Skip to content

commit

commit #32

Workflow file for this run

name: Run Scraper Daily
on:
push:
branches:
- scraper-tecq
schedule:
- cron: "*/5 * * * *" # Runs every 5 minutes
workflow_dispatch: # Allows manual workflow trigger
jobs:
run-scraper:
runs-on: ubuntu-latest
steps:
- name: Check out repository
uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: '3.13'
- name: Install Google Chrome
run: |
sudo apt-get update
sudo apt-get install -y google-chrome-stable
- name: Verify Chrome Installation
run: |
which google-chrome
google-chrome --version
- name: Install ChromeDriver
run: |
sudo apt-get install -y chromium-chromedriver
sudo ln -s /usr/lib/chromium-browser/chromedriver /usr/local/bin/chromedriver
- name: Export Chrome Binary Path
run: |
echo "CHROME_BIN=$(which google-chrome)" >> $GITHUB_ENV
- name: Install Python Dependencies
run: |
python -m pip install --upgrade pip
pip install -r requirements.txt
- name: Run Scraper
env:
CHROME_BIN: ${{ env.CHROME_BIN }}
run: |
python main.py
- name: Save Excel Output
run: |
timestamp=$(date +"%Y-%m-%d_%H-%M-%S")
mv output.xlsx "output_$timestamp.xlsx"
mv "output_$timestamp.xlsx" results/
- name: Commit and Push the Excel File
run: |
git config --local user.email "[email protected]"
git config --local user.name "GitHub Actions"
git add results/output_*.xlsx
git commit -m "Add data for $timestamp"
git push --force
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}