{"adoption": {"forks": 1385, "observed_at": "2026-08-28T04:10:31.528602+00:00", "stars": 9504}, "canonical_url": "https://ross.abutalabs.com/products/portia", "card": {"archived": true, "artifact_type": "application", "description": "Visual scraping for Scrapy", "domain": ["crawlers", "web-development", "developer-tools"], "enriched": true, "function": ["web-scraping", "gui", "parser"], "health_score": 10, "homepage": null, "language": "Python", "license": "BSD-3-Clause", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["scrapinghub/portia"], "name": "scrapinghub/portia", "platform": ["python", "self-hosted"], "pushed_at": "2024-06-26T19:43:46+00:00", "repo": "scrapinghub/portia", "stars": 9504, "tags": ["visual-scraping", "scrapy", "annotation", "no-code", "data-extraction", "docker", "web-server"], "topics": [], "urls": [], "use_cases": ["scrape websites without writing code", "extract structured data from web pages visually", "annotate a page and scrape similar pages", "build scrapy spiders through a visual interface", "collect product or listing data from e-commerce sites"], "what_it_is": "Portia is a visual web scraping tool from Scrapinghub built on Scrapy that lets users annotate web pages in a browser to define data extraction without programming. It generalizes annotations to scrape data from similar pages and is typically run via Docker.", "when_to_avoid": ["you need a maintained tool with active development and modern browser support", "you only need a lightweight headless scraping library rather than a full application", "you require JavaScript-heavy sites needing recent rendering features"], "when_to_choose": ["you need to scrape websites but have no programming knowledge", "you already use Scrapy and want a visual annotation workflow", "you want a self-hosted scraping IDE with Docker deployment"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/portia", "repo": "scrapinghub/portia", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:31.528602+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:22:01.324767+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eeca26c9253f2bdceb9eea7d84fad95c8b80460715c8232c95ddb6e6200a61ae", "fetched_at": "2026-08-28T04:10:31.528602+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapinghub/portia"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:31.528602+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:22:01.324767+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eeca26c9253f2bdceb9eea7d84fad95c8b80460715c8232c95ddb6e6200a61ae", "fetched_at": "2026-08-28T04:10:31.528602+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapinghub/portia"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:22:01.324767+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eeca26c9253f2bdceb9eea7d84fad95c8b80460715c8232c95ddb6e6200a61ae", "fetched_at": "2026-08-28T04:10:31.528602+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapinghub/portia"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:31.528602+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:31.528602+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:31.528602+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:22:01.324767+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eeca26c9253f2bdceb9eea7d84fad95c8b80460715c8232c95ddb6e6200a61ae", "fetched_at": "2026-08-28T04:10:31.528602+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapinghub/portia"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:31.528602+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:31.528602+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:22:01.324767+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eeca26c9253f2bdceb9eea7d84fad95c8b80460715c8232c95ddb6e6200a61ae", "fetched_at": "2026-08-28T04:10:31.528602+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapinghub/portia"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:31.528602+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:31.528602+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:31.528602+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:22:01.324767+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eeca26c9253f2bdceb9eea7d84fad95c8b80460715c8232c95ddb6e6200a61ae", "fetched_at": "2026-08-28T04:10:31.528602+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapinghub/portia"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:31.528602+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:31.528602+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:22:01.324767+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eeca26c9253f2bdceb9eea7d84fad95c8b80460715c8232c95ddb6e6200a61ae", "fetched_at": "2026-08-28T04:10:31.528602+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapinghub/portia"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:22:01.324767+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eeca26c9253f2bdceb9eea7d84fad95c8b80460715c8232c95ddb6e6200a61ae", "fetched_at": "2026-08-28T04:10:31.528602+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapinghub/portia"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:22:01.324767+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eeca26c9253f2bdceb9eea7d84fad95c8b80460715c8232c95ddb6e6200a61ae", "fetched_at": "2026-08-28T04:10:31.528602+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapinghub/portia"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:22:01.324767+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eeca26c9253f2bdceb9eea7d84fad95c8b80460715c8232c95ddb6e6200a61ae", "fetched_at": "2026-08-28T04:10:31.528602+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scrapinghub/portia"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4548, "days_push": 798, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}