docs: add keep duplicates flag

pull/14/head
Cullen Watson 2023-09-20 20:25:50 -05:00
parent 644f16b25b
commit e82eeaa59f
2 changed files with 3 additions and 1 deletions

View File

@ -37,6 +37,7 @@ By default:
- The `-o` or `--output` default format is `excel`. Options are `csv` or `excel`. - The `-o` or `--output` default format is `excel`. Options are `csv` or `excel`.
- If `-f` or `--filename` is left blank, the default is `HomeHarvest_<current_timestamp>`. - If `-f` or `--filename` is left blank, the default is `HomeHarvest_<current_timestamp>`.
- If `-p` or `--proxy` is not provided, the scraper uses the local IP. - If `-p` or `--proxy` is not provided, the scraper uses the local IP.
- Use `-k` or `--keep_duplicates` to keep duplicate properties based on address. If not provided, duplicates will be removed.
### Python ### Python
```py ```py
@ -73,6 +74,7 @@ Required
Optional Optional
├── site_name (list[enum], default=all three sites): zillow, realtor.com, redfin ├── site_name (list[enum], default=all three sites): zillow, realtor.com, redfin
├── proxy (str): in format 'http://user:pass@host:port' or [https, socks] ├── proxy (str): in format 'http://user:pass@host:port' or [https, socks]
└── keep_duplicates (bool, default=False): whether to keep or remove duplicate properties based on address
``` ```
### Property Schema ### Property Schema

View File

@ -1,6 +1,6 @@
[tool.poetry] [tool.poetry]
name = "homeharvest" name = "homeharvest"
version = "0.2.7" version = "0.2.8"
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/ZacharyHampton/HomeHarvest" homepage = "https://github.com/ZacharyHampton/HomeHarvest"