Merge pull request #1717 from dwisiswant0/headless/extract-urls

Add URL extractor from HTML attributes

headless/extract-urls.yaml

@@ -0,0 +1,24 @@
+id: extract-urls
+
+info:
+  name: Extract URLs from HTML attributes
+  author: dwisiswant0
+  severity: info
+  tags: headless,extractor
+
+headless:
+  - steps:
+      - args:
+          url: "{{BaseURL}}"
+        action: navigate
+      - action: waitload
+      - action: script
+        name: extract
+        args:
+          code: |
+            '\n' + [...new Set(Array.from(document.querySelectorAll('[src], [href], [url], [action]')).map(i => i.src || i.href || i.url || i.action))].join('\r\n') + '\n'
+    extractors:
+      - type: kval
+        part: extract
+        kval:
+          - extract