mirror of
https://github.com/Bunsly/HomeHarvest.git
synced 2026-03-05 12:04:31 -08:00
Compare commits
6 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
5b6a9943cc | ||
|
|
9816defaf3 | ||
|
|
f692b438b2 | ||
|
|
30f48f54c8 | ||
|
|
7f86f69610 | ||
|
|
cc64dacdb0 |
@@ -6,7 +6,7 @@
|
|||||||
|
|
||||||
**Not technical?** Try out the web scraping tool on our site at [tryhomeharvest.com](https://tryhomeharvest.com).
|
**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://calendly.com/bunsly/15min)** *to work with us.*
|
*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*
|
Check out another project we wrote: ***[JobSpy](https://github.com/Bunsly/JobSpy)** – a Python package for job scraping*
|
||||||
|
|
||||||
@@ -91,15 +91,16 @@ Optional
|
|||||||
├── past_days (integer): Number of past days to filter properties. Utilizes 'last_sold_date' for 'sold' listing types, and 'list_date' for others (for_rent, for_sale).
|
├── past_days (integer): Number of past days to filter properties. Utilizes 'last_sold_date' for 'sold' listing types, and 'list_date' for others (for_rent, for_sale).
|
||||||
│ Example: 30 (fetches properties listed/sold in the last 30 days)
|
│ Example: 30 (fetches properties listed/sold in the last 30 days)
|
||||||
│
|
│
|
||||||
├── date_range (string tuple): Start and end dates to filter properties listed or sold, both dates are required.
|
├── 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".
|
│ Format for both must be "YYYY-MM-DD".
|
||||||
│ Example: ("2023-05-01", "2023-05-15") (fetches properties listed/sold between these dates)
|
│ Example: "2023-05-01", "2023-05-15" (fetches properties listed/sold between these dates)
|
||||||
│
|
│
|
||||||
├── mls_only (True/False): If set, fetches only MLS listings (mainly applicable to 'sold' listings)
|
├── mls_only (True/False): If set, fetches only MLS listings (mainly applicable to 'sold' listings)
|
||||||
│
|
│
|
||||||
└── proxy (string): In format 'http://user:pass@host:port'
|
└── proxy (string): In format 'http://user:pass@host:port'
|
||||||
|
|
||||||
|
|
||||||
```
|
```
|
||||||
|
|
||||||
### CLI
|
### CLI
|
||||||
@@ -177,7 +178,7 @@ Property
|
|||||||
The following exceptions may be raised when using HomeHarvest:
|
The following exceptions may be raised when using HomeHarvest:
|
||||||
|
|
||||||
- `InvalidListingType` - valid options: `for_sale`, `for_rent`, `sold`
|
- `InvalidListingType` - valid options: `for_sale`, `for_rent`, `sold`
|
||||||
- `NoResultsFound` - no properties found from your search
|
- `InvalidDate` - date_from or date_to is not in the format YYYY-MM-DD
|
||||||
|
|
||||||
|
|
||||||
## Frequently Asked Questions
|
## Frequently Asked Questions
|
||||||
|
|||||||
@@ -49,6 +49,7 @@ class RealtorScraper(Scraper):
|
|||||||
listing_id
|
listing_id
|
||||||
}
|
}
|
||||||
address {
|
address {
|
||||||
|
street_direction
|
||||||
street_number
|
street_number
|
||||||
street_name
|
street_name
|
||||||
street_suffix
|
street_suffix
|
||||||
@@ -215,6 +216,7 @@ class RealtorScraper(Scraper):
|
|||||||
stories
|
stories
|
||||||
}
|
}
|
||||||
address {
|
address {
|
||||||
|
street_direction
|
||||||
street_number
|
street_number
|
||||||
street_name
|
street_name
|
||||||
street_suffix
|
street_suffix
|
||||||
@@ -315,6 +317,7 @@ class RealtorScraper(Scraper):
|
|||||||
}
|
}
|
||||||
location {
|
location {
|
||||||
address {
|
address {
|
||||||
|
street_direction
|
||||||
street_number
|
street_number
|
||||||
street_name
|
street_name
|
||||||
street_suffix
|
street_suffix
|
||||||
@@ -606,6 +609,7 @@ class RealtorScraper(Scraper):
|
|||||||
return Address(
|
return Address(
|
||||||
street=" ".join([
|
street=" ".join([
|
||||||
self.handle_none_safely(address.get('street_number')),
|
self.handle_none_safely(address.get('street_number')),
|
||||||
|
self.handle_none_safely(address.get('street_direction')),
|
||||||
self.handle_none_safely(address.get('street_name')),
|
self.handle_none_safely(address.get('street_name')),
|
||||||
self.handle_none_safely(address.get('street_suffix')),
|
self.handle_none_safely(address.get('street_suffix')),
|
||||||
]).strip(),
|
]).strip(),
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
[tool.poetry]
|
[tool.poetry]
|
||||||
name = "homeharvest"
|
name = "homeharvest"
|
||||||
version = "0.3.8"
|
version = "0.3.9"
|
||||||
description = "Real estate scraping library supporting Zillow, Realtor.com & Redfin."
|
description = "Real estate scraping library supporting Zillow, Realtor.com & Redfin."
|
||||||
authors = ["Zachary Hampton <zachary@zacharysproducts.com>", "Cullen Watson <cullen@cullen.ai>"]
|
authors = ["Zachary Hampton <zachary@zacharysproducts.com>", "Cullen Watson <cullen@cullen.ai>"]
|
||||||
homepage = "https://github.com/Bunsly/HomeHarvest"
|
homepage = "https://github.com/Bunsly/HomeHarvest"
|
||||||
|
|||||||
Reference in New Issue
Block a user