link check

Author: markzegarelli

.github/workflows/check-links.yml

@@ -17,29 +17,29 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
-    # steps:
-    #   - uses: actions/checkout@v2
-    #   - name: Ruby
-    #     uses: ruby/setup-ruby@v1
-    #     with:
-    #       ruby-version: 2.6 # Not needed with a .ruby-version file
-    #       bundler-cache: true # runs 'bundle install' and caches installed gems automatically
-    #   - name: Yarn install
-    #     run: yarn install
-    #   - name: Build jekyll website with
-    #     run: bundle exec jekyll build
-    #   - name: Check for broken links
-    #     run: |
-    #       yarn run hyperlink ./_site/index.html --canonicalroot https://segment.com/docs -i -r --skip 0.0.0.0 | yarn run tap-spot > output.md
-    #     continue-on-error: true
-    #   - name: Archive log links
-    #     uses: actions/upload-artifact@v1
-    #     with:
-    #       name: links-check.log
-    #       path: output.md
-    #   - name: Create Issue From File
-    #     uses: peter-evans/create-issue-from-file@v2
-    #     with:
-    #       title: Link Checker Report
-    #       content-filepath: output.md
-    #       labels: report, automated issue
+    steps:
+      - uses: actions/checkout@v2
+      - name: Ruby
+        uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: 2.6 # Not needed with a .ruby-version file
+          bundler-cache: true # runs 'bundle install' and caches installed gems automatically
+      - name: Yarn install
+        run: yarn install
+      - name: Build jekyll website with
+        run: bundle exec jekyll build
+      - name: Link Checker
+        uses: lycheeverse/[email protected]
+        with:
+          args: --verbose --no-progress **/*.html -a 429 -c ./lychee.toml -o lychee-out.txt
+        env:
+          GITHUB_TOKEN: ${{secrets.GITHUB_TOKEN}}
+      - name: "exclude non-400 errors"
+        run: |
+          cat ./lychee/out.md | grep -v "error sending request" > ./lychee/out.md
+      - name: Create Issue From File
+        uses: peter-evans/create-issue-from-file@v3
+        with:
+          title: Link Checker Report
+          content-filepath: ./lychee/out.md
+          labels: report, automated issue

lychee.toml

@@ -26,7 +26,7 @@ max_redirects = 10
 user_agent = "lychee/0.8.0"
 
 # Website timeout from connect to response finished
-timeout = 20
+timeout = 30
 
 # Comma-separated list of accepted status codes for valid links.
 # Omit to accept all response types.
@@ -50,7 +50,7 @@ headers = []
 ### Exclusions
 ###
 # Exclude URLs from checking (supports regex)
-exclude = ['https://ajs.cd.segment.com/analytics.js/v1/','http://0.0.0.0:4000','https://api.segment.io/v1/', 'https://segment.com/docs/assets/docs.bundle.js']
+exclude = ['https://ajs.cd.segment.com/analytics.js/v1/','http://0.0.0.0:4000','https://api.segment.io/v1/', 'https://segment.com/docs/assets/docs.bundle.js','https://www.linkedin.com', 'https://segment.com/jobs/', 'https://segment.com/press/', 'https://github.com/segmentio', 'https://unpkg.com/@segment/[email protected]/standalone/consent-manager.js', '(segment.com)', '(segmentapis.com)', '(example.com)', '(schema.org)']
 
 # Exclude URLs contained in a file from checking
 exclude_file = []