{"adoption": {"forks": 1147, "observed_at": "2026-08-28T04:08:05.704779+00:00", "stars": 3462}, "canonical_url": "https://ross.abutalabs.com/products/phpspider", "card": {"archived": false, "artifact_type": "framework", "description": "《我用爬虫一天时间“偷了”知乎一百万用户，只为证明PHP是世界上最好的语言 》所使用的程序", "domain": ["crawlers", "web-development"], "enriched": true, "function": ["web-scraping", "parser", "concurrency"], "health_score": 20, "homepage": null, "language": "PHP", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["owner888/phpspider"], "name": "owner888/phpspider", "platform": ["php", "cli"], "pushed_at": "2024-12-15T03:16:14+00:00", "repo": "owner888/phpspider", "stars": 3462, "tags": ["crawler-framework", "multi-process", "xpath-extraction", "php", "automation", "linux"], "topics": ["php", "phpspider"], "urls": [], "use_cases": ["scrape websites with php", "build a web crawler in php", "extract article content from web pages", "crawl sites that require login or captcha handling", "collect data from forums and content sites"], "what_it_is": "phpspider is a PHP web crawling framework that lets developers build scrapers with a simple config array, handling multi-process workers, login, and anti-blocking concerns. It ships with demo crawl rules for specific sites and runs from the command line.", "when_to_avoid": ["you need a modern, actively maintained scraping stack", "your project requires JavaScript-rendered pages", "you need a permissive license for commercial use"], "when_to_choose": ["you are a PHP developer wanting a quick config-driven crawler", "you need multi-process scraping with minimal boilerplate", "you want ready-made crawl rules for common sites"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/phpspider", "repo": "owner888/phpspider", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.704779+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:36:54.553387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1dcee82261209b6244e69e184178b43315ca4762e581bd72244fa5a33dfcb980", "fetched_at": "2026-08-28T04:08:05.704779+00:00", "kind": "readme", "missing": false, "url": "https://github.com/owner888/phpspider"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.704779+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:36:54.553387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1dcee82261209b6244e69e184178b43315ca4762e581bd72244fa5a33dfcb980", "fetched_at": "2026-08-28T04:08:05.704779+00:00", "kind": "readme", "missing": false, "url": "https://github.com/owner888/phpspider"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:36:54.553387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1dcee82261209b6244e69e184178b43315ca4762e581bd72244fa5a33dfcb980", "fetched_at": "2026-08-28T04:08:05.704779+00:00", "kind": "readme", "missing": false, "url": "https://github.com/owner888/phpspider"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.704779+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.704779+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.704779+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:36:54.553387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1dcee82261209b6244e69e184178b43315ca4762e581bd72244fa5a33dfcb980", "fetched_at": "2026-08-28T04:08:05.704779+00:00", "kind": "readme", "missing": false, "url": "https://github.com/owner888/phpspider"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.704779+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.704779+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:36:54.553387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1dcee82261209b6244e69e184178b43315ca4762e581bd72244fa5a33dfcb980", "fetched_at": "2026-08-28T04:08:05.704779+00:00", "kind": "readme", "missing": false, "url": "https://github.com/owner888/phpspider"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.704779+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.704779+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.704779+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:36:54.553387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1dcee82261209b6244e69e184178b43315ca4762e581bd72244fa5a33dfcb980", "fetched_at": "2026-08-28T04:08:05.704779+00:00", "kind": "readme", "missing": false, "url": "https://github.com/owner888/phpspider"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.704779+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.704779+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:36:54.553387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1dcee82261209b6244e69e184178b43315ca4762e581bd72244fa5a33dfcb980", "fetched_at": "2026-08-28T04:08:05.704779+00:00", "kind": "readme", "missing": false, "url": "https://github.com/owner888/phpspider"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:36:54.553387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1dcee82261209b6244e69e184178b43315ca4762e581bd72244fa5a33dfcb980", "fetched_at": "2026-08-28T04:08:05.704779+00:00", "kind": "readme", "missing": false, "url": "https://github.com/owner888/phpspider"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:36:54.553387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1dcee82261209b6244e69e184178b43315ca4762e581bd72244fa5a33dfcb980", "fetched_at": "2026-08-28T04:08:05.704779+00:00", "kind": "readme", "missing": false, "url": "https://github.com/owner888/phpspider"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:36:54.553387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1dcee82261209b6244e69e184178b43315ca4762e581bd72244fa5a33dfcb980", "fetched_at": "2026-08-28T04:08:05.704779+00:00", "kind": "readme", "missing": false, "url": "https://github.com/owner888/phpspider"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "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": 4046, "days_push": 626, "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}}