DataKit – Apify Scraping Tools

AI data agent in your sidebar: ask for web data in plain English, get spreadsheets. Integrates with Apify and AI tools.

DataKit — Intelligent Browser Data Assistant DataKit brings an intelligent data assistant right into your browser sidebar. Turn any public webpage or data table into a clean, exportable spreadsheet by simply describing what you need in plain English. Whether you need to collect product pricing, extract directory listings, track web updates, or extract tables from multi-page articles, DataKit coordinates direct browser parsing, AI-powered extraction, and cloud scraping tools to deliver structured datasets with minimal effort. KEY FEATURES ✦ Natural Language Extraction & Prompt Optimization Ask for the data you want in everyday language. DataKit analyzes your request, identifies relevant structured content, and extracts the fields you need into an organized table without requiring code. Automatic prompt optimization helps refine extraction instructions before processing, with controls to enable or disable automatic optimization and run it manually when needed. ✦ Direct In-Browser Table & Content Capture Quickly parse HTML tables, product grids, listings, and text blocks directly from the webpage you are currently viewing. DataKit uses page structure and DOM-based extraction to collect relevant content locally for a fast preview, helping avoid unnecessary cloud requests for straightforward pages. ✦ Pre-Built Extraction Recipes Run ready-to-use workflows for common web data tasks. Save frequent extraction steps as reusable recipes so you can repeat your workflows on matching sites with a single click. ✦ Instant Data Filtering & Exporting Inspect your extracted data directly in the sidebar. Use filters to narrow results by numeric values, text matches, ratings, and other available fields. Export datasets in CSV, Excel (XLSX), JSON, or JSONL formats ready for analysis. ✦ Advanced Cloud Scraper Integration For complex, multi-page, or JavaScript-heavy websites, DataKit can coordinate cloud scraping through Apify and supported autonomous browser automation through TinyFish. These integrations help handle pages that require navigation, scrolling, or more advanced extraction strategies. Before an Apify cloud task starts, DataKit provides run details, parameter configuration, and applicable cost or budget confirmations. This helps you understand the intended operation before authorizing potentially billable cloud work. ✦ Scheduled Monitors & Change Alerts Set recurring background checks on supported web sources. DataKit can monitor for updates at your chosen interval and notify you when new items appear or tracked data changes, where monitoring is supported and configured. ✦ Local-First Privacy & Security Your extracted datasets, recipes, preferences, and browsing context are designed to remain on your local device. DataKit does not include first-party behavioral tracking or analytics. API credentials are stored locally using browser storage mechanisms, with protection dependent on the security of your browser profile and device. When you use external AI, scraping, or browser automation providers, the information needed to perform those requests may be sent to the selected provider. Review each provider's terms and privacy practices before connecting your own credentials. HOW TO USE Click the DataKit icon in your browser toolbar or press Alt+Shift+K to open the sidebar. Navigate to a webpage containing the data you want to collect. Describe what you need in plain English, such as “Extract the table on this page with price and title,” or choose a pre-built recipe. Let DataKit analyze your request and use direct browser extraction or a supported cloud workflow, depending on the task and available integrations. Preview and inspect the structured results in the sidebar. Filter the data and export it to CSV, Excel, JSON, or JSONL. PERMISSIONS & PRIVACY TRANSPARENCY Storage: Saves preferences, local recipes, datasets, and supported provider credentials in browser storage. Side Panel: Displays the data assistant alongside your browser tabs without blocking your view. Active Tab & Scripting: Accesses the page structure of the tab you are viewing when you request extraction. Host Permissions (<all_urls>): Enables supported extraction workflows across websites you choose to visit and inspect. This permission does not mean every site can be accessed successfully. Alarms & Notifications: Supports scheduled monitoring and notifications for configured background tasks. External Providers: Apify, TinyFish, and connected AI providers may receive the URLs, prompts, page data, or other information required by the specific workflow you initiate. DataKit supports a Bring-Your-Own-Key (BYOK) model for external AI and scraping services. You control which providers you connect and when to use supported cloud services. Credentials are intended to stay in local browser storage, but information submitted to an external provider is subject to that provider's processing and privacy policies.