Neil Sangwaiya

Extract topics and full post text from any Discourse forum. Clean plain-text output for LLM training, RAG corpora and community research.

Scrape any documentation site to clean markdown. Works on Docusaurus, Mintlify, GitBook, MkDocs, ReadTheDocs and more. Preserves code blocks for RAG and LLM training.

Turn any public GitHub repository into a clean dataset of code and documentation files. One download, no API token, no rate limits. Built for AI coding assistants and RAG.

Convert PDFs to clean markdown with real reading order. Handles two-column layouts, detects headings and paragraphs. Built for RAG pipelines and LLM ingestion.

Extract every table from any web page into clean rows, JSON and markdown. Correctly handles colspan, rowspan and stacked headers that break other extractors.

Scrape posts, pages and content from any WordPress site via the REST API. Clean plain text with authors, categories and tags, ready for LLM training and RAG.

Scrape all articles from any Zendesk Help Center. Full plain-text bodies with sections, categories and labels. Ready for RAG, AI support bots and knowledge base migration.