{"adoption": {"forks": 421, "observed_at": "2026-08-28T04:09:47.944470+00:00", "stars": 6709}, "canonical_url": "https://ross.abutalabs.com/products/trafilatura", "card": {"archived": false, "artifact_type": "library", "description": "Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML", "domain": ["web-development", "crawlers", "large-language-models", "data-science"], "enriched": true, "function": ["web-scraping", "parser", "nlp", "cli", "http-client", "rag"], "health_score": 99, "homepage": "https://trafilatura.readthedocs.io", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["adbar/trafilatura"], "name": "adbar/trafilatura", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2026-08-21T16:08:46+00:00", "repo": "adbar/trafilatura", "stars": 6709, "tags": ["html-to-markdown", "text-extraction", "readability", "article-extraction", "corpus-building", "metadata-extraction", "news-crawler", "natural-language-processing"], "topics": ["web-scraping", "text-extraction", "nlp", "html2text", "text-mining", "crawler", "text-cleaning", "text-preprocessing", "article-extractor", "readability", "scraping", "news-crawler", "tei", "html-to-markdown", "corpus-builder", "corpus-tools", "rss-feed", "news-aggregator", "rag", "llm"], "urls": [], "use_cases": ["extract article text from web pages", "scrape news articles and metadata", "build text corpora for NLP or LLM training", "convert HTML to markdown or plain text", "crawl sitemaps and RSS feeds for content discovery", "prepare clean web text for RAG pipelines"], "what_it_is": "Trafilatura is a Python package and command-line tool for crawling the web and extracting main text, metadata, and comments from raw HTML while filtering out boilerplate noise. It outputs structured results in formats such as CSV, JSON, HTML, Markdown, TXT, and XML.", "when_to_avoid": ["you need a full browser-based scraper for JavaScript-heavy sites", "you require structured extraction of arbitrary page elements rather than main content", "you need a distributed large-scale crawling framework"], "when_to_choose": ["you need high-precision main-content extraction from HTML without boilerplate", "you want an all-in-one crawl-download-extract pipeline in Python", "you need multiple output formats including JSON, Markdown, and XML", "you are building datasets for LLM or NLP research"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/trafilatura", "repo": "adbar/trafilatura", "role": "main", "score": 93}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:47.944470+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:42:56.825441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4a0b6de17b52d63ab6c5d13d9ac0514ae84d9d590abff2c2f7676c56bbcba52f", "fetched_at": "2026-08-28T04:09:47.944470+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adbar/trafilatura"}, {"content_hash": "0d7d14be21cad1c20c9ea6fc048fec839a9f542c2e0c91cc46ec1bc1ba8bb8bf", "fetched_at": "2026-08-29T08:39:30.147870+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/trafilatura/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:47.944470+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:42:56.825441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4a0b6de17b52d63ab6c5d13d9ac0514ae84d9d590abff2c2f7676c56bbcba52f", "fetched_at": "2026-08-28T04:09:47.944470+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adbar/trafilatura"}, {"content_hash": "0d7d14be21cad1c20c9ea6fc048fec839a9f542c2e0c91cc46ec1bc1ba8bb8bf", "fetched_at": "2026-08-29T08:39:30.147870+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/trafilatura/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:42:56.825441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4a0b6de17b52d63ab6c5d13d9ac0514ae84d9d590abff2c2f7676c56bbcba52f", "fetched_at": "2026-08-28T04:09:47.944470+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adbar/trafilatura"}, {"content_hash": "0d7d14be21cad1c20c9ea6fc048fec839a9f542c2e0c91cc46ec1bc1ba8bb8bf", "fetched_at": "2026-08-29T08:39:30.147870+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/trafilatura/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:47.944470+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:47.944470+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:47.944470+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:42:56.825441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4a0b6de17b52d63ab6c5d13d9ac0514ae84d9d590abff2c2f7676c56bbcba52f", "fetched_at": "2026-08-28T04:09:47.944470+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adbar/trafilatura"}, {"content_hash": "0d7d14be21cad1c20c9ea6fc048fec839a9f542c2e0c91cc46ec1bc1ba8bb8bf", "fetched_at": "2026-08-29T08:39:30.147870+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/trafilatura/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:47.944470+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:47.944470+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:42:56.825441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4a0b6de17b52d63ab6c5d13d9ac0514ae84d9d590abff2c2f7676c56bbcba52f", "fetched_at": "2026-08-28T04:09:47.944470+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adbar/trafilatura"}, {"content_hash": "0d7d14be21cad1c20c9ea6fc048fec839a9f542c2e0c91cc46ec1bc1ba8bb8bf", "fetched_at": "2026-08-29T08:39:30.147870+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/trafilatura/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:47.944470+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:47.944470+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:47.944470+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:42:56.825441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4a0b6de17b52d63ab6c5d13d9ac0514ae84d9d590abff2c2f7676c56bbcba52f", "fetched_at": "2026-08-28T04:09:47.944470+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adbar/trafilatura"}, {"content_hash": "0d7d14be21cad1c20c9ea6fc048fec839a9f542c2e0c91cc46ec1bc1ba8bb8bf", "fetched_at": "2026-08-29T08:39:30.147870+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/trafilatura/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:47.944470+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:47.944470+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:42:56.825441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4a0b6de17b52d63ab6c5d13d9ac0514ae84d9d590abff2c2f7676c56bbcba52f", "fetched_at": "2026-08-28T04:09:47.944470+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adbar/trafilatura"}, {"content_hash": "0d7d14be21cad1c20c9ea6fc048fec839a9f542c2e0c91cc46ec1bc1ba8bb8bf", "fetched_at": "2026-08-29T08:39:30.147870+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/trafilatura/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:42:56.825441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4a0b6de17b52d63ab6c5d13d9ac0514ae84d9d590abff2c2f7676c56bbcba52f", "fetched_at": "2026-08-28T04:09:47.944470+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adbar/trafilatura"}, {"content_hash": "0d7d14be21cad1c20c9ea6fc048fec839a9f542c2e0c91cc46ec1bc1ba8bb8bf", "fetched_at": "2026-08-29T08:39:30.147870+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/trafilatura/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:42:56.825441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4a0b6de17b52d63ab6c5d13d9ac0514ae84d9d590abff2c2f7676c56bbcba52f", "fetched_at": "2026-08-28T04:09:47.944470+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adbar/trafilatura"}, {"content_hash": "0d7d14be21cad1c20c9ea6fc048fec839a9f542c2e0c91cc46ec1bc1ba8bb8bf", "fetched_at": "2026-08-29T08:39:30.147870+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/trafilatura/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:42:56.825441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4a0b6de17b52d63ab6c5d13d9ac0514ae84d9d590abff2c2f7676c56bbcba52f", "fetched_at": "2026-08-28T04:09:47.944470+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adbar/trafilatura"}, {"content_hash": "0d7d14be21cad1c20c9ea6fc048fec839a9f542c2e0c91cc46ec1bc1ba8bb8bf", "fetched_at": "2026-08-29T08:39:30.147870+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/trafilatura/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 100, "rhythm": 83}, "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": 2704, "days_push": 12, "days_rel": 33, "gap_med": 84, "n_releases_24m": 4}, "score": 93, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}