{"adoption": {"forks": 817, "observed_at": "2026-08-28T04:10:09.371042+00:00", "stars": 7904}, "canonical_url": "https://ross.abutalabs.com/products/autoscraper", "card": {"archived": false, "artifact_type": "library", "description": "A Smart, Automatic, Fast and Lightweight Web Scraper for Python", "domain": ["crawlers", "web-development", "machine-learning"], "enriched": true, "function": ["web-scraping", "machine-learning", "parser"], "health_score": 77, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "stable", "member_repos": ["alirezamika/autoscraper"], "name": "alirezamika/autoscraper", "platform": ["python", "cross-platform"], "pushed_at": "2026-07-29T17:17:55+00:00", "repo": "alirezamika/autoscraper", "stars": 7904, "tags": ["scraper", "automatic-rule-learning", "crawler", "data-extraction", "automation"], "topics": ["scraping", "scraper", "scrape", "webscraping", "crawler", "web-scraping", "ai", "artificial-intelligence", "python", "webautomation", "automation", "machine-learning"], "urls": [], "use_cases": ["scrape all post titles from a stackoverflow question page", "extract live stock prices from yahoo finance", "learn scraping rules from example data instead of writing css selectors", "reuse a learned scraper on new urls to get similar content", "scrape product prices and names from e-commerce pages", "extract urls or html tag values from a web page automatically"], "what_it_is": "AutoScraper is a Python library that automatically learns scraping rules from a URL or HTML content plus a list of sample data you want to extract. The learned scraper object can then be reused on new pages to fetch similar elements or exact matching values.", "when_to_avoid": ["you need javascript-rendered page scraping out of the box", "you need large-scale distributed crawling infrastructure", "you need full control over parsing logic for complex or highly dynamic sites"], "when_to_choose": ["you want to scrape structured data without hand-writing selectors or xpath", "you have sample values of what you want and need rules generated automatically", "you need a lightweight python library for repeated scraping of similar pages"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/autoscraper", "repo": "alirezamika/autoscraper", "role": "main", "score": 66}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:09.371042+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:33:23.424014+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2e9a288cfdd69b2c401e6e381318f0649f51b7e698073fe2c386edc7dbdb3db7", "fetched_at": "2026-08-28T04:10:09.371042+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alirezamika/autoscraper"}, {"content_hash": "ea7b476a236fad32257c60cf7625d5a13f747b836ec772a595707421fb1ca0fa", "fetched_at": "2026-08-29T08:30:02.983747+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/autoscraper/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:09.371042+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:33:23.424014+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2e9a288cfdd69b2c401e6e381318f0649f51b7e698073fe2c386edc7dbdb3db7", "fetched_at": "2026-08-28T04:10:09.371042+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alirezamika/autoscraper"}, {"content_hash": "ea7b476a236fad32257c60cf7625d5a13f747b836ec772a595707421fb1ca0fa", "fetched_at": "2026-08-29T08:30:02.983747+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/autoscraper/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:33:23.424014+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2e9a288cfdd69b2c401e6e381318f0649f51b7e698073fe2c386edc7dbdb3db7", "fetched_at": "2026-08-28T04:10:09.371042+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alirezamika/autoscraper"}, {"content_hash": "ea7b476a236fad32257c60cf7625d5a13f747b836ec772a595707421fb1ca0fa", "fetched_at": "2026-08-29T08:30:02.983747+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/autoscraper/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:09.371042+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:09.371042+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:09.371042+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:33:23.424014+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2e9a288cfdd69b2c401e6e381318f0649f51b7e698073fe2c386edc7dbdb3db7", "fetched_at": "2026-08-28T04:10:09.371042+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alirezamika/autoscraper"}, {"content_hash": "ea7b476a236fad32257c60cf7625d5a13f747b836ec772a595707421fb1ca0fa", "fetched_at": "2026-08-29T08:30:02.983747+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/autoscraper/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:09.371042+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:09.371042+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:33:23.424014+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2e9a288cfdd69b2c401e6e381318f0649f51b7e698073fe2c386edc7dbdb3db7", "fetched_at": "2026-08-28T04:10:09.371042+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alirezamika/autoscraper"}, {"content_hash": "ea7b476a236fad32257c60cf7625d5a13f747b836ec772a595707421fb1ca0fa", "fetched_at": "2026-08-29T08:30:02.983747+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/autoscraper/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:09.371042+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:09.371042+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:09.371042+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:33:23.424014+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2e9a288cfdd69b2c401e6e381318f0649f51b7e698073fe2c386edc7dbdb3db7", "fetched_at": "2026-08-28T04:10:09.371042+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alirezamika/autoscraper"}, {"content_hash": "ea7b476a236fad32257c60cf7625d5a13f747b836ec772a595707421fb1ca0fa", "fetched_at": "2026-08-29T08:30:02.983747+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/autoscraper/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:09.371042+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:09.371042+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:33:23.424014+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2e9a288cfdd69b2c401e6e381318f0649f51b7e698073fe2c386edc7dbdb3db7", "fetched_at": "2026-08-28T04:10:09.371042+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alirezamika/autoscraper"}, {"content_hash": "ea7b476a236fad32257c60cf7625d5a13f747b836ec772a595707421fb1ca0fa", "fetched_at": "2026-08-29T08:30:02.983747+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/autoscraper/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:33:23.424014+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2e9a288cfdd69b2c401e6e381318f0649f51b7e698073fe2c386edc7dbdb3db7", "fetched_at": "2026-08-28T04:10:09.371042+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alirezamika/autoscraper"}, {"content_hash": "ea7b476a236fad32257c60cf7625d5a13f747b836ec772a595707421fb1ca0fa", "fetched_at": "2026-08-29T08:30:02.983747+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/autoscraper/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:33:23.424014+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2e9a288cfdd69b2c401e6e381318f0649f51b7e698073fe2c386edc7dbdb3db7", "fetched_at": "2026-08-28T04:10:09.371042+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alirezamika/autoscraper"}, {"content_hash": "ea7b476a236fad32257c60cf7625d5a13f747b836ec772a595707421fb1ca0fa", "fetched_at": "2026-08-29T08:30:02.983747+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/autoscraper/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:33:23.424014+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2e9a288cfdd69b2c401e6e381318f0649f51b7e698073fe2c386edc7dbdb3db7", "fetched_at": "2026-08-28T04:10:09.371042+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alirezamika/autoscraper"}, {"content_hash": "ea7b476a236fad32257c60cf7625d5a13f747b836ec772a595707421fb1ca0fa", "fetched_at": "2026-08-29T08:30:02.983747+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/autoscraper/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 95, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2193, "days_push": 35, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 66, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}