webpeel 0.21.61 → 0.21.63

package/README.md

@@ -8,7 +8,6 @@
   <a href="https://github.com/webpeel/webpeel/actions/workflows/ci.yml"><img src="https://github.com/webpeel/webpeel/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
   <a href="https://www.npmjs.com/package/webpeel"><img src="https://img.shields.io/npm/v/webpeel.svg?style=flat-square" alt="npm version"></a>
   <a href="https://pypi.org/project/webpeel/"><img src="https://img.shields.io/pypi/v/webpeel.svg?style=flat-square" alt="PyPI version"></a>
-  <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg?style=flat-square" alt="License: MIT"></a>
   <a href="LICENSE"><img src="https://img.shields.io/badge/license-WebPeel%20SDK-blue.svg?style=flat-square" alt="License"></a>
   <a href="https://webpeel.dev/status"><img src="https://img.shields.io/badge/status-operational-brightgreen.svg?style=flat-square" alt="Status"></a>
 </p>
@@ -305,20 +304,20 @@ webpeel "https://news.ycombinator.com"
 # Search the web
 webpeel search "typescript orm comparison 2025"
 
-# Extract structured data
-webpeel extract "https://stripe.com/pricing" --schema pricing-schema.json
+# Extract structured data with a JSON schema
+webpeel "https://stripe.com/pricing" --extract-schema pricing-schema.json
 
-# Crawl a site, save to folder
-webpeel crawl "https://docs.example.com" --output ./docs-dump --max-pages 100
+# Crawl a site
+webpeel crawl "https://docs.example.com" --max-pages 100
 
 # Screenshot
 webpeel screenshot "https://webpeel.dev" --full-page --output screenshot.png
 
 # YouTube transcript
-webpeel youtube "https://youtube.com/watch?v=dQw4w9WgXcQ"
+webpeel "https://youtube.com/watch?v=dQw4w9WgXcQ" --json
 
 # Ask a question about a page
-webpeel qa "https://openai.com/pricing" --question "How much does GPT-4o cost per million tokens?"
+webpeel ask "https://openai.com/pricing" "How much does GPT-4o cost per million tokens?"
 
 # Output as JSON
 webpeel "https://example.com" --json

package/dist/cli/utils.js

@@ -398,7 +398,7 @@ export function buildCondensedHelp() {
         `    --raw                 Full page (disable auto reader mode)`,
         `    --full                Full page, no budget limit`,
         `    --json                JSON output with metadata`,
-        `    --budget: 4000)`,
+        `    --budget <n>          Token budget (default: 4000 in pipe mode)`,
         `    -q, --question <q>    Ask about the content`,
         `    -s, --silent          No spinner output`,
         '',

package/dist/server/routes/fetch-queue.js

@@ -176,6 +176,33 @@ export function createQueueFetchRouter() {
             pollUrl: `/v1/jobs/${jobId}`,
         });
     }
+    // GET /v1/fetch?url=...  — CLI and backward-compatible GET requests
+    // Maps query params into req.body so handleEnqueue works uniformly
+    router.get('/v1/fetch', (req, res) => {
+        // Map query string to body for uniform handling
+        req.body = {
+            url: req.query.url,
+            format: req.query.format || 'markdown',
+            render: req.query.render === 'true',
+            stealth: req.query.stealth === 'true',
+            wait: req.query.wait ? Number(req.query.wait) : undefined,
+            selector: req.query.selector,
+            readable: req.query.readable === 'true',
+            budget: req.query.budget ? Number(req.query.budget) : undefined,
+            question: req.query.question,
+            screenshot: req.query.screenshot === 'true',
+            fullPage: req.query.fullPage === 'true' || req.query['full-page'] === 'true',
+            maxTokens: req.query.maxTokens ? Number(req.query.maxTokens) : undefined,
+            lite: req.query.lite === 'true',
+            raw: req.query.raw === 'true',
+            images: req.query.images === 'true',
+        };
+        void handleEnqueue(req, res, false);
+    });
+    router.get('/v1/render', (req, res) => {
+        req.body = { url: req.query.url, format: req.query.format || 'markdown' };
+        void handleEnqueue(req, res, true);
+    });
     router.post('/v1/fetch', (req, res) => void handleEnqueue(req, res, false));
     router.post('/v1/render', (req, res) => void handleEnqueue(req, res, true));
     /**
@@ -186,6 +213,19 @@ export function createQueueFetchRouter() {
     router.get('/v1/jobs/:id', async (req, res) => {
         const { id } = req.params;
         const requestId = req.requestId || randomUUID();
+        // Auth required — prevent IDOR (unauthenticated access to job results)
+        if (!req.auth?.keyInfo) {
+            res.status(401).json({
+                success: false,
+                error: {
+                    type: 'unauthorized',
+                    message: 'API key required to poll job results.',
+                    docs: 'https://webpeel.dev/docs/errors#unauthorized',
+                },
+                requestId,
+            });
+            return;
+        }
         if (!id || typeof id !== 'string') {
             res.status(400).json({
                 success: false,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "webpeel",
-  "version": "0.21.61",
+  "version": "0.21.63",
   "description": "Fast web fetcher for AI agents - stealth mode, crawl mode, page actions, structured extraction, PDF parsing, smart escalation from simple HTTP to headless browser",
   "author": "Jake Liu",
   "license": "AGPL-3.0-only",