spruce_the_data: messy HTML and text to clean JSON

Json To Excel

zuzka/json-to-excel

Convert your json into a tabular form, such as CSV, Excel or HTML table fast and easy.

Website Content Crawler - Clean Text, Markdown & RAG Chunks

topapi/website-content-crawler

Crawl any website or URL list for $1.20 per 1,000 pages: one row per page with clean text, Markdown, HTML, metadata, links, headings, tables and RAG chunks. Plain HTTP first, headless Chrome only for JavaScript pages. Sitemaps, llms.txt, PDF/DOCX text, Bing/DuckDuckGo search, change monitor.

Website Content Extractor for RAG: Markdown, HTML, Text

nezha/website-content-crawler

Turn docs sites, help centers, blogs, and websites into clean markdown, text, or HTML for RAG, AI knowledge bases, and internal search. Crawl from start URLs or sitemaps and keep the crawl in scope.

TOON to JSON (converter)

room_js/toon-to-json-converter

This actor allows you to convert TOON format to JSON

Contextractor — clean web content extraction for LLMs

markdownee/contextractor

Crawl any website and extract clean main-content text as Markdown, plain text, JSON, or HTML — ready for LLMs, RAG pipelines, and vector databases. Built on the rs-trafilatura engine and an adaptive Crawlee + Playwright crawler.

AI Web Scraper — Extract Website Data to Structured JSON

muhammadafzal/ai-web-extractor

Extract data from websites into structured JSON with AI: name the fields in plain English, no CSS selectors. For analysts and AI agents. USD 20 per 1,000 pages.

Convert XLSX, CSV and TSV files from URLs into clean JSON — one dataset item per spreadsheet row — with all sheets included and types preserved. $0.01 per successfully converted file, no start fee. Failed, unsupported or corrupt files are reported but never charged.

Agent-callable MCP server that turns messy CSV/spreadsheets into clean, typed, structured data: header detection, type inference, coercion, junk-row removal.

Turn invoices, receipts, statements, contracts, resumes, and any document (PDF or image) into clean, schema-valid JSON. It runs on ParseRail, the AI back-end for your product, from Compound Labs. Bring your own key. 500 free credits monthly, no card.

Download every image from web pages, or a list of image URLs, in bulk. Finds img, srcset (largest size), lazy-loaded, picture, og:image, icons and CSS backgrounds. Width/height filters, duplicate removal, optional ZIP. $3 per 1,000 images. File mode downloads any file type too.