{"adoption": {"forks": 423, "observed_at": "2026-08-28T04:05:22.616130+00:00", "stars": 1691}, "canonical_url": "https://ross.abutalabs.com/products/autocrawler", "card": {"archived": false, "artifact_type": "cli-tool", "description": "Google, Naver multiprocess image web crawler (Selenium)", "domain": ["crawlers", "machine-learning", "developer-tools"], "enriched": true, "function": ["web-scraping", "cli", "image-processing"], "health_score": 20, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["YoongiKim/AutoCrawler"], "name": "YoongiKim/AutoCrawler", "platform": ["python", "windows"], "pushed_at": "2024-04-15T10:15:21+00:00", "repo": "YoongiKim/AutoCrawler", "stars": 1691, "tags": ["image-crawler", "selenium", "chromedriver", "multiprocess", "dataset-collection", "google-images", "naver", "linux", "macos", "docker"], "topics": ["crawler", "selenium", "deep-learning", "image-crawler", "chromedriver", "bigdata", "google", "multiprocess", "thread", "customizable", "python"], "urls": [], "use_cases": ["scrape images from google image search for a dataset", "download training images for a deep learning model", "bulk download images by keyword list", "crawl naver images", "collect face images for face recognition training", "headless image crawling on a remote server"], "what_it_is": "A Python multiprocess image web crawler that downloads images from Google and Naver image search using Selenium and ChromeDriver. It is designed for building image datasets, with options for full-resolution downloads, face search mode, threading, proxies, and headless operation.", "when_to_avoid": ["you need a supported official image API instead of scraping", "you need sources other than Google or Naver without writing your own crawler module", "you need a maintained turnkey scraper with no breakage risk from site changes"], "when_to_choose": ["you need to quickly assemble an image dataset from search engines", "you want a customizable Selenium-based crawler you can patch when sites change", "you need multiprocess downloading with proxy support and headless server operation"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/autocrawler", "repo": "YoongiKim/AutoCrawler", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.616130+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:38:15.791319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29e79d56c18bb6deb9643bab02be23328e7a2b488746516ba272cdf8c31e07b", "fetched_at": "2026-08-28T04:05:22.616130+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YoongiKim/AutoCrawler"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.616130+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:38:15.791319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29e79d56c18bb6deb9643bab02be23328e7a2b488746516ba272cdf8c31e07b", "fetched_at": "2026-08-28T04:05:22.616130+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YoongiKim/AutoCrawler"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:38:15.791319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29e79d56c18bb6deb9643bab02be23328e7a2b488746516ba272cdf8c31e07b", "fetched_at": "2026-08-28T04:05:22.616130+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YoongiKim/AutoCrawler"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.616130+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.616130+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.616130+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:38:15.791319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29e79d56c18bb6deb9643bab02be23328e7a2b488746516ba272cdf8c31e07b", "fetched_at": "2026-08-28T04:05:22.616130+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YoongiKim/AutoCrawler"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.616130+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.616130+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:38:15.791319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29e79d56c18bb6deb9643bab02be23328e7a2b488746516ba272cdf8c31e07b", "fetched_at": "2026-08-28T04:05:22.616130+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YoongiKim/AutoCrawler"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.616130+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.616130+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.616130+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:38:15.791319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29e79d56c18bb6deb9643bab02be23328e7a2b488746516ba272cdf8c31e07b", "fetched_at": "2026-08-28T04:05:22.616130+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YoongiKim/AutoCrawler"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.616130+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.616130+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:38:15.791319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29e79d56c18bb6deb9643bab02be23328e7a2b488746516ba272cdf8c31e07b", "fetched_at": "2026-08-28T04:05:22.616130+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YoongiKim/AutoCrawler"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:38:15.791319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29e79d56c18bb6deb9643bab02be23328e7a2b488746516ba272cdf8c31e07b", "fetched_at": "2026-08-28T04:05:22.616130+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YoongiKim/AutoCrawler"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:38:15.791319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29e79d56c18bb6deb9643bab02be23328e7a2b488746516ba272cdf8c31e07b", "fetched_at": "2026-08-28T04:05:22.616130+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YoongiKim/AutoCrawler"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:38:15.791319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29e79d56c18bb6deb9643bab02be23328e7a2b488746516ba272cdf8c31e07b", "fetched_at": "2026-08-28T04:05:22.616130+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YoongiKim/AutoCrawler"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2842, "days_push": 870, "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}}