{"adoption": {"forks": 308, "observed_at": "2026-08-28T04:04:45.838555+00:00", "stars": 1450}, "canonical_url": "https://ross.abutalabs.com/products/fscrawler", "card": {"archived": false, "artifact_type": "application", "description": "Elasticsearch File System Crawler (FS Crawler)", "domain": ["files", "pdf", "developer-tools"], "enriched": true, "function": ["search-engine", "etl", "ocr", "parser"], "health_score": 100, "homepage": "https://fscrawler.readthedocs.io/", "language": "Java", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["dadoonet/fscrawler"], "name": "dadoonet/fscrawler", "platform": ["jvm", "cross-platform", "cli"], "pushed_at": "2026-08-26T18:34:15+00:00", "repo": "dadoonet/fscrawler", "stars": 1450, "tags": ["elasticsearch", "tika", "file-crawler", "binary-documents", "indexing", "rest-upload", "search", "docker"], "topics": ["java", "elasticsearch", "crawler", "tika"], "urls": [], "use_cases": ["index pdf and office documents into elasticsearch", "crawl a local folder and keep an elasticsearch index in sync", "extract text from binary documents for full-text search", "upload documents to elasticsearch via a rest endpoint", "crawl files over ssh or ftp and index them", "build a document search engine from a file share"], "what_it_is": "FSCrawler is a Java-based file system crawler that indexes binary documents (PDF, MS Office, Open Office) into Elasticsearch, tracking new, updated, and deleted files. It supports local and remote (SSH/FTP) file systems and offers a REST interface for uploading documents directly.", "when_to_avoid": ["you use a search engine other than elasticsearch", "you only need to crawl web pages rather than local or remote file systems", "you want a fully managed cloud ingestion service"], "when_to_choose": ["you need to full-text search binary documents stored on a file system with elasticsearch", "you want automatic syncing of file additions, updates, and deletions into an index", "you need tika-based text extraction without writing your own pipeline"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/fscrawler", "repo": "dadoonet/fscrawler", "role": "main", "score": 88}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.838555+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:35:55.190241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3bc8837088dc9f2693f8475d33c75d78459f4ad58085de541f8991a50bc3d250", "fetched_at": "2026-08-28T04:04:45.838555+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dadoonet/fscrawler"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.838555+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:35:55.190241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3bc8837088dc9f2693f8475d33c75d78459f4ad58085de541f8991a50bc3d250", "fetched_at": "2026-08-28T04:04:45.838555+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dadoonet/fscrawler"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:35:55.190241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3bc8837088dc9f2693f8475d33c75d78459f4ad58085de541f8991a50bc3d250", "fetched_at": "2026-08-28T04:04:45.838555+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dadoonet/fscrawler"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.838555+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.838555+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.838555+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:35:55.190241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3bc8837088dc9f2693f8475d33c75d78459f4ad58085de541f8991a50bc3d250", "fetched_at": "2026-08-28T04:04:45.838555+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dadoonet/fscrawler"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.838555+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.838555+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:35:55.190241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3bc8837088dc9f2693f8475d33c75d78459f4ad58085de541f8991a50bc3d250", "fetched_at": "2026-08-28T04:04:45.838555+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dadoonet/fscrawler"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.838555+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.838555+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.838555+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:35:55.190241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3bc8837088dc9f2693f8475d33c75d78459f4ad58085de541f8991a50bc3d250", "fetched_at": "2026-08-28T04:04:45.838555+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dadoonet/fscrawler"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.838555+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.838555+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:35:55.190241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3bc8837088dc9f2693f8475d33c75d78459f4ad58085de541f8991a50bc3d250", "fetched_at": "2026-08-28T04:04:45.838555+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dadoonet/fscrawler"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:35:55.190241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3bc8837088dc9f2693f8475d33c75d78459f4ad58085de541f8991a50bc3d250", "fetched_at": "2026-08-28T04:04:45.838555+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dadoonet/fscrawler"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:35:55.190241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3bc8837088dc9f2693f8475d33c75d78459f4ad58085de541f8991a50bc3d250", "fetched_at": "2026-08-28T04:04:45.838555+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dadoonet/fscrawler"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:35:55.190241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3bc8837088dc9f2693f8475d33c75d78459f4ad58085de541f8991a50bc3d250", "fetched_at": "2026-08-28T04:04:45.838555+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dadoonet/fscrawler"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 67}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 5199, "days_push": 7, "days_rel": 7, "gap_med": null, "n_releases_24m": 1}, "score": 88, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}