Web Text Extractor

OCR Text Extractor - Images & Scanned PDFs to Text

scrapesage/ocr-text-extractor

Extract text from images (PNG, JPG, TIFF, WEBP, BMP, GIF) and scanned PDFs with Tesseract OCR in 28 languages. Per-page text, confidence scores, optional word boxes, automatic text-layer detection for born-digital PDFs. No API key, no browser. JSON, CSV, Excel.

Web Page Text Scraper – Clean Text & Links

simple.actor/page-text-reader

Scrape any web page as clean text: the full visible prose, with scripts, navigation, headers, footers, booking widgets and cookie banners stripped out. Discover mode also returns every same-site link with its anchor text. JavaScript is rendered only when a page needs it.

AI Schema Web Extractor: BYOK + Browser Fallback

automa-flow/ai-schema-web-extractor

Extract schema-validated JSON from URLs with your own LLM key. Starts on fast HTTP and renders JavaScript only when the page needs it, with source evidence for the fields.

Extract existing text from batches of public HTTPS PDFs. Get page-by-page text, page numbers, title and author, plus clear results for files with no text or download errors. Up to 25 PDFs per run; 10 MiB and 100 pages per PDF. No OCR.

RAG Web Browser Lite — Cheap Markdown for AI Agents

subimpact/rag-web-browser-lite

Web search and fetch tool for AI agents and RAG pipelines. Queries Google Search, scrapes the top N pages over raw HTTP, and returns clean Markdown. Fixed $0.002 per page — no surprise compute bills.

Convert any web page into clean, readable Markdown or plain text — ads, navigation and boilerplate stripped out. Built for feeding AI agents, LLMs and RAG pipelines. Pay only per page.

Turn any list of URLs into clean Markdown, text, HTML and links for LLMs and RAG. Renders JavaScript when needed, returns title, description and metadata. Pay per page, failed pages are free.

Web to Markdown — LLM Web Page Reader

drain54/web-to-markdown

Extract clean, LLM-ready Markdown, titles, and metadata from any public webpage. Strips ads, navigation, and boilerplate.

Idealista API Scraper

rl1987/idealista-api-scraper

Scrape Idealista real-estate listings (ES/IT/PT/FR) directly from the Idealista mobile API — price, size, rooms, location, coordinates, property type, URL and the seller/agency CONTACT (commercial name + phone number).

PDF to Text & Markdown: Extract PDF Content by URL

accountable_eel/pdf-text-extractor

Extracts text or Markdown from PDFs by URL, for a list of PDF URLs from a crawl, a Sheet, or a CRM export. Rebuilds paragraphs and headings from PDF fonts, with best-effort tables, then feeds a RAG pipeline, an LLM prompt, or a row to Google Sheets. No OCR: scanned PDFs are flagged, not charged.