Htmlparse - parse out page citation references from page html #1801

	name: lint_python
	on:
	push:
	branches: ["main"]
	pull_request:
	branches: ["main"]
	jobs:
	ruff:
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v3
	- run: pip install --user ruff
	- run: ruff --format=github --target-version=py37 .

	lint_python:
	needs: ruff
	runs-on: ubuntu-latest
	# https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsenv
	env:
	TESTDEADLINK_KEY: ${{ secrets.TESTDEADLINK_KEY }}
	ia_sandbox: ${{ secrets.ia_sandbox }}
	steps:
	- uses: actions/checkout@v3
	- name: Install poetry
	run: pipx install poetry
	- uses: actions/setup-python@v4
	with:
	python-version: 3.x
	cache: 'poetry'
	# - name: Redis Server in GitHub Actions
	# uses: supercharge/[email protected]
	- run: pip install --upgrade pip wheel
	- run: poetry install --with=dev
	- run: poetry run black --check .
	- run: poetry run codespell src/ tests/ .md .py # --ignore-words-list="" --skip=".css,.js,*.lock"
	- run: mkdir --parents --verbose .mypy_cache
	- run: poetry run mypy --ignore-missing-imports --install-types --non-interactive --exclude test_data --exclude deprecated .
	# remove safety check, as it was requiring a commercial license to succeed!
	# - run: poetry run safety check

	# Copy the config
	- run: cp config_sample.py config.py
	- run: poetry run pytest .

Provide feedback