{"adoption": {"forks": 176, "observed_at": "2026-08-28T04:04:12.825539+00:00", "stars": 1274}, "canonical_url": "https://ross.abutalabs.com/products/dragnet", "card": {"archived": false, "artifact_type": "library", "description": "Just the facts -- web page content extraction", "domain": ["web-development", "machine-learning", "crawlers"], "enriched": true, "function": ["nlp", "parser", "machine-learning", "web-scraping"], "health_score": 38, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["dragnet-org/dragnet"], "name": "dragnet-org/dragnet", "platform": ["python"], "pushed_at": "2025-07-08T00:53:21+00:00", "repo": "dragnet-org/dragnet", "stars": 1274, "tags": ["content-extraction", "boilerplate-removal", "html-parsing", "readability", "article-extraction", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["extract main article text from html pages", "strip boilerplate and chrome from web pages", "extract article content and comments from a webpage", "readability-style content extraction in python", "train a custom content extraction model", "clean html for text mining pipelines"], "what_it_is": "Dragnet is a Python library that uses machine learning models to extract the main article content, and optionally user comments, from HTML web pages. It provides simple extraction functions plus sklearn-style trainable extractors with pre-trained models.", "when_to_avoid": ["you need to extract structured data like tables or product listings rather than article text", "you need a maintained general-purpose scraper with JavaScript rendering", "your project requires actively developed dependencies and recent community activity"], "when_to_choose": ["you need high-accuracy main-content extraction from article pages", "you want to also capture user comments alongside the article", "you want to train or fine-tune your own extraction model with sklearn-style APIs"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/dragnet", "repo": "dragnet-org/dragnet", "role": "main", "score": 36}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:12.825539+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T05:03:07.034187+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "07d69d2f0d0ee9d93caedfafd53bb4f1a9ae9bb3c5084ebd305e11b4bd3751ab", "fetched_at": "2026-08-28T04:04:12.825539+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dragnet-org/dragnet"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:12.825539+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T05:03:07.034187+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "07d69d2f0d0ee9d93caedfafd53bb4f1a9ae9bb3c5084ebd305e11b4bd3751ab", "fetched_at": "2026-08-28T04:04:12.825539+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dragnet-org/dragnet"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T05:03:07.034187+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "07d69d2f0d0ee9d93caedfafd53bb4f1a9ae9bb3c5084ebd305e11b4bd3751ab", "fetched_at": "2026-08-28T04:04:12.825539+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dragnet-org/dragnet"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:12.825539+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:12.825539+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:12.825539+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T05:03:07.034187+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "07d69d2f0d0ee9d93caedfafd53bb4f1a9ae9bb3c5084ebd305e11b4bd3751ab", "fetched_at": "2026-08-28T04:04:12.825539+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dragnet-org/dragnet"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:12.825539+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:12.825539+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T05:03:07.034187+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "07d69d2f0d0ee9d93caedfafd53bb4f1a9ae9bb3c5084ebd305e11b4bd3751ab", "fetched_at": "2026-08-28T04:04:12.825539+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dragnet-org/dragnet"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:12.825539+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:12.825539+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:12.825539+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T05:03:07.034187+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "07d69d2f0d0ee9d93caedfafd53bb4f1a9ae9bb3c5084ebd305e11b4bd3751ab", "fetched_at": "2026-08-28T04:04:12.825539+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dragnet-org/dragnet"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:12.825539+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:12.825539+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T05:03:07.034187+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "07d69d2f0d0ee9d93caedfafd53bb4f1a9ae9bb3c5084ebd305e11b4bd3751ab", "fetched_at": "2026-08-28T04:04:12.825539+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dragnet-org/dragnet"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T05:03:07.034187+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "07d69d2f0d0ee9d93caedfafd53bb4f1a9ae9bb3c5084ebd305e11b4bd3751ab", "fetched_at": "2026-08-28T04:04:12.825539+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dragnet-org/dragnet"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T05:03:07.034187+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "07d69d2f0d0ee9d93caedfafd53bb4f1a9ae9bb3c5084ebd305e11b4bd3751ab", "fetched_at": "2026-08-28T04:04:12.825539+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dragnet-org/dragnet"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T05:03:07.034187+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "07d69d2f0d0ee9d93caedfafd53bb4f1a9ae9bb3c5084ebd305e11b4bd3751ab", "fetched_at": "2026-08-28T04:04:12.825539+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dragnet-org/dragnet"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 30, "longevity": 100, "rhythm": 8}, "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": 5187, "days_push": 422, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 36, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}