feat: align CLI with scrapegraph-js v2 c5bf757

- Bump scrapegraph-js pin b570a57 → c5bf757
- scrape: support 8 formats (markdown, html, screenshot, branding,
  links, images, summary, json), multi-format via comma-separated -f,
  add --html-mode, --scrolls, --prompt/--schema for json format
- search: add --location-geo-code, --time-range, --format
- crawl: add --format flag
- README: document new flags and formats

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: VinciGit00

README.md

@@ -132,10 +132,13 @@ Search the web and extract structured data from results (replaces `search-scrape
 ### Usage
 
 ```bash
-just-scrape search <query>                            # AI-powered web search
-just-scrape search <query> --num-results <n>          # Sources to scrape (1-20, default 3)
-just-scrape search <query> -p <prompt>                # Extraction prompt for results
-just-scrape search <query> --schema <json>            # Enforce output schema
+just-scrape search <query>                                    # AI-powered web search
+just-scrape search <query> --num-results <n>                  # Sources to scrape (1-20, default 3)
+just-scrape search <query> -p <prompt>                        # Extraction prompt for results
+just-scrape search <query> --schema <json>                    # Enforce output schema
+just-scrape search <query> --location-geo-code <code>         # Geo-target search (e.g. 'us', 'de', 'jp-tk')
+just-scrape search <query> --time-range <range>               # past_hour | past_24_hours | past_week | past_month | past_year
+just-scrape search <query> --format <markdown|html>           # Result format (default markdown)
 just-scrape search <query> --headers <json>
 ```
 
@@ -145,40 +148,53 @@ just-scrape search <query> --headers <json>
 # Research a topic across multiple sources
 just-scrape search "What are the best Python web frameworks in 2025?" --num-results 10
 
+# Recent news only, scoped to Germany
+just-scrape search "EU AI act latest news" --time-range past_week --location-geo-code de
+
 # Structured output with schema
 just-scrape search "Top 5 cloud providers pricing" \
   --schema '{"type":"object","properties":{"providers":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"free_tier":{"type":"string"}}}}}}'
 ```
 
 ## Scrape
 
-Scrape content from a URL in various formats: markdown (default), html, screenshot, or branding. [docs](https://docs.scrapegraphai.com/api-reference/scrape)
+Scrape content from a URL in one or more formats. The v2 API supports **8 formats**: `markdown`, `html`, `screenshot`, `branding`, `links`, `images`, `summary`, `json`. [docs](https://docs.scrapegraphai.com/api-reference/scrape)
 
 ### Usage
 
 ```bash
-just-scrape scrape <url>                               # Markdown (default)
-just-scrape scrape <url> -f html                       # Raw HTML
-just-scrape scrape <url> -f screenshot                 # Screenshot
-just-scrape scrape <url> -f branding                   # Extract branding info
-just-scrape scrape <url> -m direct+stealth             # Anti-bot bypass
-just-scrape scrape <url> --country <iso>               # Geo-targeting
+just-scrape scrape <url>                                  # Markdown (default)
+just-scrape scrape <url> -f html                          # Raw HTML
+just-scrape scrape <url> -f screenshot                    # Page screenshot
+just-scrape scrape <url> -f branding                      # Branding (logos, colors, fonts)
+just-scrape scrape <url> -f links                         # Extracted links
+just-scrape scrape <url> -f images                        # Extracted images
+just-scrape scrape <url> -f summary                       # AI-generated page summary
+just-scrape scrape <url> -f json -p <prompt>              # Structured JSON via prompt
+just-scrape scrape <url> -f markdown,links,images         # Multi-format (comma-separated)
+just-scrape scrape <url> --html-mode reader               # normal (default), reader, or prune
+just-scrape scrape <url> --scrolls <n>                    # Infinite scroll (0-100)
+just-scrape scrape <url> -m direct+stealth                # Anti-bot bypass
+just-scrape scrape <url> --country <iso>                  # Geo-targeting
 ```
 
 ### Examples
 
 ```bash
-# Get markdown of a page
+# Markdown of a page
 just-scrape scrape https://example.com
 
-# Get raw HTML
-just-scrape scrape https://example.com -f html
+# Raw HTML with reader-mode extraction
+just-scrape scrape https://blog.example.com -f html --html-mode reader
+
+# Multi-format: markdown + links + images in a single call
+just-scrape scrape https://example.com -f markdown,links,images
+
+# Structured JSON output with a prompt
+just-scrape scrape https://store.example.com -f json -p "Extract product name and price"
 
