Download and clean transcripts #36

	name: Download and clean transcripts

	on:
	workflow_dispatch:
	schedule:
	- cron: "41 23 * * 6" # “At 23:43 on Saturday.”

	jobs:
	scheduled:
	runs-on: ubuntu-latest
	steps:
	- name: Check out this repo
	uses: actions/checkout@v3
	with:
	submodules: recursive

	- name: Update submodule
	run: git submodule update --remote

	- name: Set up Python ${{ matrix.python-version }}
	uses: actions/setup-python@v4
	with:
	python-version: "3.10"
	cache: 'pip' # caching pip dependencies

	- name: Install dependencies
	run: \|
	python -m pip install --upgrade pip
	pip install -r requirements/requirements.txt

	- name: Add spaCy model language
	run: python -m spacy download en_core_web_sm

	- name: Run flow
	run: python flows/clean_transcripts.py

	- name: Commit and push if it changed
	run: \|-
	git config user.name "Automated"
	git config user.email "[email protected]"
	git add -A
	timestamp=$(date -u)
	git commit -m "Update data: ${timestamp}" \|\| exit 0
	git push

Provide feedback