Hybrid Template Extractor

Hybrid Template Extractor

This add-on can automatically extract the web template from the loaded webpage. For this, it uses a combination of analyses including a page-level analysis of content and a site-level analysis of hyperlinks.

Merlin
Additional files are visible only to premium users

manifest.json


{
  "manifest_version": 2,
  "name": "__MSG_extensionName__",
  "author": "Josep Silva",
  "description": "__MSG_extensionDescription__",
  "version": "1.2",
  "icons": {
    "24": "icons/t3.png"
  },
  "permissions": [
    "notifications",
    "activeTab",
    "tabs",
    "webRequest",
    "webRequestBlocking"
  ],
  "background": {
    "scripts": [
      "background-scripts/background.js"
    ]
  },
  "browser_action": {
    "default_icon": "icons/t3.png",
    "default_title": "__MSG_extensionDescription__"
  },
  "content_scripts": [
    {
      "matches": [
        "<all_urls>"
      ],
      "run_at": "document_idle",
      "all_frames": false,
      "js": [
        "content-scripts/createNamespaces.js",
        "content-scripts/HybEx/loader/PageLoader.js",
        "content-scripts/HybEx/util/Hashtable.js",
        "content-scripts/HybEx/util/TreeSearch.js",
        "content-scripts/HybEx/misc/Misc.js",
        "content-scripts/HybEx/site/Link.js",
        "content-scripts/HybEx/site/Webpage.js",
        "content-scripts/HybEx/site/Website.js",
        "content-scripts/HybEx/algorithm/HybEx/Config.js",
        "content-scripts/HybEx/algorithm/HybEx/HierarchyLinks.js",
        "content-scripts/HybEx/algorithm/HybEx/Map.js",
        "content-scripts/HybEx/algorithm/HybEx/HybEx.js",
        "content-scripts/HybEx/algorithm/HybEx/ConEx.js",
        "content-scripts/HybEx/algorithm/HybEx/Content.js",
        "content-scripts/HybEx/TemplateExtractor.js",
        "content-scripts/browserOverlay.js"
      ]
    }
  ],
  "default_locale": "en",
  "browser_specific_settings": {
    "gecko": {
      "id": "{b4fe534c-afd4-455f-8aa3-b28555039d22}"
    }
  }
}