Scrape latest data #1141

	name: Scrape latest data

	on:
	push:
	workflow_dispatch:
	schedule:
	- cron: '21 11 * * *'

	jobs:
	scheduled:
	runs-on: ubuntu-latest
	steps:
	- name: Check out this repo
	uses: actions/checkout@v2
	with:
	fetch-depth: 0
	- name: Set up Python
	uses: actions/setup-python@v2
	with:
	python-version: 3.8
	- uses: actions/cache@v2
	name: Configure pip caching
	with:
	path: ~/.cache/pip
	key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
	restore-keys: \|
	${{ runner.os }}-pip-
	- name: Install Python dependencies
	run: \|-
	pip install -r requirements.txt
	- name: Fetch latest data
	run: \|-
	cp Street_Tree_List.csv Street_Tree_List-old.csv
	curl -o Street_Tree_List-unsorted.csv "https://data.sfgov.org/api/views/tkzw-k3nq/rows.csv?accessType=DOWNLOAD"
	# Remove heading line and use it to start a new file
	head -n 1 Street_Tree_List-unsorted.csv > Street_Tree_List.csv
	# Sort all but the first line and append to that file
	tail -n +2 "Street_Tree_List-unsorted.csv" \| sort >> Street_Tree_List.csv
	# Generate commit message using csv-diff
	csv-diff Street_Tree_List-old.csv Street_Tree_List.csv --key=TreeID --singular=tree --plural=trees > message.txt
	- name: Commit and push if it changed
	run: \|-
	git config user.name "Automated"
	git config user.email "[email protected]"
	git add Street_Tree_List.csv
	timestamp=$(date -u)
	git commit -F message.txt \|\| exit 0
	git push

Provide feedback