Regularly scheduled check links #291
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
# This is called after the deployed environment is ready to be checked | |
name: Regularly scheduled check links | |
on: | |
schedule: | |
- cron: "0 2 * * 1,4" | |
workflow_dispatch: | |
inputs: | |
url: | |
description: 'Site to check for broken links' | |
required: true | |
type: string | |
default: 'https://docs.platform.sh/' | |
jobs: | |
check-links: | |
name: Check links | |
runs-on: ubuntu-latest | |
steps: | |
- uses: actions/setup-python@v4 | |
with: | |
python-version: '3.10' | |
- name: install linkchecker | |
id: install-linkchecker | |
run: | | |
pip3 install linkchecker | |
- name: checkout xml to markdown | |
uses: actions/checkout@v3 | |
with: | |
repository: platformsh/linkchecker-xml2md | |
- name: install-parser | |
run: | | |
pip3 install -r requirements.txt | |
- name: Set URL to scan | |
id: set-url | |
shell: bash | |
run: | | |
# If this is a workflow dispatch, then use what was entered. | |
# If not, then use the repository variable SCAN_URL if it is set | |
# if not, fall back to the hard-coded default | |
scanURL="https://docs.platform.sh/" | |
if [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then | |
scanURL="${{ inputs.url }}" | |
elif [[ -n "${{ vars.SCAN_URL }}" ]]; then | |
scanURL="${{ vars.SCAN_URL }}" | |
fi | |
echo "scanURL=${scanURL}" >> "$GITHUB_ENV" | |
- name: Run linkchecker | |
id: run-link-checker | |
continue-on-error: true | |
shell: bash | |
run: | | |
echo "::notice::Scanning ${{ inputs.url }} for broken links." | |
# if linkchecker exits with a non-zero then it means broken links were found. | |
scan=$(linkchecker ${{ env.scanURL }} -F xml/utf_8/brokenlinks.xml --check-extern --user-agent "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36" --ignore-url="^https://github.com/platformsh*" --ignore-url="console.platform.sh/projects/*" --ignore-url="support.blackfire.io/*" --ignore-url="cloud.orange-business.com/*" --ignore-url="developers.cloudflare.com/*" --ignore-url="discord.com/*" --ignore-url="pptr.dev/*" --ignore-url="mvnrepository.com/*" --ignore-url="https://dev.mysql.com/doc/refman/en/" --ignore-url="https://www.microsoft.com/en-us/trust-center/privacy/data-management") | |
result=$? | |
if [[ $result -ne 0 ]]; then | |
echo "::notice::Broken links detected." | |
fi | |
- name: Convert xml to markdown | |
if: ${{ steps.run-link-checker.outcome == 'failure' }} | |
run: | | |
./xml2md.py brokenlinks.xml > broken_links.md | |
- name: Report no broken links | |
if: ${{ steps.run-link-checker.outcome == 'success' }} | |
run: | | |
echo "::notice::No broken links were detected" | |
- name: Create issue from Markdown file | |
id: create-issue | |
if: ${{ steps.run-link-checker.outcome == 'failure' }} | |
uses: actions/github-script@v6 | |
with: | |
script: | | |
var fs = require('fs'); | |
var bodyMsg = fs.readFileSync('broken_links.md','utf8'); | |
failMsg = ':bug: Broken links detected' | |
github.rest.issues.create({ | |
owner: context.repo.owner, | |
repo: context.repo.repo, | |
title: failMsg, | |
body: bodyMsg, | |
labels: ['broken-links'], | |
}) |