Page to Markdown Scraper

Capture page content and OCR text from any page or PDF. Saves as Markdown/ZIP for ChatGPT and LLMs. 100% local processing.

Page to Markdown Scraper captures web page content and saves it as a clean Markdown file in a ZIP, ready to upload to ChatGPT, Claude, Gemini, or any other LLM. VERSION 1.5.0 - NOW WITH BUILT-IN OCR Three capture modes: MANUAL MODE Capture the current page with one click. Text, images, and metadata are extracted and downloaded immediately as a ZIP file. AUTO MODE Start a recording session, then browse normally. Every page you visit is captured automatically. A red border and REC badge show that recording is active. Stop the session to download everything in a single ZIP. OCR MODE (NEW) Extract text from screenshots using built-in optical character recognition. Works on content that normal scraping cannot reach: images, scanned documents, PDFs, canvas elements, and pages that block text selection. - OCR Viewport: Capture and extract text from the visible screen area - OCR Full Page: Auto-scrolls the entire page or PDF, capturing and recognising each section - PDF support: Automatically detects PDF files and scrolls through the full document - Keyboard shortcut: Ctrl+Shift+O (Cmd+Shift+O on Mac) for quick viewport capture - Results panel: Shows word count and confidence score with a one-click download button PRIVACY - All processing happens locally in your browser. Nothing is sent to any server. - OCR runs via Tesseract.js (WebAssembly) entirely on your device. No cloud APIs. - No analytics, no tracking, no accounts, no data collection. - Open source: https://github.com/SlambertDK/page-to-markdown-extension OUTPUT - content.md: Clean Markdown optimised for LLM upload - images/ folder: All page images and OCR screenshots - README.txt: Usage instructions - Everything in a single ZIP file DISCLAIMER You are responsible for ensuring you have the right to capture and use any content. A terms disclaimer is shown before every capture session.