feat(sitemap): add sitemap crawl option (#40)

Author: j-mendez

.github/workflows/action.yml

@@ -13,6 +13,7 @@ jobs:
           FAIL_TOTAL_COUNT: 10000
           EXTERNAL: false
           SITE_WIDE: true
+          SITEMAP: true
           SUBDOMAINS: true
           TLD: true
           LIST: true

.github/workflows/bench-axe.yml

@@ -9,14 +9,15 @@ Some of the primary features include pass/fail testing, code fixes, and detailed
 ### Usage
 
 ```yaml
-- uses: a11ywatch/github-action@v1.12.3
+- uses: a11ywatch/github-action@v1.13.0
   with:
     WEBSITE_URL: ${{ secrets.WEBSITE_URL }}
     SUBDOMAINS: true
-    TLD: true
+    TLD: false
+    SITEMAP: true
     FAIL_ERRORS_COUNT: 15
     LIST: true
-    FIX: true
+    FIX: false
     UPGRADE: false
     COMPUTER_VISION_SUBSCRIPTION_KEY: ${{ secrets.COMPUTER_VISION_SUBSCRIPTION_KEY }}
     COMPUTER_VISION_ENDPOINT: ${{ secrets.COMPUTER_VISION_SUBSCRIPTION_KEY }}
@@ -32,6 +33,7 @@ All inputs are **optional** except $WEBSITE_URL.
 | `SITE_WIDE`                        | Site-wide scanning across all pages.                                                                                                                                                                                     | false          |
 | `FIX`                              | Attempt to apply recommendations to code and commit to github.                                                                                                                                                           | false          |
 | `SUBDOMAINS`                       | Include all subdomains (required SITE_WIDE=true).                                                                                                                                                                        | true           |
+| `SITEMAP`                          | Extend crawl with sitemap links (required SITE_WIDE=true).                                                                                                                                                               | true           |
 | `TLD`                              | Include all tld extensions (required SITE_WIDE=true).                                                                                                                                                                    | true           |
 | `LIST`                             | Report the results to github as a pass or fail list or detailed report.                                                                                                                                                  | false          |
 | `FAIL_TOTAL_COUNT`                 | Determine whether to fail the CI if total issues warnings and errors exceed the counter. Takes precedence over the other FAIL inputs.                                                                                    | 0              |
@@ -103,8 +105,6 @@ On a larger website A11yWatch action runs over 60x-10,000x+ faster depending on
 
 When `AI_DISABLED` is set to true the run for `A11yWatch` may increase.
 
-Pa11y-CI could not finish the crawl as it exceeds the github action free limits at 6 hours. It handled around 1000 pages before failing at the 6 hour mark.
-
 ## Common Issues
 
 If you experience issues on your CI you may have to toggle the `UPGRADE` input to true in order to get the latest docker images.

.github/workflows/bench-pa11y.yml

@@ -25,6 +25,10 @@ inputs:
     description: Perform a site-wide scan.
     required: false
     default: false
+  SITEMAP:
+    description: Extend crawl with sitemap links.
+    required: false
+    default: false
   SUBDOMAINS:
     description: Include all subdomains.
     required: false
@@ -170,12 +174,12 @@ runs:
     - name: A11yWatch Crawl [Local]
       if: ${{ inputs.EXTERNAL == 'false' && inputs.SITE_WIDE == 'true' }}
       shell: bash
-      run: a11ywatch crawl --url ${{ inputs.WEBSITE_URL }} ${{ inputs.SUBDOMAINS == 'true' && '--subdomains' || '' }} ${{ inputs.TLD == 'true' && '--tld' || ''}} --save ${{ inputs.FIX == 'true' && '--fix' || '' }}
+      run: a11ywatch crawl --url ${{ inputs.WEBSITE_URL }} ${{ inputs.SUBDOMAINS == 'true' && '--subdomains' || '' }} ${{ inputs.TLD == 'true' && '--tld' || ''}} ${{ inputs.SITEMAP == 'true' && '--sitemap' || '' }} --save ${{ inputs.FIX == 'true' && '--fix' || '' }}
 
     - name: A11yWatch Crawl [External]
       if: ${{ inputs.EXTERNAL == 'true' && inputs.SITE_WIDE == 'true' }}
       shell: bash
-      run: a11ywatch crawl --url ${{ inputs.WEBSITE_URL }} ${{ inputs.SUBDOMAINS == 'true' && '--subdomains' || '' }} ${{ inputs.TLD == 'true' && '--tld' || ''}} --external --save ${{ inputs.FIX == 'true' && '--fix' || '' }}
+      run: a11ywatch crawl --url ${{ inputs.WEBSITE_URL }} ${{ inputs.SUBDOMAINS == 'true' && '--subdomains' || '' }} ${{ inputs.TLD == 'true' && '--tld' || ''}} ${{ inputs.SITEMAP == 'true' && '--sitemap' || '' }} --external --save ${{ inputs.FIX == 'true' && '--fix' || '' }}
 
     - name: Scan Results Check
       id: a11ywatch-results-generator