Long essays and articles as plain text with word counts

Created by

Rowcraft

Actor

Website to Markdown Extractor: Clean Text for LLMs and RAG

Three well-known public essays and articles, each read once and returned as plain text and Markdown with the title, the publication date where the page states one, the headings and the word count. A starting point for a reading list, a summary job or an index of your own articles.

Try for free

Website to Markdown Extractor: Clean Text for LLMs and RAGrowcraft/website-markdown-extractor

Page title

Words in the extracted text (the whole text, also when it was cut at the character limit)

Language declared by the page (html lang)

Publication date from the page metadata (ISO 8601), or null

+3 fields

Input

Page URLs(required):https://martinfowler.com/articles/microservices.html+2

Keep links:false

Keep images:false

Maximum characters per page:30000

Output fields

Page title

Words in the extracted text (the whole text, also when it was cut at the character limit)

Language declared by the page (html lang)

Publication date from the page metadata (ISO 8601), or null

Headings of the content, one per line, as "H2: text"

True when the Markdown or the text was cut at the character limit

Address that answered, after redirects

How it works

Sign up on Apify or log in

The Website to Markdown Extractor: Clean Text for LLMs and RAG Actor is ready to run with the inputs already set for "Long essays and articles as plain text with word counts". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Long essays and articles as plain text with word counts" task

The Website to Markdown Extractor: Clean Text for LLMs and RAG Actor will start running based on the input automatically. You can also change all the input fields, like page urls, keep links, and more, to match your specific use case.

Receive the "Long essays and articles as plain text with word counts" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as page title, words in the extracted text (the whole text, also when it was cut at the character limit), language declared by the page (html lang), and more.