ogscrap 1.0.0

package/README.md

@@ -0,0 +1,47 @@
+# ogscrap
+
+Lightweight utility to fetch a web page and extract clean metadata.
+
+It returns a simple JSON object with:
+
+- `url`
+- `title`
+- `description`
+- `image`
+
+## Install
+
+```bash
+npm install
+```
+
+## Usage
+
+```ts
+import { fetchPageMetadata } from "./app/page-metadata";
+
+const data = await fetchPageMetadata("https://example.com/post");
+console.log(data);
+```
+
+Response shape:
+
+```json
+{
+  "url": "https://example.com/post",
+  "title": "Page title",
+  "description": "Short summary about the content",
+  "image": "https://example.com/image.jpg"
+}
+```
+
+## Local Example
+
+You can run the sample in `app/example.ts` (depending on your TS runtime setup):
+
+```ts
+import { fetchPageMetadata } from "./page-metadata";
+
+const data = await fetchPageMetadata("https://example.com/post");
+console.log(data);
+```

package/app/example.ts

@@ -0,0 +1,4 @@
+import { fetchPageMetadata } from "./page-metadata.js";
+const data = await fetchPageMetadata("https://medium.com/@pshubham/using-react-with-cordova-f235de698cc3");
+console.log(data);
+//https://fr.wikipedia.org/wiki/Ski_acrobatique_aux_Jeux_olympiques_de_2026

package/app/page-metadata.ts

@@ -0,0 +1,127 @@
+import * as cheerio from "cheerio";
+import createDOMPurify from "dompurify";
+import { JSDOM } from "jsdom";
+
+export type PageMetadata = {
+  url: string;
+  title: string;
+  description: string;
+  image: string;
+};
+
+const purifyWindow = new JSDOM("").window;
+const DOMPurify = createDOMPurify(purifyWindow as typeof purifyWindow);
+
+function cleanText(value: string | undefined): string {
+  return (value ?? "").replace(/\s+/g, " ").trim();
+}
+
+function sanitizePlainText(value: string | undefined): string {
+  const sanitized = DOMPurify.sanitize(value ?? "", {
+    ALLOWED_TAGS: [],
+    ALLOWED_ATTR: [],
+  });
+  return cleanText(sanitized);
+}
+
+function firstNonEmpty(values: Array<string | undefined>): string {
+  for (const value of values) {
+    const cleaned = sanitizePlainText(value);
+    if (cleaned) return cleaned;
+  }
+  return "";
+}
+
+function toAbsoluteUrl(baseUrl: string, maybeUrl: string | undefined): string {
+  const value = sanitizePlainText(maybeUrl);
+  if (!value) return "";
+  try {
+    return new URL(value, baseUrl).toString();
+  } catch {
+    return "";
+  }
+}
+
+function getMainText($: cheerio.CheerioAPI): string {
+  const candidates = [
+    $("main article").first().text(),
+    $("article").first().text(),
+    $("main").first().text(),
+  ];
+  return sanitizePlainText(candidates.find((v) => sanitizePlainText(v)));
+}
+
+function getMainImage($: cheerio.CheerioAPI, url: string): string {
+  const imageSrc = firstNonEmpty([
+    $("main article img").first().attr("src"),
+    $("article img").first().attr("src"),
+    $("main img").first().attr("src"),
+    $("img").first().attr("src"),
+  ]);
+  return toAbsoluteUrl(url, imageSrc);
+}
+
+function getTitle($: cheerio.CheerioAPI): string {
+  return firstNonEmpty([
+    $('meta[name="title"]').attr("content"),
+    $('meta[name="twitter:title"]').attr("content"),
+    $('meta[property="og:title"]').attr("content"),
+    $("title").first().text(),
+    $("h1").first().text(),
+  ]);
+}
+
+function getDescription($: cheerio.CheerioAPI): string {
+  return firstNonEmpty([
+    $('meta[name="description"]').attr("content"),
+    $('meta[name="twitter:description"]').attr("content"),
+    $('meta[property="og:description"]').attr("content"),
+    $("meta[name='description']").first().attr("content"),
+    $("meta[name='twitter:description']").first().attr("content"),
+    $("meta[property='og:description']").first().attr("content"),
+    $("p").first().text(),
+  ]);
+}
+
+function getImage($: cheerio.CheerioAPI, url: string): string {
+  const metaImage = firstNonEmpty([
+    $('meta[name="image"]').attr("content"),
+    $('meta[property="og:image"]').attr("content"),
+    $('meta[name="twitter:image"]').attr("content"),
+    $('link[rel="image_src"]').attr("href"),
+    $("img").first().attr("src"),
+    $('link[rel="apple-touch-icon"]').attr("href"),
+    $('link[rel="icon"]').attr("href"),
+  ]);
+  return toAbsoluteUrl(url, metaImage);
+}
+
+export async function fetchPageMetadata(url: string): Promise<PageMetadata> {
+  const response = await fetch(url, {
+    headers: {
+      "user-agent": "Mozilla/5.0 (compatible; page-metadata/1.0)",
+      accept: "text/html,application/xhtml+xml",
+      referrerPolicy: "no-referrer"
+    },
+  });
+
+  if (!response.ok) {
+    throw new Error(`Failed to fetch ${url}: ${response.status} ${response.statusText}`);
+  }
+
+  const html = await response.text();
+  const $ = cheerio.load(html);
+
+  const title = getTitle($);
+  const descriptionFromMeta = getDescription($);
+  const mainText = getMainText($);
+  const description = sanitizePlainText(descriptionFromMeta || mainText.slice(0, 300));
+  const image = getImage($, url) || getMainImage($, url);
+
+  return {
+    url: toAbsoluteUrl(url, url),
+    title: sanitizePlainText(title),
+    description,
+    image: sanitizePlainText(image),
+  };
+}

