{"adoption": {"forks": 1016, "observed_at": "2026-08-28T04:07:52.188157+00:00", "stars": 3253}, "canonical_url": "https://ross.abutalabs.com/products/scrapy-examples", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Multifarious Scrapy examples. Spiders for alexa / amazon / douban / douyu / github / linkedin etc.", "domain": ["crawlers", "developer-tools", "tutorials"], "enriched": true, "function": ["web-scraping", "developer-tools"], "health_score": 20, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["geekan/scrapy-examples"], "name": "geekan/scrapy-examples", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2023-11-03T06:14:04+00:00", "repo": "geekan/scrapy-examples", "stars": 3253, "tags": ["scrapy", "spiders", "example-code", "proxy-support", "web-crawling"], "topics": [], "urls": [], "use_cases": ["learn scrapy by example", "scrape book listings from douban", "write a spider quickly with css rules", "scrape with rotating proxies and user agents", "bootstrap a new scrapy project", "extract data from linkedin or zhihu profiles"], "what_it_is": "A collection of example Scrapy spiders demonstrating web scraping patterns for sites like Douban, LinkedIn, Zhihu, Alexa, and GitHub. It includes reusable helpers such as CSS-rule-based parsing and proxy/agent middleware to speed up writing new spiders.", "when_to_avoid": ["you need a production scraping framework rather than example code", "you require a maintained project with a license and active support", "you are scraping sites whose terms of service prohibit it"], "when_to_choose": ["you are learning Scrapy and want working spider examples", "you need a template with proxy and user-agent middleware already wired up", "you want a quick project scaffold for a new scraper"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/scrapy-examples", "repo": "geekan/scrapy-examples", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:52.188157+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:24:24.442305+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "96e205c717e1ec806f7a9d0da399c4563cfb4ce46b51d4d9507546f76e0b58fb", "fetched_at": "2026-08-28T04:07:52.188157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/geekan/scrapy-examples"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:52.188157+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:24:24.442305+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "96e205c717e1ec806f7a9d0da399c4563cfb4ce46b51d4d9507546f76e0b58fb", "fetched_at": "2026-08-28T04:07:52.188157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/geekan/scrapy-examples"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:24:24.442305+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "96e205c717e1ec806f7a9d0da399c4563cfb4ce46b51d4d9507546f76e0b58fb", "fetched_at": "2026-08-28T04:07:52.188157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/geekan/scrapy-examples"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:52.188157+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:52.188157+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:52.188157+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:24:24.442305+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "96e205c717e1ec806f7a9d0da399c4563cfb4ce46b51d4d9507546f76e0b58fb", "fetched_at": "2026-08-28T04:07:52.188157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/geekan/scrapy-examples"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:52.188157+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:52.188157+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:24:24.442305+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "96e205c717e1ec806f7a9d0da399c4563cfb4ce46b51d4d9507546f76e0b58fb", "fetched_at": "2026-08-28T04:07:52.188157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/geekan/scrapy-examples"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:52.188157+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:52.188157+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:52.188157+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:24:24.442305+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "96e205c717e1ec806f7a9d0da399c4563cfb4ce46b51d4d9507546f76e0b58fb", "fetched_at": "2026-08-28T04:07:52.188157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/geekan/scrapy-examples"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:52.188157+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:52.188157+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:24:24.442305+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "96e205c717e1ec806f7a9d0da399c4563cfb4ce46b51d4d9507546f76e0b58fb", "fetched_at": "2026-08-28T04:07:52.188157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/geekan/scrapy-examples"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:24:24.442305+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "96e205c717e1ec806f7a9d0da399c4563cfb4ce46b51d4d9507546f76e0b58fb", "fetched_at": "2026-08-28T04:07:52.188157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/geekan/scrapy-examples"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:24:24.442305+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "96e205c717e1ec806f7a9d0da399c4563cfb4ce46b51d4d9507546f76e0b58fb", "fetched_at": "2026-08-28T04:07:52.188157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/geekan/scrapy-examples"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:24:24.442305+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "96e205c717e1ec806f7a9d0da399c4563cfb4ce46b51d4d9507546f76e0b58fb", "fetched_at": "2026-08-28T04:07:52.188157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/geekan/scrapy-examples"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+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": 4617, "days_push": 1034, "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}}