Pricing

from $1.92 / 1,000 item extracteds

Try for free

Go to Apify Store

LLM Web Page Research Browser

Try for free

Convert public web pages into cleaned Markdown, compact chunks, metadata, links, and citations for LLM research and RAG ingestion.

Pricing

from $1.92 / 1,000 item extracteds

Rating

0.0

(0)

Developer

Stas Persiianenko

Actor stats

Bookmarked

Total users

Monthly active users

8 days ago

Last modified

Categories

Developer tools

url

Optional

Final public source URL after redirects.

Type:string | null

Example:

https://docs.example.org/guide

requestedUrl

Optional

Original URL supplied in the run input.

Type:string | null

Example:

https://docs.example.org/guide

title

Optional

Readable page or article title.

Type:string | null

Example:

Example research guide

description

Optional

Page metadata description when available.

Type:string | null

Example:

A practical guide to the example topic.

author

Optional

Page or article author when available.

Type:string | null

Example:

Example Editorial Team

siteName

Optional

Publisher or site name when available.

Type:string | null

Example:

Example Documentation

language

Optional

Declared or extracted document language.

Type:string | null

Example:

publishedAt

Optional

Source publication timestamp when exposed.

Type:string | null

Example:

2025-01-15T12:00:00.000Z

retrievedAt

Optional

UTC timestamp when the page was fetched.

Type:string | null

Example:

2025-01-16T09:30:00.000Z

statusCode

Optional

Successful source response status.

Type:integer | null

Example:

200

contentType

Optional

HTTP content type returned by the source.

Type:string | null

Example:

text/html; charset=utf-8

markdown

Optional

Cleaned page content in Markdown when requested.

Type:string | null

Example:

# Example research guide Readable source content.

text

Optional

Cleaned plain text when requested.

Type:string | null

Example:

Example research guide Readable source content.

charCount

Optional

Cleaned Markdown character count.

Type:integer | null

Example:

2450

wordCount

Optional

Approximate cleaned content word count.

Type:integer | null

Example:

410

tokenEstimate

Optional

Approximate LLM token count using four characters per token.

Type:integer | null

Example:

613

truncated

Optional

Whether content reached maxContentChars.

Type:boolean | null

Example:

false

links

Optional

Deduplicated same-origin HTTP(S) links found on the page.

Type:object[] | null

Example:

[
  {
    "url": "https://docs.example.org/next",
    "text": "Next topic"
  }
]

chunks

Optional

Compact overlapping Markdown chunks with source citations.

Type:object[] | null

Example:

[
  {
    "id": "docs.example.org-001",
    "text": "Readable source content.",
    "charCount": 24,
    "wordCount": 3,
    "citation": {
      "sourceUrl": "https://docs.example.org/guide",
      "title": "Example research guide",
      "retrievedAt": "2025-01-16T09:30:00.000Z"
    }
  }
]

citation

Optional

Page-level citation for downstream research answers.

Type:object | null

Example:

{
  "sourceUrl": "https://docs.example.org/guide",
  "title": "Example research guide",
  "retrievedAt": "2025-01-16T09:30:00.000Z"
}

Other properties may be included.

AI Web Extractor: URL → Clean Markdown + JSON for LLM/RAG

boxbox10/ai-web-extractor

Turn any URL into clean, LLM-ready Markdown + structured JSON (title, headings, main content, links, metadata, token count). Perfect for RAG pipelines, AI agents, and LLM context.

Marvin Eguilos

URL to Markdown - Clean Web Pages for LLMs & RAG

scrapesage/url-to-markdown

Convert any list of web pages to clean Markdown for LLM/RAG ingestion, notes or docs. Main-content mode (Readability) keeps just the article; full-page mode converts the whole body. Tables and links preserved. No browser.

Scrape Sage

URL to Markdown MCP

reverberant_equality/mcp-url-to-markdown

Convert any web page to clean markdown for AI agents. Uses Firefox Reader Mode engine for content extraction. Perfect for RAG pipelines, research, and LLM content ingestion.

Jordan C

LLM-Ready Web Content Extractor

beyondxl/llm-ready-content-extractor

Turn any public web page or shallow site crawl into clean, LLM-ready Markdown + metadata + optional RAG chunks. Boilerplate/nav/ads removed. Honors robots.txt.

Leopold Ai

LLM-Ready Web Extractor

phantom_horse/my-actor-1

Turn any web page into clean, LLM-ready Markdown. Strips scripts, nav, and page chrome, then converts the main content to tidy Markdown with title, meta description, and token counts. Perfect for AI prompts and RAG ingestion pipelines.

NATNAEL FIKRE

PDF Extractor: PDF → Clean Markdown + JSON for LLM/RAG

boxbox10/pdf-extractor

Turn any PDF URL into clean, LLM-ready Markdown + structured JSON (title, metadata, per-page text, page count, word count, token count). Perfect for RAG pipelines, AI agents, and LLM document ingestion.

Marvin Eguilos

Website Content Crawler — Text, Markdown & HTML for AI/LLM

hichemdev/website-content-crawler

Crawl any website and extract clean text, Markdown, and HTML from every page — ready for LLM, RAG, and AI ingestion.

Hichem Ben Moussa

Doc to Markdown — DOCX, PDF & web pages to clean markdown

amanatools/doc-to-markdown

Convert DOCX files, PDFs, and web pages into clean markdown for LLM and agent ingestion. Main-content extraction strips navigation junk from web pages. Pay per document.

Dos

Web-to-Markdown Generator for AI & RAG Pipelines

profitstack/web-to-markdown-generator-for-ai-rag-pipelines

Convert any website into clean, heading-based chunking, LLM-ready Markdown for RAG and AI agents.

Manas Mantri

LLM-Ready Web Extractor: URL to Clean Markdown & JSON

f0rty7even/llm-web-extractor

Turn any web page or site into clean, LLM-ready Markdown and structured JSON for RAG, agents, and fine-tuning. Strips nav/ads/boilerplate; returns main content + metadata.