Canada Gas Dashboard Hourly Scrape #2084

	name: Canada Gas Dashboard Hourly Scrape

	on:
	schedule:
	# Every hour at minute 7 (UTC)
	- cron: "7 * * * *"
	workflow_dispatch:

	permissions:
	contents: read

	concurrency:
	group: canada-hourly-scrape
	cancel-in-progress: false

	jobs:
	scrape:
	runs-on: ubuntu-latest
	timeout-minutes: 20
	defaults:
	run:
	working-directory: Collection/gasgx/gasgx_canadian_natural_gas_data_acquisition_module
	env:
	PYTHONUNBUFFERED: "1"
	SUPABASE_URL: ${{ secrets.SUPABASE_URL }}
	SUPABASE_SERVICE_ROLE_KEY: ${{ secrets.SUPABASE_SERVICE_ROLE_KEY }}
	# Optional fallback if your repo still uses old key name
	SUPABASE_KEY: ${{ secrets.SUPABASE_KEY }}
	SUPABASE_TABLE_RUNS: canada_scrape_runs
	SUPABASE_TABLE_PAYLOADS: canada_chart_payloads
	SUPABASE_TABLE_POINTS: canada_chart_points
	SUPABASE_TABLE_ASSETS: canada_chart_assets
	SUPABASE_TABLE_TABLES: canada_chart_tables
	SUPABASE_TABLE_TABLE_POINTS: canada_chart_table_points
	HTTP_TIMEOUT_SECONDS: "30"
	CURRENCY: CAD
	UNIT: GJ
	LOCAL_TIMEZONE: Asia/Shanghai

	steps:
	- name: Checkout
	uses: actions/checkout@v4

	- name: Setup Python
	uses: actions/setup-python@v5
	with:
	python-version: "3.9"
	cache: "pip"
	cache-dependency-path: Collection/gasgx/gasgx_canadian_natural_gas_data_acquisition_module/requirements.txt

	- name: Install dependencies
	run: pip install -r requirements.txt

	- name: Verify OCR runtime
	run: \|
	python - <<'PY'
	import sys
	from rapidocr_onnxruntime import RapidOCR
	print("python:", sys.version)
	print("rapidocr:", RapidOCR)
	PY

	- name: Run collector once
	run: python collector.py --once

Navigation Menu