{"ref":"osintverse-community/cdx-toolkit","version":"0.9.39","status":"published","signer_identity":"pypi:GitHub:commoncrawl/cdx_toolkit/publish_pypi.yaml","signer_issuer":"https://pypi.org","scan_status":"pass","health":"unknown","health_checked_at":null,"verified_publisher":true,"source_unavailable":false,"manifest":{"schema":1,"name":"cdx-toolkit","namespace":"osintverse-community","version":"0.9.39","summary":"Lists a domain's pages in Common Crawl's URL index, with each capture's time, status, type and language","readme":"README.md","license":"Apache-2.0","homepage":"https://github.com/commoncrawl/cdx_toolkit","categories":["web-archive","domain-dns"],"tags":["common-crawl","urls","web-archive","cdx"],"inputs":[{"name":"domain","type":"domain","required":true,"description":"Domain or host name; pages on its subdomains are not included"},{"name":"crawls","type":"integer","required":false,"default":1,"description":"How many of the latest crawls (about one a month) to search"},{"name":"limit","type":"integer","required":false,"default":100,"description":"Most captures to return"}],"outputs":[{"type":"url"}],"runtime":{"kind":"pipx","package":"cdx-toolkit","package_version":"0.9.39","index":"pypi","python":">=3.9","entrypoint":"cdxt","wheel_sha256":"577ae9a9578f33ce4bae6c887074f0f70331bf4d6a66a26d1e20836b3004e431","command":["cdxt","--crawl","{crawls}","--limit","{limit}","iter","--fields","url,timestamp,status,mime,languages,length","--jsonl","{domain}/*"],"output_format":"jsonl","timeout_seconds":600},"network":{"egress":true},"ethics":{"touches_target":false,"auth_required":false,"collects_personal_data":false},"test":{"input":{"domain":"example.com","crawls":1,"limit":20}},"kind":"tool"},"manifest_full":{"schema":1,"name":"cdx-toolkit","namespace":"osintverse-community","version":"0.9.39","summary":"Lists a domain's pages in Common Crawl's URL index, with each capture's time, status, type and language","readme":"README.md","license":"Apache-2.0","homepage":"https://github.com/commoncrawl/cdx_toolkit","categories":["web-archive","domain-dns"],"tags":["common-crawl","urls","web-archive","cdx"],"inputs":[{"name":"domain","type":"domain","required":true,"description":"Domain or host name; pages on its subdomains are not included","example":"example.com"},{"name":"crawls","type":"integer","required":false,"default":1,"description":"How many of the latest crawls (about one a month) to search"},{"name":"limit","type":"integer","required":false,"default":100,"description":"Most captures to return"}],"outputs":[{"type":"url"}],"runtime":{"kind":"pipx","package":"cdx-toolkit","package_version":"0.9.39","index":"pypi","python":">=3.9","entrypoint":"cdxt","wheel_sha256":"577ae9a9578f33ce4bae6c887074f0f70331bf4d6a66a26d1e20836b3004e431","command":["cdxt","--crawl","{crawls}","--limit","{limit}","iter","--fields","url,timestamp,status,mime,languages,length","--jsonl","{domain}/*"],"output_format":"jsonl","timeout_seconds":600,"typical_seconds":30},"network":{"egress":true},"ethics":{"touches_target":false,"auth_required":false,"collects_personal_data":false,"notifies_target":false},"test":{"input":{"domain":"example.com","crawls":1,"limit":20}},"kind":"tool"},"wheel_url":"https://api.otinstaller.com/v1/tools/osintverse-community/cdx-toolkit/0.9.39/wheel/cdx_toolkit-0.9.39-py3-none-any.whl"}