{"adoption": {"forks": 272, "observed_at": "2026-08-28T04:05:48.789310+00:00", "stars": 1883}, "canonical_url": "https://ross.abutalabs.com/products/scrapely", "card": {"archived": false, "artifact_type": "library", "description": "A pure-python HTML screen-scraping library", "domain": ["crawlers", "web-development"], "enriched": true, "function": ["web-scraping", "parser", "nlp"], "health_score": 20, "homepage": null, "language": "HTML", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["scrapy/scrapely"], "name": "scrapy/scrapely", "platform": ["python", "cross-platform", "cli"], "pushed_at": "2022-04-04T10:53:21+00:00", "repo": "scrapy/scrapely", "stars": 1883, "tags": ["html-extraction", "template-based-scraping", "annotation-based-training", "no-xpath", "data-engineering"], "topics": [], "urls": [], "use_cases": ["extract structured data from html pages", "train a scraper from example pages and expected fields", "scrape similar pages without writing xpaths or regexes", "build template-based web scrapers", "power annotation-driven scraping tools like portia"], "what_it_is": "Scrapely is a pure-Python library for extracting structured data from HTML pages. It learns a parser from example pages annotated with the data to extract, then applies that parser to scrape similar pages without xpaths or regexes.", "when_to_avoid": ["you need a full crawling framework like scrapy", "the project is unmaintained and you need modern python support or fixes", "you need javascript-rendered page extraction"], "when_to_choose": []}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/scrapely", "repo": "scrapy/scrapely", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.789310+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:13:42.303857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3f88b1df029df0d548a208f1ab03001b0eede8be1aa171a28a656bf0fe055ea6", "fetched_at": "2026-08-28T04:05:48.789310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapy/scrapely"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.789310+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:13:42.303857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3f88b1df029df0d548a208f1ab03001b0eede8be1aa171a28a656bf0fe055ea6", "fetched_at": "2026-08-28T04:05:48.789310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapy/scrapely"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:13:42.303857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3f88b1df029df0d548a208f1ab03001b0eede8be1aa171a28a656bf0fe055ea6", "fetched_at": "2026-08-28T04:05:48.789310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapy/scrapely"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.789310+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.789310+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.789310+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:13:42.303857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3f88b1df029df0d548a208f1ab03001b0eede8be1aa171a28a656bf0fe055ea6", "fetched_at": "2026-08-28T04:05:48.789310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapy/scrapely"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.789310+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.789310+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:13:42.303857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3f88b1df029df0d548a208f1ab03001b0eede8be1aa171a28a656bf0fe055ea6", "fetched_at": "2026-08-28T04:05:48.789310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapy/scrapely"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.789310+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.789310+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.789310+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:13:42.303857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3f88b1df029df0d548a208f1ab03001b0eede8be1aa171a28a656bf0fe055ea6", "fetched_at": "2026-08-28T04:05:48.789310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapy/scrapely"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.789310+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.789310+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:13:42.303857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3f88b1df029df0d548a208f1ab03001b0eede8be1aa171a28a656bf0fe055ea6", "fetched_at": "2026-08-28T04:05:48.789310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapy/scrapely"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:13:42.303857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3f88b1df029df0d548a208f1ab03001b0eede8be1aa171a28a656bf0fe055ea6", "fetched_at": "2026-08-28T04:05:48.789310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapy/scrapely"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:13:42.303857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3f88b1df029df0d548a208f1ab03001b0eede8be1aa171a28a656bf0fe055ea6", "fetched_at": "2026-08-28T04:05:48.789310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapy/scrapely"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:13:42.303857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3f88b1df029df0d548a208f1ab03001b0eede8be1aa171a28a656bf0fe055ea6", "fetched_at": "2026-08-28T04:05:48.789310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapy/scrapely"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 5616, "days_push": 1612, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}