Fetch new data and update the repository #884

	name: Fetch new data and update the repository

	on:
	workflow_dispatch:
	schedule:
	- cron: "5 8 /3 *"

	jobs:
	update-data:
	runs-on: ubuntu-latest
	steps:
	- name: Checkout code
	uses: actions/checkout@v3
	- name: Setup Python
	uses: actions/setup-python@master
	with:
	python-version: 3
	- name: Grab latest alltheplaces
	run: \|
	git clone --depth=1 https://github.com/alltheplaces/alltheplaces.git
	- name: Install scrapy
	run: \|
	pip install --quiet --upgrade pip scrapy xlrd geonamescache json5 chompjs xmltodict phonenumbers reverse_geocoder xmltodict requests_cache pycountry ijson openpyxl pyproj pygeohash unidecode phpserialize shapely babel geopandas h2 pdfplumber scrapy_zyte_api
	- name: Run USPS spider
	run: \|
	cd alltheplaces
	scrapy crawl usps_collection_boxes --output ../usps_collection_boxes.ndjson:ndgeojson --loglevel=ERROR
	- name: Sort the data
	run: \|
	mkdir -p data
	python sort.py usps_collection_boxes.ndjson usps_collection_boxes_sorted.ndjson --prefix-dir=data --prefix-chars=3
	- name: Push changes to remote
	run: \|
	git config user.email "ian.dees+bot@gmail.com"
	git config user.name "USPS Bot"
	echo "$(date +%Y-%m-%dT%H:%M:%SZ)" > data/last_updated.txt
	git add data
	git commit -m "Adding data from $(date +%Y-%m-%d)"
	git push origin master

Provide feedback