docs: update examples for v2 API

- Remove old v1 examples (smartscraper, markdownify, searchscraper, sitemap, agenticscraper)
- Add scrape examples (basic, multi-format, pdf, fetchConfig)
- Add extract examples (basic, with-schema)
- Add search examples (basic, with-extraction)
- Add monitor examples (basic, with-webhook)
- Update crawl examples for namespace API
- Update schema examples for camelCase fields
- Update utilities for v2 response shapes

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Author: FrancescoSaverioZuppichini

examples/agenticscraper/agenticscraper_ai_extraction.ts

@@ -2,22 +2,20 @@ import { crawl } from "scrapegraph-js";
 
 const apiKey = process.env.SGAI_API_KEY!;
 
-const res = await crawl(
-	apiKey,
-	{
-		url: "https://scrapegraphai.com",
-		prompt: "Extract the main content from each page",
-		max_pages: 5,
-		depth: 2,
-		sitemap: true,
-	},
-	(status) => console.log(`Poll: ${status}`),
-);
+const startRes = await crawl.start(apiKey, {
+	url: "https://example.com",
+	maxPages: 5,
+	maxDepth: 2,
+});
 
-if (res.status === "success") {
-	console.log("Pages crawled:", res.data?.crawled_urls?.length);
-	console.log("Result:", JSON.stringify(res.data?.llm_result, null, 2));
-	console.log(`Took ${res.elapsedMs}ms`);
-} else {
-	console.error("Failed:", res.error);
+if (startRes.status !== "success") {
+	console.error("Failed to start:", startRes.error);
+	process.exit(1);
 }
+
+console.log("Crawl started:", startRes.data?.id);
+console.log("Status:", startRes.data?.status);
+
+const getRes = await crawl.get(apiKey, startRes.data!.id);
+console.log("\nProgress:", getRes.data?.finished, "/", getRes.data?.total);
+console.log("Pages:", getRes.data?.pages.map((p) => p.url));

examples/agenticscraper/agenticscraper_basic.ts

@@ -0,0 +1,23 @@
+import { crawl } from "scrapegraph-js";
+
+const apiKey = process.env.SGAI_API_KEY!;
+
+const res = await crawl.start(apiKey, {
+	url: "https://example.com",
+	formats: [
+		{ type: "markdown", mode: "reader" },
+		{ type: "screenshot", width: 1280, height: 720 },
+	],
+	maxPages: 10,
+	maxDepth: 2,
+	includePatterns: ["/blog/*", "/docs/*"],
+	excludePatterns: ["/admin/*"],
+});
+
+if (res.status === "success") {
+	console.log("Crawl ID:", res.data?.id);
+	console.log("Status:", res.data?.status);
+	console.log("Total pages to crawl:", res.data?.total);
+} else {
+	console.error("Failed:", res.error);
+}

examples/crawl/crawl_basic.ts

@@ -0,0 +1,15 @@
+import { extract } from "scrapegraph-js";
+
+const apiKey = process.env.SGAI_API_KEY!;
+
+const res = await extract(apiKey, {
+	url: "https://example.com",
+	prompt: "What is this page about? Extract the main heading and description.",
+});
+
+if (res.status === "success") {
+	console.log("Extracted:", JSON.stringify(res.data?.json, null, 2));
+	console.log("\nTokens used:", res.data?.usage);
+} else {
+	console.error("Failed:", res.error);
+}

examples/crawl/crawl_markdown.ts

@@ -0,0 +1,22 @@
+import { extract } from "scrapegraph-js";
+
+const apiKey = process.env.SGAI_API_KEY!;
+
+const res = await extract(apiKey, {
+	url: "https://example.com",
+	prompt: "Extract the page title and description",
+	schema: {
+		type: "object",
+		properties: {
+			title: { type: "string" },
+			description: { type: "string" },
+		},
+		required: ["title"],
+	},
+});
+
+if (res.status === "success") {
+	console.log("Extracted:", JSON.stringify(res.data?.json, null, 2));
+} else {
+	console.error("Failed:", res.error);
+}