package/package.json

@@ -0,0 +1,21 @@
+{
+  "name": "ogscrap",
+  "version": "1.0.0",
+  "description": "Lightweight utility to fetch a web page and extract clean metadata.",
+  "main": "./dist/index.js",
+  "scripts": {
+    "build" : "tsc"
+  },
+  "keywords": ["metadata" , "ogscrap", "page-metadata", "scraper"],
+  "author": "edah",
+  "license": "MIT",
+  "type": "module",
+  "dependencies": {
+    "cheerio": "^1.2.0",
+    "dompurify": "^3.3.1",
+    "jsdom": "^28.1.0"
+  },
+  "devDependencies": {
+    "@types/jsdom": "^27.0.0"
+  }
+}

package/tsconfig.json

@@ -0,0 +1,51 @@
+{
+  // Visit https://aka.ms/tsconfig to read more about this file
+  "compilerOptions": {
+    // File Layout
+    "rootDir": "./app",
+    "outDir": "./dist",
+
+
+
+
+    // Environment Settings
+    // See also https://aka.ms/tsconfig/module
+    "module": "nodenext",
+    "target": "esnext",
+    "types": [],
+    // For nodejs:
+    // "lib": ["esnext"],
+    // "types": ["node"],
+    // and npm install -D @types/node
+
+    // Other Outputs
+    "sourceMap": false,
+    "declaration": true,
+    "declarationMap": false,
+
+    // Stricter Typechecking Options
+    "noUncheckedIndexedAccess": true,
+    "exactOptionalPropertyTypes": true,
+
+    // Style Options
+    // "noImplicitReturns": true,
+    // "noImplicitOverride": true,
+    // "noUnusedLocals": true,
+    // "noUnusedParameters": true,
+    // "noFallthroughCasesInSwitch": true,
+    // "noPropertyAccessFromIndexSignature": true,
+
+    // Recommended Options
+    "strict": true,
+    
+    "verbatimModuleSyntax": true,
+    "isolatedModules": true,
+    "noUncheckedSideEffectImports": true,
+    "moduleDetection": "force",
+    "skipLibCheck": true,
+  },
+      "exclude" : [
+      "node_modules",
+      "./app/example.ts"
+    ],
+}