 # Scrape with anti-bot bypass and geo-targeting
 just-scrape scrape https://store.example.com -m direct+stealth --country DE
-
-# Extract branding info (logos, colors, fonts)
-just-scrape scrape https://example.com -f branding
 ```
 
 ## Markdownify
@@ -218,6 +234,7 @@ just-scrape crawl <url> --max-pages <n>                # Max pages (default 50)
 just-scrape crawl <url> --max-depth <n>                # Crawl depth (default 2)
 just-scrape crawl <url> --max-links-per-page <n>       # Links per page (default 10)
 just-scrape crawl <url> --allow-external               # Allow external domains
+just-scrape crawl <url> -f html                        # Page format (default markdown)
 just-scrape crawl <url> -m direct+stealth              # Anti-bot bypass
 ```
 
@@ -283,8 +300,9 @@ Commands have been renamed to match the v2 API:
 | `smart-scraper` | `extract` | Renamed |
 | `search-scraper` | `search` | Renamed |
 | `markdownify` | `markdownify` | Now wraps `scrape --format markdown` |
-| `scrape` | `scrape` | Gains `--format` flag (markdown, html, screenshot, branding) |
-| `crawl` | `crawl` | New options: `--max-depth`, `--max-links-per-page`, `--allow-external` |
+| `scrape` | `scrape` | Gains `--format` (markdown, html, screenshot, branding, links, images, summary, json), multi-format via comma, `--html-mode`, `--scrolls`, `--prompt`, `--schema` |
+| `crawl` | `crawl` | New options: `--max-depth`, `--max-links-per-page`, `--allow-external`, `--format` |
+| `search` | `search` | New options: `--location-geo-code`, `--time-range`, `--format` |
 | `--stealth` flag | `--mode direct+stealth` | Fetch mode enum replaces boolean (`auto`, `fast`, `js`, `direct+stealth`, `js+stealth`) |
 | `agentic-scraper` | — | Removed from API |
 | `generate-schema` | — | Removed from API |

bun.lock

@@ -28,7 +28,7 @@
 		"chalk": "^5.4.1",
 		"citty": "^0.1.6",
 		"dotenv": "^17.2.4",
-		"scrapegraph-js": "github:ScrapeGraphAI/scrapegraph-js#b570a57"
+		"scrapegraph-js": "github:ScrapeGraphAI/scrapegraph-js#c5bf757"
 	},
 	"devDependencies": {
 		"@biomejs/biome": "^1.9.4",

package.json

@@ -19,7 +19,17 @@ export default defineCommand({
 		"max-depth": { type: "string", description: "Crawl depth (default 2)" },
 		"max-links-per-page": { type: "string", description: "Max links per page (default 10)" },
 		"allow-external": { type: "boolean", description: "Allow crawling external domains" },
-		mode: { type: "string", alias: "m", description: "Fetch mode: auto (default), fast, js, direct+stealth, js+stealth" },
+		format: {
+			type: "string",
+			alias: "f",
+			description:
+				"Page format: markdown (default), html, screenshot, branding, links, images, summary",
+		},
+		mode: {
+			type: "string",
+			alias: "m",
+			description: "Fetch mode: auto (default), fast, js, direct+stealth, js+stealth",
+		},
 		json: { type: "boolean", description: "Output raw JSON (pipeable)" },
 	},
 	run: async ({ args }) => {
@@ -33,6 +43,7 @@ export default defineCommand({
 		if (args["max-links-per-page"])
 			crawlOptions.maxLinksPerPage = Number(args["max-links-per-page"]);
 		if (args["allow-external"]) crawlOptions.allowExternal = true;
+		if (args.format) crawlOptions.format = args.format;
 		if (args.mode) crawlOptions.fetchConfig = { mode: args.mode };
 
 		out.start("Crawling");
@@ -54,7 +65,11 @@ export default defineCommand({
 				const statusData = status.data as { status: string; [key: string]: unknown };
 				out.poll(statusData.status);
 
-				if (statusData.status === "completed" || statusData.status === "failed" || statusData.status === "cancelled") {
+				if (
+					statusData.status === "completed" ||
+					statusData.status === "failed" ||
+					statusData.status === "cancelled"
+				) {
 					out.stop(Math.round(performance.now() - t0));
 					out.result(status.data);
 					return;

src/commands/crawl.ts

@@ -2,10 +2,23 @@ import { defineCommand } from "citty";
 import { createClient } from "../lib/client.js";
 import * as log from "../lib/log.js";
 
