Scrape MedPages Data #24
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Scrape MedPages Data | |
| on: | |
| # Run on manual trigger | |
| workflow_dispatch: | |
| # Run on schedule (every Sunday at 00:00 UTC) | |
| schedule: | |
| - cron: '0 0 * * 0' | |
| # Run on push to main branch | |
| push: | |
| branches: | |
| - main | |
| paths: | |
| - 'scrapeAll.py' | |
| - 'medpages_full_links.csv' | |
| - 'medpages_mental_health.csv' | |
| - '.github/workflows/scrape_medpages.yml' | |
| jobs: | |
| scrape: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: 📥 Checkout repository | |
| uses: actions/checkout@v4 | |
| with: | |
| token: ${{ secrets.GITHUB_TOKEN }} | |
| - name: 🐍 Set up Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: '3.10' | |
| cache: 'pip' | |
| - name: 📦 Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install -r requirements.txt | |
| - name: 🔍 Run scraper | |
| run: | | |
| python scrapeAll.py | |
| - name: 📊 Display results | |
| run: | | |
| if [ -f medpages_all_data.json ]; then | |
| echo "✅ Scraping completed successfully!" | |
| echo "File size: $(du -h medpages_all_data.json | cut -f1)" | |
| echo "Number of lines: $(wc -l < medpages_all_data.json)" | |
| else | |
| echo "❌ Output file not found!" | |
| exit 1 | |
| fi | |
| - name: 📤 Upload artifact | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: medpages-data-${{ github.run_number }} | |
| path: medpages_all_data.json | |
| retention-days: 90 | |
| - name: 🔄 Commit and push data back to repo | |
| run: | | |
| git config --local user.email "github-actions[bot]@users.noreply.github.com" | |
| git config --local user.name "github-actions[bot]" | |
| # Add the data file | |
| git add medpages_all_data.json | |
| # Check if there are changes to commit | |
| if git diff --staged --quiet; then | |
| echo "No changes to commit" | |
| else | |
| git commit -m "🤖 Update medpages data - $(date +'%Y-%m-%d %H:%M:%S UTC')" | |
| git push | |
| echo "✅ Data pushed back to repository" | |
| fi | |
| - name: 📈 Create summary | |
| if: always() | |
| run: | | |
| echo "## 📊 Scraping Summary" >> $GITHUB_STEP_SUMMARY | |
| echo "" >> $GITHUB_STEP_SUMMARY | |
| if [ -f medpages_all_data.json ]; then | |
| echo "✅ **Status:** Success" >> $GITHUB_STEP_SUMMARY | |
| echo "" >> $GITHUB_STEP_SUMMARY | |
| echo "- **File:** medpages_all_data.json" >> $GITHUB_STEP_SUMMARY | |
| echo "- **Size:** $(du -h medpages_all_data.json | cut -f1)" >> $GITHUB_STEP_SUMMARY | |
| echo "- **Run Number:** ${{ github.run_number }}" >> $GITHUB_STEP_SUMMARY | |
| echo "- **Timestamp:** $(date +'%Y-%m-%d %H:%M:%S UTC')" >> $GITHUB_STEP_SUMMARY | |
| echo "" >> $GITHUB_STEP_SUMMARY | |
| echo "🎉 Data has been uploaded as an artifact and committed to the repository!" >> $GITHUB_STEP_SUMMARY | |
| else | |
| echo "❌ **Status:** Failed" >> $GITHUB_STEP_SUMMARY | |
| echo "" >> $GITHUB_STEP_SUMMARY | |
| echo "The scraper did not produce an output file." >> $GITHUB_STEP_SUMMARY | |
| fi | |
| permissions: | |
| contents: write | |
| actions: read |