{"id":"trafilatura-3","name":"Trafilatura","library":"Data, AI and orchestration","library_file":"09","category":"Acquisition and document processing","status":"Open source, Apache-2.0","sources":[{"label":"Trafilatura repository","url":"https://github.com/adbar/trafilatura"}],"links":[{"label":"Trafilatura repository","url":"https://github.com/adbar/trafilatura"}],"attributes":{"status_license":"Open source, Apache-2.0","best_use":"Main-text and metadata extraction from HTML","boundary":"Extraction quality must be sampled; preserve the original artifact","official_source":"Trafilatura repository"},"defined_in":{"file":"09","file_slug":"data-ai-orchestration-tool-library","section":"2-acquisition-and-document-processing","table":"09.2-acquisition-and-document-processing.t1","line":26}}