search, location
search_variables |= {
"city": location_info.get("city"),
@@ -621,6 +646,7 @@ 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):
@@ -630,7 +656,16 @@ class RealtorScraper(Scraper):
if style is not None:
style = style.upper()
primary_photo = ""
if result and "primary_photo" in result:
primary_photo_info = result["primary_photo"]
if primary_photo_info and "href" in primary_photo_info:
primary_photo_href = primary_photo_info["href"]
primary_photo = primary_photo_href.replace("s.jpg", "od-w480_h360_x2.webp?w=1080&q=75")
return Description(
primary_photo=primary_photo,
alt_photos=RealtorScraper.process_alt_photos(result.get("photos")),
style=style,
beds=description_data.get("beds"),
baths_full=description_data.get("baths_full"),
@@ -643,6 +678,7 @@ class RealtorScraper(Scraper):
stories=description_data.get("stories"),
)
@staticmethod
def calculate_days_on_mls(result: dict) -> Optional[int]:
list_date_str = result.get("list_date")
@@ -661,3 +697,16 @@ class RealtorScraper(Scraper):
days = (today - list_date).days
if days >= 0:
return days
@staticmethod
def process_alt_photos(photos_info):
try:
alt_photos = []
if photos_info:
for photo_info in photos_info:
href = photo_info.get("href", "")
alt_photo_href = href.replace("s.jpg", "od-w480_h360_x2.webp?w=1080&q=75")
alt_photos.append(alt_photo_href)
return alt_photos
except Exception:
pass

View File

@@ -31,6 +31,8 @@ ordered_properties = [
"stories",
"hoa_fee",
"parking_garage",
"primary_photo",
"alt_photos",
]
@@ -49,6 +51,8 @@ def process_result(result: Property) -> pd.DataFrame:
prop_data["price_per_sqft"] = prop_data["prc_sqft"]
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["beds"] = description.beds
prop_data["full_baths"] = description.baths_full

View File

@@ -1,6 +1,6 @@
[tool.poetry]
name = "homeharvest"
version = "0.3.9"
version = "0.3.11"
description = "Real estate scraping library supporting Zillow, Realtor.com & Redfin."
authors = ["Zachary Hampton <zachary@zacharysproducts.com>", "Cullen Watson <cullen@cullen.ai>"]
homepage = "https://github.com/Bunsly/HomeHarvest"