+const FORMATS = [
+	"markdown",
+	"html",
+	"screenshot",
+	"branding",
+	"links",
+	"images",
+	"summary",
+	"json",
+] as const;
+type Format = (typeof FORMATS)[number];
+
 export default defineCommand({
 	meta: {
 		name: "scrape",
-		description: "Scrape content from a URL (markdown, html, screenshot, or branding)",
+		description:
+			"Scrape content from a URL (markdown, html, screenshot, branding, links, images, summary, json)",
 	},
 	args: {
 		url: {
@@ -16,9 +29,27 @@ export default defineCommand({
 		format: {
 			type: "string",
 			alias: "f",
-			description: "Output format: markdown (default), html, screenshot, branding",
+			description: `Output format: ${FORMATS.join(", ")} (default: markdown). Comma-separate for multi-format output.`,
+		},
+		prompt: {
+			type: "string",
+			alias: "p",
+			description: "Prompt for json format (required when --format includes json)",
 		},
-		mode: { type: "string", alias: "m", description: "Fetch mode: auto (default), fast, js, direct+stealth, js+stealth" },
+		schema: {
+			type: "string",
+			description: "Schema for json format (JSON string)",
+		},
+		mode: {
+			type: "string",
+			alias: "m",
+			description: "Fetch mode: auto (default), fast, js, direct+stealth, js+stealth",
+		},
+		"html-mode": {
+			type: "string",
+			description: "HTML/markdown extraction mode: normal (default), reader, prune",
+		},
+		scrolls: { type: "string", description: "Number of infinite scrolls (0-100)" },
 		country: { type: "string", description: "ISO country code for geo-targeting" },
 		json: { type: "boolean", description: "Output raw JSON (pipeable)" },
 	},
@@ -29,10 +60,50 @@ export default defineCommand({
 
 		const fetchConfig: Record<string, unknown> = {};
 		if (args.mode) fetchConfig.mode = args.mode;
+		if (args.scrolls) fetchConfig.scrolls = Number(args.scrolls);
 		if (args.country) fetchConfig.country = args.country;
 
-		const scrapeOptions: Record<string, unknown> = {};
-		if (args.format) scrapeOptions.format = args.format;
+		const requestedFormats = (args.format ?? "markdown")
+			.split(",")
+			.map((f) => f.trim())
+			.filter(Boolean) as Format[];
+		const htmlMode = (args["html-mode"] as "normal" | "reader" | "prune" | undefined) ?? "normal";
+
+		const formats = requestedFormats.map((f) => {
+			switch (f) {
+				case "markdown":
+					return { type: "markdown" as const, mode: htmlMode };
+				case "html":
+					return { type: "html" as const, mode: htmlMode };
+				case "screenshot":
+					return { type: "screenshot" as const };
+				case "branding":
+					return { type: "branding" as const };
+				case "links":
+					return { type: "links" as const };
+				case "images":
+					return { type: "images" as const };
+				case "summary":
+					return { type: "summary" as const };
+				case "json": {
+					if (!args.prompt) {
+						out.error("--prompt is required when --format includes json");
+						return { type: "json" as const };
+					}
+					return {
+						type: "json" as const,
+						prompt: args.prompt,
+						schema: args.schema ? JSON.parse(args.schema) : undefined,
+						mode: htmlMode,
+					};
+				}
+				default:
+					out.error(`Unknown format: ${f}. Valid: ${FORMATS.join(", ")}`);
+					return { type: "markdown" as const, mode: htmlMode };
+			}
+		});
+
+		const scrapeOptions: Record<string, unknown> = { formats };
 		if (Object.keys(fetchConfig).length > 0) scrapeOptions.fetchConfig = fetchConfig;
 
 		out.start("Scraping");

src/commands/scrape.ts

@@ -23,6 +23,19 @@ export default defineCommand({
 			description: "Number of websites to scrape (1-20, default 3)",
 		},
 		schema: { type: "string", description: "Output JSON schema (as JSON string)" },
+		"location-geo-code": {
+			type: "string",
+			description: "Geo-location code for search (e.g. 'us', 'de', 'jp-tk')",
+		},
+		"time-range": {
+			type: "string",
+			description:
+				"Filter results by recency: past_hour, past_24_hours, past_week, past_month, past_year",
+		},
+		format: {
+			type: "string",
+			description: "Result format: markdown (default) or html",
+		},
 		headers: { type: "string", description: "Custom headers as JSON object string" },
 		json: { type: "boolean", description: "Output raw JSON (pipeable)" },
 	},
@@ -35,6 +48,9 @@ export default defineCommand({
 		if (args["num-results"]) searchOptions.numResults = Number(args["num-results"]);
 		if (args.schema) searchOptions.schema = JSON.parse(args.schema);
 		if (args.prompt) searchOptions.prompt = args.prompt;
+		if (args["location-geo-code"]) searchOptions.locationGeoCode = args["location-geo-code"];
+		if (args["time-range"]) searchOptions.timeRange = args["time-range"];
+		if (args.format) searchOptions.format = args.format;
 		if (args.headers) searchOptions.fetchConfig = { headers: JSON.parse(args.headers) };
 
 		out.start("Searching");