{"id":"common-crawl","name":"Common Crawl","library":"Technical and passive OSINT","library_file":"05","category":"Hosted free and open-data sources","status":"free CDXJ/JSON index and WARC","sources":[{"label":"Index","url":"https://commoncrawl.org/cdxj-index"},{"label":"Terms","url":"https://commoncrawl.org/terms-of-use"}],"links":[{"label":"Index","url":"https://commoncrawl.org/cdxj-index"},{"label":"Terms","url":"https://commoncrawl.org/terms-of-use"}],"attributes":{"status_access":"free CDXJ/JSON index and WARC","i_o_and_fit":"URL/domain → captures/status/MIME/WARC; strong offline history","current_limitations_and_safe_interpretation":"incomplete/stale; source copyright/privacy persists; prefer bulk data to hammering index","official_source":"Index · Terms"},"defined_in":{"file":"05","file_slug":"technical-osint-tool-library","section":"3-hosted-free-open-data-sources","table":"05.3-hosted-free-open-data-sources.t1","line":47}}