root: project

.gitignore

+# Based on https://raw.githubusercontent.com/github/gitignore/main/Node.gitignore
+
+# Logs
+
+logs
+_.log
+npm-debug.log_
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-debug.log*
+
+# Caches
+
+.cache
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+
+report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
+
+# Runtime data
+
+pids
+_.pid
+_.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+
+lib-cov
+
+# Coverage directory used by tools like istanbul
+
+coverage
+*.lcov
+
+# nyc test coverage
+
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+
+bower_components
+
+# node-waf configuration
+
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+
+build/Release
+
+# Dependency directories
+
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+
+web_modules/
+
+# TypeScript cache
+
+*.tsbuildinfo
+
+# Optional npm cache directory
+
+.npm
+
+# Optional eslint cache
+
+.eslintcache
+
+# Optional stylelint cache
+
+.stylelintcache
+
+# Microbundle cache
+
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+
+.node_repl_history
+
+# Output of 'npm pack'
+
+*.tgz
+
+# Yarn Integrity file
+
+.yarn-integrity
+
+# dotenv environment variable files
+
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+
+.parcel-cache
+
+# Next.js build output
+
+.next
+out
+
+# Nuxt.js build / generate output
+
+.nuxt
+dist
+
+# Gatsby files
+
+# Comment in the public line in if your project uses Gatsby and not Next.js
+
+# https://nextjs.org/blog/next-9-1#public-directory-support
+
+# public
+
+# vuepress build output
+
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+
+.temp
+
+# Docusaurus cache and generated files
+
+.docusaurus
+
+# Serverless directories
+
+.serverless/
+
+# FuseBox cache
+
+.fusebox/
+
+# DynamoDB Local files
+
+.dynamodb/
+
+# TernJS port file
+
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+
+.vscode-test
+
+# yarn v2
+
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.*
+
+# IntelliJ based IDEs
+.idea
+
+# Finder (MacOS) folder config
+.DS_Store

README.md

+# falcon
+
+To install dependencies:
+
+```bash
+bun install
+```
+
+To run:
+
+```bash
+bun run index.ts
+```
+
+This project was created using `bun init` in bun v1.1.18. [Bun](https://bun.sh) is a fast all-in-one JavaScript runtime.

package.json

+{
+  "name": "falcon",
+  "module": "index.ts",
+  "type": "module",
+  "devDependencies": {
+    "@types/bun": "latest"
+  },
+  "peerDependencies": {
+    "typescript": "^5.0.0"
+  },
+  "dependencies": {
+    "jsdom": "^26.1.0"
+  }
+}
\ No newline at end of file

src/clients/bobcat/SiteInfo.ts

+import { JSDOM } from 'jsdom';
+
+
+export const HOST = process.env.BOBCAT_HOST!;
+
+const cookie = process.env.BOBCAT_USER_COOKIE!;
+
+const getContentUrl = (siteId: string) => `${HOST}/s/admin/sites/${siteId}/content`
+
+
+export const fetchSiteData = async (siteId: string) => {
+
+  const url = getContentUrl(siteId)
+  const content = await fetch(url, {
+    "headers": {
+      "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+      "accept-language": "en-US,en;q=0.9",
+      "cache-control": "no-cache",
+      "pragma": "no-cache",
+      "priority": "u=0, i",
+      "sec-ch-ua": "\"Chromium\";v=\"131\", \"Not_A Brand\";v=\"24\"",
+      "sec-ch-ua-mobile": "?0",
+      "sec-ch-ua-platform": "\"macOS\"",
+      "sec-fetch-dest": "document",
+      "sec-fetch-mode": "navigate",
+      "sec-fetch-site": "same-origin",
+      "sec-fetch-user": "?1",
+      "upgrade-insecure-requests": "1",
+      "cookie": cookie,
+      "Referer": url,
+      "referrerPolicy": "strict-origin-when-cross-origin",
+    },
+    "body": null,
+    "method": "GET"
+  }).then(res => res.text()).then(htmlString => {
+    const dom = new JSDOM(htmlString);
+    const document = dom.window.document;
+
+    const element: any = document.getElementById('site_data_content');
+
+
+    const formUrl = document.querySelector('form.edit_site_data').action
+    const elementContent = element.value || element.textContent || '{}'
+
+    const content = JSON.parse(elementContent)
+
+
+    return {
+      content,
+      formUrl,
+    }
+  })
+
+  return content
+}
+
+

src/constant/section_selectors.ts

+export const section_selectors = [
+    "27328697",
+    "27328389",
+    "27328392",
+    "27328396",
+    "27328399",
+    "27328401",
+    "27328404",
+    "27328406",
+    "27328408",
+    "27328410",
+    "27328412",
+    "27328414",
+    "27328415",
+    "27328416",
+    "27328417",
+    "27328419",
+    "27665235",
+    "27656391"
+]
+
+export const ai_section_selectors = [
+    "29279960",
+    "29286540",
+    "29286613",
+    "29286646",
+    "29278357",
+    "29286780",
+    "29278350",
+    "29286835",
+    "29286857",
+    "29279949",
+    "29278331",
+    "29278319",
+    "29278287",
+    "29278284",
+    "29278371",
+    "29279914",
+    "29278297",
+    "29279930"
+]
\ No newline at end of file

src/detect_section_selector_masters/index.ts

+import { fetchSiteData } from '../clients/bobcat/SiteInfo'
+import {
+    section_selectors,
+    ai_section_selectors
+} from '../constant/section_selectors'
+
+
+// demo
+
+// await Promise.all(
+//     section_selectors.map(async (siteId, index) => {
+//         const jsonData = await fetchSiteData(siteId);
+//         // jsonData.content is page data under this site
+//         return jsonData.content;
+//     })
+// )
\ No newline at end of file

tsconfig.json

+{
+  "compilerOptions": {
+    // Enable latest features
+    "lib": ["ESNext", "DOM"],
+    "target": "ESNext",
+    "module": "ESNext",
+    "moduleDetection": "force",
+    "jsx": "react-jsx",
+    "allowJs": true,
+
+    // Bundler mode
+    "moduleResolution": "bundler",
+    "allowImportingTsExtensions": true,
+    "verbatimModuleSyntax": true,
+    "noEmit": true,
+
+    // Best practices
+    "strict": true,
+    "skipLibCheck": true,
+    "noFallthroughCasesInSwitch": true,
+
+    // Some stricter flags (disabled by default)
+    "noUnusedLocals": false,
+    "noUnusedParameters": false,
+    "noPropertyAccessFromIndexSignature": false
+  }
+}