Check for internal and external broken links #1
This file contains 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: Check for internal and external broken links | |
| on: | |
| workflow_dispatch: | |
| schedule: | |
| - cron: "0 12 * * *" | |
| jobs: | |
| check-broken-links: | |
| runs-on: ubuntu-latest | |
| timeout-minutes: 30 | |
| steps: | |
| - name: Setup node | |
| uses: actions/setup-node@v4 | |
| with: | |
| node-version: "lts/*" | |
| - name: Set Vercel URL output | |
| id: vercel | |
| run: | | |
| echo "url=https://docs.cloudquery.io" >> $GITHUB_OUTPUT | |
| - name: Check for broken links | |
| # We need to exclude some hosts that protect against bots | |
| run: | | |
| set -o pipefail | |
| npx broken-link-checker --requests 100 --host-requests 10 -f -r -v -o --filter-level 3 \ | |
| --exclude "${{ steps.vercel.outputs.url }}/logo" \ | |
| --exclude "${{ steps.vercel.outputs.url }}/docs/plugins/sources/*/tables" \ | |
| --exclude "${{ steps.vercel.outputs.url }}/integrations/*" \ | |
| --exclude "${{ steps.vercel.outputs.url }}/buy/*" \ | |
| --exclude "${{ steps.vercel.outputs.url }}/contact" \ | |
| --exclude "${{ steps.vercel.outputs.url }}/contact-policies" \ | |
| --exclude "${{ steps.vercel.outputs.url }}/register_for_cloud" \ | |
| --exclude "${{ steps.vercel.outputs.url }}/apply_for_job" \ | |
| --exclude "${{ steps.vercel.outputs.url }}/careers" \ | |
| --exclude "${{ steps.vercel.outputs.url }}/register-for-marketplace" \ | |
| --exclude "${{ steps.vercel.outputs.url }}/blog" \ | |
| --exclude "${{ steps.vercel.outputs.url }}/blog/*" \ | |
| --exclude "${{ steps.vercel.outputs.url }}/integrations" \ | |
| --exclude "${{ steps.vercel.outputs.url }}/integrations/*" \ | |
| --exclude linkedin \ | |
| --exclude cloudquery.io/discord \ | |
| --exclude cloudquery.io/buy \ | |
| --exclude fonts.gstatic.com \ | |
| --exclude fonts.googleapis.com \ | |
| --exclude github.com \ | |
| --exclude support.google.com \ | |
| --exclude work-bench.com \ | |
| --exclude api.typeform.com \ | |
| --exclude api.eu.typeform.com \ | |
| --exclude mailchimp.com \ | |
| --exclude returngis.net \ | |
| --exclude plausible.io \ | |
| --exclude localhost \ | |
| --exclude twitter.com \ | |
| --exclude mongodb.com \ | |
| --exclude regex101.com \ | |
| --exclude help.shopify.com/en/manual/apps/app-types/custom-apps \ | |
| --exclude hub.cloudquery.io \ | |
| --exclude www.g2.com \ | |
| --exclude cql.ink \ | |
| --exclude egghead.io \ | |
| ${{ steps.vercel.outputs.url }}/docs \ | |
| | grep -v '───OK───' | grep -v '──SKIP──' | grep -v '0 broken' | |
| - name: Slack Notify | |
| uses: ravsamhq/notify-slack-action@v2 # https://github.com/marketplace/actions/notify-slack-action | |
| if: always() | |
| with: | |
| status: ${{ job.status }} | |
| notify_when: 'failure' | |
| notification_title: 'Broken links detected :bang:' | |
| footer: '<{repo_url}|{repo}>' | |
| env: | |
| SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK }} |