schedule.yml

name: confluence-scraper

env:
  CONFLUENCE_USER_NAME: ${{ secrets.CONFLUENCE_USER_NAME }}
  CONFLUENCE_TOKEN: ${{ secrets.CONFLUENCE_TOKEN }}
  BASE_URL: ${{ secrets.CONFLUENCE_URL }}
  PAGES: "120392107,115081594,163422029,160074735,171770103"

on:
  workflow_dispatch:
  schedule:
    # * is a special character in YAML, so you have to quote this string
    - cron:  '0 0 * * *'

jobs:
  crud-confluenc:
    name: Get and update contents from confluence
    runs-on: ubuntu-24.04
    defaults:
      run:
        working-directory: confluence-scraper
    steps:
      - name: Check out repository
        uses: actions/checkout@v4

      - name: Add Node.js
        uses: actions/setup-node@v4
        with:
          node-version: 20
          cache: npm
          cache-dependency-path: confluence-scraper/package-lock.json

      - name: Install Dependencies
        run: npm ci

      - name: process script
        id: confluence_script
        run: |
          node index.js

      - name: Commit files  # transfer the new html files back into the repository
        if: steps.confluence_script.outputs.updated == 'true'
        id: commit_push_pr
        run: |
          git config --global user.email "omprakashmishra3978@example.com"
          git config --global user.name "Omprakash Mishra"
          git checkout -b update/confluence-content
          git add ../patterns
          git commit -m "Adding or updating the confluence pages" || echo "No changes to commit"
          git push origin update/confluence-content
          gh pr create --assignee "mishraomp" --base main --title "Updated content from confluence." --body "Updated content from confluence."
        env:
          GH_TOKEN: ${{ secrets.PAT_GHA }}