{"adoption": {"forks": 92, "observed_at": "2026-08-28T04:04:34.852129+00:00", "stars": 1385}, "canonical_url": "https://ross.abutalabs.com/products/mlscraper", "card": {"archived": false, "artifact_type": "library", "description": "🤖 Scrape data from HTML websites automatically by just providing examples", "domain": ["crawlers", "web-development", "machine-learning", "data-science"], "enriched": true, "function": ["web-scraping", "machine-learning", "parser", "data-science"], "health_score": 20, "homepage": "https://pypi.org/project/mlscraper/", "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["lorey/mlscraper"], "name": "lorey/mlscraper", "platform": ["python", "cross-platform"], "pushed_at": "2024-03-17T08:12:02+00:00", "repo": "lorey/mlscraper", "stars": 1385, "tags": ["html-extraction", "automatic-scraping", "example-based-training", "structured-data-extraction"], "topics": ["scraping", "crawling", "html", "machine-learning", "extraction-engine", "scraper", "crawler", "crawler-python"], "urls": [], "use_cases": ["scrape structured data from html pages without writing css selectors", "extract data from websites by providing example values", "train a scraper from sample data and apply it to new pages", "automatically find extraction rules for html dom nodes", "convert html pages into clean dictionaries of data", "build a web scraper without manual selector engineering"], "what_it_is": "mlscraper is a Python library that automatically extracts structured data from HTML pages using machine learning. Instead of writing CSS selectors or XPath rules manually, you provide a few example outputs and it learns the extraction rules to apply to new pages.", "when_to_avoid": ["you need to scrape JavaScript-rendered single-page applications rather than static HTML", "you need a no-code browser-based scraping tool with a visual interface", "you have no example data available to train the extractor", "you need a battle-tested 1.0 release, since the stable PyPI version is still 0.x"], "when_to_choose": ["you want to scrape data from similar HTML pages but don't want to hand-write selectors", "you have a few example outputs and want the rules figured out automatically", "you prefer an open-source Python alternative to point-and-click scraping services", "you need to extract data repeatedly from pages with consistent structure"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/mlscraper", "repo": "lorey/mlscraper", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.852129+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:39:57.362451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e29b486a147b6e4bf1c5930be2398b1c9349934105c215ec56c54deddad4b1b", "fetched_at": "2026-08-28T04:04:34.852129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lorey/mlscraper"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:55:34.900285+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/mlscraper/"}, {"content_hash": "49ceb33e03f120d4d53318468c3fc3357174f8e6d02d183a06153b03f1c3d333", "fetched_at": "2026-08-29T11:55:34.909537+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mlscraper/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.852129+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:39:57.362451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e29b486a147b6e4bf1c5930be2398b1c9349934105c215ec56c54deddad4b1b", "fetched_at": "2026-08-28T04:04:34.852129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lorey/mlscraper"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:55:34.900285+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/mlscraper/"}, {"content_hash": "49ceb33e03f120d4d53318468c3fc3357174f8e6d02d183a06153b03f1c3d333", "fetched_at": "2026-08-29T11:55:34.909537+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mlscraper/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:39:57.362451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e29b486a147b6e4bf1c5930be2398b1c9349934105c215ec56c54deddad4b1b", "fetched_at": "2026-08-28T04:04:34.852129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lorey/mlscraper"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:55:34.900285+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/mlscraper/"}, {"content_hash": "49ceb33e03f120d4d53318468c3fc3357174f8e6d02d183a06153b03f1c3d333", "fetched_at": "2026-08-29T11:55:34.909537+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mlscraper/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.852129+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.852129+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.852129+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:39:57.362451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e29b486a147b6e4bf1c5930be2398b1c9349934105c215ec56c54deddad4b1b", "fetched_at": "2026-08-28T04:04:34.852129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lorey/mlscraper"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:55:34.900285+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/mlscraper/"}, {"content_hash": "49ceb33e03f120d4d53318468c3fc3357174f8e6d02d183a06153b03f1c3d333", "fetched_at": "2026-08-29T11:55:34.909537+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mlscraper/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.852129+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.852129+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:39:57.362451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e29b486a147b6e4bf1c5930be2398b1c9349934105c215ec56c54deddad4b1b", "fetched_at": "2026-08-28T04:04:34.852129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lorey/mlscraper"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:55:34.900285+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/mlscraper/"}, {"content_hash": "49ceb33e03f120d4d53318468c3fc3357174f8e6d02d183a06153b03f1c3d333", "fetched_at": "2026-08-29T11:55:34.909537+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mlscraper/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.852129+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.852129+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.852129+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:39:57.362451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e29b486a147b6e4bf1c5930be2398b1c9349934105c215ec56c54deddad4b1b", "fetched_at": "2026-08-28T04:04:34.852129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lorey/mlscraper"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:55:34.900285+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/mlscraper/"}, {"content_hash": "49ceb33e03f120d4d53318468c3fc3357174f8e6d02d183a06153b03f1c3d333", "fetched_at": "2026-08-29T11:55:34.909537+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mlscraper/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.852129+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.852129+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:39:57.362451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e29b486a147b6e4bf1c5930be2398b1c9349934105c215ec56c54deddad4b1b", "fetched_at": "2026-08-28T04:04:34.852129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lorey/mlscraper"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:55:34.900285+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/mlscraper/"}, {"content_hash": "49ceb33e03f120d4d53318468c3fc3357174f8e6d02d183a06153b03f1c3d333", "fetched_at": "2026-08-29T11:55:34.909537+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mlscraper/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:39:57.362451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e29b486a147b6e4bf1c5930be2398b1c9349934105c215ec56c54deddad4b1b", "fetched_at": "2026-08-28T04:04:34.852129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lorey/mlscraper"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:55:34.900285+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/mlscraper/"}, {"content_hash": "49ceb33e03f120d4d53318468c3fc3357174f8e6d02d183a06153b03f1c3d333", "fetched_at": "2026-08-29T11:55:34.909537+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mlscraper/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:39:57.362451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e29b486a147b6e4bf1c5930be2398b1c9349934105c215ec56c54deddad4b1b", "fetched_at": "2026-08-28T04:04:34.852129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lorey/mlscraper"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:55:34.900285+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/mlscraper/"}, {"content_hash": "49ceb33e03f120d4d53318468c3fc3357174f8e6d02d183a06153b03f1c3d333", "fetched_at": "2026-08-29T11:55:34.909537+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mlscraper/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:39:57.362451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e29b486a147b6e4bf1c5930be2398b1c9349934105c215ec56c54deddad4b1b", "fetched_at": "2026-08-28T04:04:34.852129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lorey/mlscraper"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:55:34.900285+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/mlscraper/"}, {"content_hash": "49ceb33e03f120d4d53318468c3fc3357174f8e6d02d183a06153b03f1c3d333", "fetched_at": "2026-08-29T11:55:34.909537+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mlscraper/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2225, "days_push": 899, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}