Skip to content

scrape-ph-auto

scrape-ph-auto #5058

# This is a basic workflow to help you get started with Actions
name: scrape-ph-auto
# Controls when the workflow will run
on:
schedule:
- cron: 46 20 * * * # runs at 02:46 UTC (10:46 PHT) for Regular Menu
- cron: 26 16 * * * # runs at 22:26 UTC (06:26 PHT) for Breakfast Menu
concurrency:
group: scrape-and-schedule
cancel-in-progress: false
# A workflow run is made up of one or more jobs that can run sequentially or in parallel
jobs:
# This workflow contains a single job called "build"
build:
# The type of runner that the job will run on
runs-on: ubuntu-latest
# Steps represent a sequence of tasks that will be executed as part of the job
steps:
- name: checkout repo content
uses: actions/checkout@v3 # checkout the repository content to github runner.
- name: setup python
uses: actions/setup-python@v5
with:
python-version: '3.12'
- name: setup dependencies
working-directory: ./mcd-scr-ph
run: |
pip3 install scrapy==2.11.2
pip3 install pandas
pip3 install pytz
pip3 install path
pip3 install pathlib2
pip3 install pyopenssl==22.0.0
pip3 install cryptography==37.0.4 --ignore-installed
- name: execute py script # run mcd-scr-ph.py to get the latest data
working-directory: ./mcd-scr-ph
run: |
scrapy crawl mcd-scr-ph
- name: Commit and push if it changed
run: |
git config user.name "${GITHUB_ACTOR}"
git config user.email "${GITHUB_ACTOR}@users.noreply.github.com"
git add -A
timestamp=$(date -u)
git commit -m "Scraped: [${timestamp}] mcd-scr-ph (auto)"
git push "https://${GITHUB_ACTOR}:${TOKEN}@github.com/${GITHUB_REPOSITORY}.git" HEAD:main || exit 0