{"adoption": {"forks": 86, "observed_at": "2026-08-28T04:04:44.740030+00:00", "stars": 1442}, "canonical_url": "https://ross.abutalabs.com/products/scrapeghost", "card": {"archived": false, "artifact_type": "library", "description": "👻 Experimental library for scraping websites using OpenAI's GPT API.", "domain": ["crawlers", "developer-tools"], "enriched": true, "function": ["web-scraping", "llm-inference", "parser", "nlp"], "health_score": 61, "homepage": "https://jamesturk.github.io/scrapeghost/", "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "abandoned", "member_repos": ["jamesturk/scrapeghost"], "name": "jamesturk/scrapeghost", "platform": ["python"], "pushed_at": "2026-01-14T04:01:42+00:00", "repo": "jamesturk/scrapeghost", "stars": 1442, "tags": ["gpt", "openai", "html-to-", "schema-extraction", "experimental", "natural-language-processing"], "topics": ["gpt", "webscraping", "openai-api"], "urls": [], "use_cases": ["extract structured data from web pages using GPT", "scrape HTML into JSON without writing page-specific parsers", "define a schema in Python and let an LLM fill it from a URL", "validate LLM-extracted data against a pydantic schema", "check that scraped values actually appear on the page", "track and cap token costs when scraping with GPT"], "what_it_is": "scrapeghost is an experimental Python library that uses OpenAI's GPT models to scrape structured data from websites without writing page-specific code. It supports Python-based schema definitions, HTML preprocessing, JSON/schema validation, hallucination checks, and cost controls, but is explicitly no longer maintained.", "when_to_avoid": ["you need a maintained, production-ready scraping solution (the project is explicitly unmaintained)", "you want to avoid commercial LLM API costs and latency", "you need deterministic, guaranteed-accurate extraction", "your use case requires a permissive license (Hippocratic License 3.0)"], "when_to_choose": ["you want to experiment with LLM-based web scraping in Python", "you need one-off structured extraction from pages where writing selectors is impractical", "you want built-in cost tracking, budget limits, and hallucination checks for GPT scraping"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/scrapeghost", "repo": "jamesturk/scrapeghost", "role": "main", "score": 49}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.740030+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:36:24.448750+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "29d49c14c72aefde1fa23c07ae5bb29e2d8312c135de3661c81a523fc3139fb5", "fetched_at": "2026-08-28T04:04:44.740030+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jamesturk/scrapeghost"}, {"content_hash": "449cf648d21155d05a81ae10078283df08a651c429db6a8b153d8fddf4448cc0", "fetched_at": "2026-08-29T11:46:32.435461+00:00", "kind": "homepage", "missing": false, "url": "https://jamesturk.github.io/scrapeghost/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.740030+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:36:24.448750+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "29d49c14c72aefde1fa23c07ae5bb29e2d8312c135de3661c81a523fc3139fb5", "fetched_at": "2026-08-28T04:04:44.740030+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jamesturk/scrapeghost"}, {"content_hash": "449cf648d21155d05a81ae10078283df08a651c429db6a8b153d8fddf4448cc0", "fetched_at": "2026-08-29T11:46:32.435461+00:00", "kind": "homepage", "missing": false, "url": "https://jamesturk.github.io/scrapeghost/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:36:24.448750+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "29d49c14c72aefde1fa23c07ae5bb29e2d8312c135de3661c81a523fc3139fb5", "fetched_at": "2026-08-28T04:04:44.740030+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jamesturk/scrapeghost"}, {"content_hash": "449cf648d21155d05a81ae10078283df08a651c429db6a8b153d8fddf4448cc0", "fetched_at": "2026-08-29T11:46:32.435461+00:00", "kind": "homepage", "missing": false, "url": "https://jamesturk.github.io/scrapeghost/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.740030+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.740030+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.740030+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:36:24.448750+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "29d49c14c72aefde1fa23c07ae5bb29e2d8312c135de3661c81a523fc3139fb5", "fetched_at": "2026-08-28T04:04:44.740030+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jamesturk/scrapeghost"}, {"content_hash": "449cf648d21155d05a81ae10078283df08a651c429db6a8b153d8fddf4448cc0", "fetched_at": "2026-08-29T11:46:32.435461+00:00", "kind": "homepage", "missing": false, "url": "https://jamesturk.github.io/scrapeghost/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.740030+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.740030+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:36:24.448750+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "29d49c14c72aefde1fa23c07ae5bb29e2d8312c135de3661c81a523fc3139fb5", "fetched_at": "2026-08-28T04:04:44.740030+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jamesturk/scrapeghost"}, {"content_hash": "449cf648d21155d05a81ae10078283df08a651c429db6a8b153d8fddf4448cc0", "fetched_at": "2026-08-29T11:46:32.435461+00:00", "kind": "homepage", "missing": false, "url": "https://jamesturk.github.io/scrapeghost/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.740030+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.740030+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.740030+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:36:24.448750+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "29d49c14c72aefde1fa23c07ae5bb29e2d8312c135de3661c81a523fc3139fb5", "fetched_at": "2026-08-28T04:04:44.740030+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jamesturk/scrapeghost"}, {"content_hash": "449cf648d21155d05a81ae10078283df08a651c429db6a8b153d8fddf4448cc0", "fetched_at": "2026-08-29T11:46:32.435461+00:00", "kind": "homepage", "missing": false, "url": "https://jamesturk.github.io/scrapeghost/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.740030+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.740030+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:36:24.448750+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "29d49c14c72aefde1fa23c07ae5bb29e2d8312c135de3661c81a523fc3139fb5", "fetched_at": "2026-08-28T04:04:44.740030+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jamesturk/scrapeghost"}, {"content_hash": "449cf648d21155d05a81ae10078283df08a651c429db6a8b153d8fddf4448cc0", "fetched_at": "2026-08-29T11:46:32.435461+00:00", "kind": "homepage", "missing": false, "url": "https://jamesturk.github.io/scrapeghost/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:36:24.448750+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "29d49c14c72aefde1fa23c07ae5bb29e2d8312c135de3661c81a523fc3139fb5", "fetched_at": "2026-08-28T04:04:44.740030+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jamesturk/scrapeghost"}, {"content_hash": "449cf648d21155d05a81ae10078283df08a651c429db6a8b153d8fddf4448cc0", "fetched_at": "2026-08-29T11:46:32.435461+00:00", "kind": "homepage", "missing": false, "url": "https://jamesturk.github.io/scrapeghost/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:36:24.448750+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "29d49c14c72aefde1fa23c07ae5bb29e2d8312c135de3661c81a523fc3139fb5", "fetched_at": "2026-08-28T04:04:44.740030+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jamesturk/scrapeghost"}, {"content_hash": "449cf648d21155d05a81ae10078283df08a651c429db6a8b153d8fddf4448cc0", "fetched_at": "2026-08-29T11:46:32.435461+00:00", "kind": "homepage", "missing": false, "url": "https://jamesturk.github.io/scrapeghost/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:36:24.448750+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "29d49c14c72aefde1fa23c07ae5bb29e2d8312c135de3661c81a523fc3139fb5", "fetched_at": "2026-08-28T04:04:44.740030+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jamesturk/scrapeghost"}, {"content_hash": "449cf648d21155d05a81ae10078283df08a651c429db6a8b153d8fddf4448cc0", "fetched_at": "2026-08-29T11:46:32.435461+00:00", "kind": "homepage", "missing": false, "url": "https://jamesturk.github.io/scrapeghost/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 62, "longevity": 90, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1265, "days_push": 231, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 49, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}