migrate

2026-07-20 09:23:17 -04:00
parent c1315882da
commit 72272e4006
3179 changed files with 562960 additions and 14 deletions
@@ -0,0 +1,110 @@
+{
+  "slug": "broken-link-crawler",
+  "kind": "python",
+  "metadata": {
+    "name": "Broken Link Crawler",
+    "description": "Standalone Python crawler for one website that walks same-host pages, checks discovered links and assets, and prints a stdout summary.",
+    "tags": [
+      "crawler",
+      "links",
+      "website",
+      "audit",
+      "python"
+    ],
+    "icon": {
+      "provider": "simple-icons",
+      "id": "python",
+      "color": "emerald"
+    },
+    "draft": false,
+    "version": {
+      "name": "1.0.0",
+      "source_dep_name": "manual/broken-link-crawler"
+    }
+  },
+  "variables": [
+    {
+      "title": "Targets",
+      "name": "targets",
+      "items": [
+        {
+          "name": "website_url",
+          "type": "str",
+          "title": "Website URL",
+          "required": true,
+          "default": "https://example.com",
+          "description": "Single crawl entrypoint. The crawler stays on this exact host.",
+          "config": {
+            "placeholder": "https://example.com"
+          }
+        }
+      ]
+    },
+    {
+      "title": "Crawler",
+      "name": "crawler",
+      "items": [
+        {
+          "name": "max_pages",
+          "type": "int",
+          "title": "Max Pages",
+          "required": true,
+          "default": 100,
+          "description": "Maximum number of HTML pages to crawl.",
+          "config": {
+            "placeholder": "100"
+          }
+        },
+        {
+          "name": "request_timeout_seconds",
+          "type": "int",
+          "title": "Timeout Seconds",
+          "required": true,
+          "default": 10,
+          "description": "Timeout for each outbound HTTP request.",
+          "config": {
+            "placeholder": "10"
+          }
+        },
+        {
+          "name": "verify_tls",
+          "type": "bool",
+          "title": "Verify TLS",
+          "required": false,
+          "default": true,
+          "description": "Validate remote TLS certificates during requests."
+        },
+        {
+          "name": "follow_redirects",
+          "type": "bool",
+          "title": "Follow Redirects",
+          "required": false,
+          "default": true,
+          "description": "Follow redirects when checking URLs."
+        },
+        {
+          "name": "request_headers_json",
+          "type": "str",
+          "title": "Request Headers JSON",
+          "required": false,
+          "default": "{}",
+          "description": "JSON object of headers added to every request.",
+          "config": {
+            "placeholder": "{\"Authorization\": \"Bearer replace-me\"}"
+          }
+        },
+        {
+          "name": "user_agent",
+          "type": "str",
+          "title": "User Agent",
+          "required": false,
+          "default": "boilerplates-broken-link-crawler/1.0",
+          "description": "User-Agent header value used by the crawler.",
+          "config": {
+            "placeholder": "boilerplates-broken-link-crawler/1.0"
+          }
+        }
+      ]
+    }
+  ]
+}