Scrape PDFs, parse, and transform #105

	name: Scrape PDFs, parse, and transform

	on:
	# Run this job at 15:00 UTC every day
	schedule:
	- cron: "0 15 * * *"
	# Also allow the job to be manually triggered
	workflow_dispatch:

	permissions:
	contents: write

	jobs:
	fetch:
	runs-on: ubuntu-latest
	timeout-minutes: 30
	steps:
	- name: Check-out the repo
	uses: actions/checkout@v4
	with:
	fetch-depth: 0
	ref: main

	- name: Set up Python 3.10
	uses: actions/setup-python@v4
	with:
	python-version: "3.10"

	- name: Install Python venv and requirements
	run: make venv

	- name: Configure git
	run: git config --global user.name "Automated"; git config user.email "[email protected]"

	- name: Log Python packages
	run: \|
	source venv/bin/activate
	pip freeze

	- name: Log Python version and path
	run: \|
	source venv/bin/activate
	python --version
	which python

	# Scrape TSA website for new PDFs
	- name: Scrape
	run: \|
	source venv/bin/activate
	make scrape
	git add pdfs
	git diff --cached --quiet \|\| git commit -m "Add new/updated TSA complaint PDFs"
	git push

	# Parse new PDFs and transform data
	- name: Parse and transform
	run: \|
	source venv/bin/activate
	make transform
	git add output
	git diff --cached --quiet \|\| git commit -m "Parse new PDFs and transform data"
	git push

Provide feedback