{"adoption": {"forks": 200, "observed_at": "2026-08-28T04:03:16.064854+00:00", "stars": 1022}, "canonical_url": "https://ross.abutalabs.com/products/top250movie_douban", "card": {"archived": false, "artifact_type": "learning-resource", "description": "TOP250豆瓣电影短评：Scrapy 爬虫+数据清理/分析+构建中文文本情感分析模型", "domain": ["data-science", "crawlers", "tutorials"], "enriched": true, "function": ["web-scraping", "nlp", "data-science", "data-visualization", "machine-learning"], "health_score": 20, "homepage": null, "language": "Jupyter Notebook", "license": "BSD-2-Clause", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["iphysresearch/TOP250movie_douban"], "name": "iphysresearch/TOP250movie_douban", "platform": ["python"], "pushed_at": "2022-07-23T06:46:00+00:00", "repo": "iphysresearch/TOP250movie_douban", "stars": 1022, "tags": ["scrapy", "sentiment-analysis", "chinese-text", "douban", "jupyter-notebook", "text-classification", "word-cloud", "natural-language-processing"], "topics": ["project"], "urls": [], "use_cases": ["learn web scraping with scrapy", "chinese sentiment analysis example", "analyze douban movie reviews", "text classification tutorial with cnn rnn", "data cleaning and visualization practice project", "build a naive bayes text classifier"], "what_it_is": "A Jupyter Notebook-based educational project that scrapes Douban Top 250 movie short reviews with Scrapy, then performs data cleaning, statistical analysis, visualization, and builds Chinese text sentiment classification models (Naive Bayes, SVM, fastText, CNN, RNN, GRU). It serves as an end-to-end data science project example.", "when_to_avoid": ["production web scraping of Douban at scale", "a maintained sentiment analysis library", "non-Chinese text analysis"], "when_to_choose": ["learning the full pipeline from scraping to NLP modeling", "studying Chinese text classification with multiple model approaches", "looking for a complete data science project example"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/top250movie_douban", "repo": "iphysresearch/TOP250movie_douban", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.064854+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:08:44.714318+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e605f2cb4047ad5778dbcfe6a9716d7537c6d288d413ea370ffa2ddbd212766f", "fetched_at": "2026-08-28T04:03:16.064854+00:00", "kind": "readme", "missing": false, "url": "https://github.com/iphysresearch/TOP250movie_douban"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.064854+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:08:44.714318+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e605f2cb4047ad5778dbcfe6a9716d7537c6d288d413ea370ffa2ddbd212766f", "fetched_at": "2026-08-28T04:03:16.064854+00:00", "kind": "readme", "missing": false, "url": "https://github.com/iphysresearch/TOP250movie_douban"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:08:44.714318+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e605f2cb4047ad5778dbcfe6a9716d7537c6d288d413ea370ffa2ddbd212766f", "fetched_at": "2026-08-28T04:03:16.064854+00:00", "kind": "readme", "missing": false, "url": "https://github.com/iphysresearch/TOP250movie_douban"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.064854+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.064854+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.064854+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:08:44.714318+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e605f2cb4047ad5778dbcfe6a9716d7537c6d288d413ea370ffa2ddbd212766f", "fetched_at": "2026-08-28T04:03:16.064854+00:00", "kind": "readme", "missing": false, "url": "https://github.com/iphysresearch/TOP250movie_douban"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.064854+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.064854+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:08:44.714318+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e605f2cb4047ad5778dbcfe6a9716d7537c6d288d413ea370ffa2ddbd212766f", "fetched_at": "2026-08-28T04:03:16.064854+00:00", "kind": "readme", "missing": false, "url": "https://github.com/iphysresearch/TOP250movie_douban"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.064854+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.064854+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.064854+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:08:44.714318+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e605f2cb4047ad5778dbcfe6a9716d7537c6d288d413ea370ffa2ddbd212766f", "fetched_at": "2026-08-28T04:03:16.064854+00:00", "kind": "readme", "missing": false, "url": "https://github.com/iphysresearch/TOP250movie_douban"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.064854+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.064854+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:08:44.714318+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e605f2cb4047ad5778dbcfe6a9716d7537c6d288d413ea370ffa2ddbd212766f", "fetched_at": "2026-08-28T04:03:16.064854+00:00", "kind": "readme", "missing": false, "url": "https://github.com/iphysresearch/TOP250movie_douban"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:08:44.714318+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e605f2cb4047ad5778dbcfe6a9716d7537c6d288d413ea370ffa2ddbd212766f", "fetched_at": "2026-08-28T04:03:16.064854+00:00", "kind": "readme", "missing": false, "url": "https://github.com/iphysresearch/TOP250movie_douban"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:08:44.714318+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e605f2cb4047ad5778dbcfe6a9716d7537c6d288d413ea370ffa2ddbd212766f", "fetched_at": "2026-08-28T04:03:16.064854+00:00", "kind": "readme", "missing": false, "url": "https://github.com/iphysresearch/TOP250movie_douban"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:08:44.714318+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e605f2cb4047ad5778dbcfe6a9716d7537c6d288d413ea370ffa2ddbd212766f", "fetched_at": "2026-08-28T04:03:16.064854+00:00", "kind": "readme", "missing": false, "url": "https://github.com/iphysresearch/TOP250movie_douban"}], "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": 3021, "days_push": 1502, "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}}