From e82eeaa59fe4f794ef3280153895caefffdf7f9d Mon Sep 17 00:00:00 2001 From: Cullen Watson Date: Wed, 20 Sep 2023 20:25:50 -0500 Subject: [PATCH] docs: add keep duplicates flag --- README.md | 2 ++ pyproject.toml | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index e92d929..37f4515 100644 --- a/README.md +++ b/README.md @@ -37,6 +37,7 @@ By default: - The `-o` or `--output` default format is `excel`. Options are `csv` or `excel`. - If `-f` or `--filename` is left blank, the default is `HomeHarvest_`. - 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 ```py @@ -73,6 +74,7 @@ Required Optional ├── site_name (list[enum], default=all three sites): zillow, realtor.com, redfin ├── 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 diff --git a/pyproject.toml b/pyproject.toml index c439cca..9d014b0 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "homeharvest" -version = "0.2.7" +version = "0.2.8" description = "Real estate scraping library supporting Zillow, Realtor.com & Redfin." authors = ["Zachary Hampton ", "Cullen Watson "] homepage = "https://github.com/ZacharyHampton/HomeHarvest"