MD-This-Page
MD-This-Page converts any web page to clean, readable Markdown in one click—extracts main content, removes clutter, and exports for reading or AI workflows.
What is MD-This-Page?
MD-This-Page is a browser extension that extracts the main content of an article or webpage, removes clutter, and converts the result into well-formatted Markdown. It targets users who need web content in a cleaner, structured format—particularly for workflows that send content to large language models (LLMs).
The extension’s core purpose is to turn “web pages” (often filled with navigation, scripts, ads, and deeply nested HTML) into “LLM-ready documents.” By focusing on simplified structure, it helps reduce noise from irrelevant UI and boilerplate while preserving content elements such as headings and sections.
Key Features
- One-click conversion from the context menu or keyboard shortcut (Alt+M) to convert the current page quickly.
- Smart extraction using Mozilla’s Readability library to isolate the main article or webpage content and ignore ads, navbars, and unnecessary elements.
- Dedicated preview tab that opens a clean interface to view the extracted Markdown and refine it.
- Customizable Markdown output options, including toggles to remove/keep images, remove/keep links, and show/hide metadata (title, author, date).
- Document structure / page map generation to produce a representation of the document’s structure.
- Export options such as copy to clipboard, download as a .md file, and copy as a prompt for AI workflows.
How to Use MD-This-Page
- Install the extension from the repository’s releases, or build it from source.
- Open any webpage (for example, an article page).
- Right-click the page and select “.MD this page” from the context menu (or use Alt+M).
- Use the preview tab to review the extracted Markdown.
- Adjust output settings as needed (e.g., images, links, metadata) and export the Markdown via clipboard, .md download, or “copy as a prompt.”
Use Cases
- Preparing article text for an LLM: Convert an article webpage into structured Markdown so downstream extraction, summarization, or Q&A gets cleaner input than raw HTML.
- Building compact “source documents” for prompts: Use the “copy as a prompt” option to transfer the converted content into AI workflows with less layout noise.
- Document archiving or note-taking: Export the result as a .md file to store readable versions of web pages in a consistent format.
- Content review with adjustable fidelity: Toggle images, links, and metadata to match the level of detail you need for analysis or referencing.
- Faster navigation through long pages: Generate a document structure / page map to understand how the page is organized before extracting or summarizing it.
FAQ
-
How does MD-This-Page decide what content to keep? It uses Mozilla’s Readability library to isolate main content while ignoring elements such as ads and navigation/other unnecessary page parts.
-
What input/output formats does the extension support? It converts webpages into Markdown and supports exporting via copy to clipboard, download as a .md file, and copy as a prompt.
-
How do I convert a page once the extension is installed? Use the right-click context menu entry labeled “.MD this page” or press Alt+M.
-
Can I control what appears in the Markdown? Yes. The extension provides toggles to remove/keep images, remove/keep links, and show/hide metadata (title, author, date), along with options to generate a document structure/page map.
-
Where can I preview the extracted Markdown? The extension opens a dedicated preview tab where you can view and refine the extracted Markdown.
Alternatives
- Readability-style content extraction tools or extensions: These also focus on extracting main page text from cluttered webpages. They may differ by output format; some produce plain text or cleaned HTML rather than Markdown.
- “HTML to Markdown” converters: General converters can translate HTML to Markdown, but they typically don’t perform main-content isolation. That means more navigation/boilerplate may remain compared to MD-This-Page’s Readability-based extraction.
- Manual copy-and-paste with cleaning: Some workflows rely on browser reader modes or manual selection followed by formatting. This can be more controlled but is usually less one-click than MD-This-Page.
- Developer-side extraction scripts: Automated pipelines can fetch and parse webpages to create structured documents. These require setup and maintenance and may not provide the same in-browser preview/export flow.
Alternatives
AakarDev AI
AakarDev AI is a powerful platform that simplifies the development of AI applications with seamless vector database integration, enabling rapid deployment and scalability.
Nolain OCR
Nolain OCR is an advanced Optical Character Recognition solution designed to accurately extract text and data from various document formats, streamlining document processing workflows.
BookAI.chat
BookAI allows you to chat with your books using AI by simply providing the title and author.
skills-janitor
Audit, track usage, and compare your Claude Code skills with skills-janitor—nine focused slash commands and zero dependencies.
Jenni
Jenni is an AI workspace to read PDFs, draft essays and papers, and generate in-text citations in 2.6k+ styles.
FeelFish
FeelFish AI Novel Writing Agent PC client helps novel creators plan characters and settings, generate and edit chapters, and continue plots with context consistency.