{"adoption": {"forks": 348, "observed_at": "2026-08-28T04:04:57.710524+00:00", "stars": 1520}, "canonical_url": "https://ross.abutalabs.com/products/rvest", "card": {"archived": false, "artifact_type": "library", "description": "Simple web scraping for R", "domain": ["web-development", "data-science", "crawlers"], "enriched": true, "function": ["web-scraping", "parser", "http-client"], "health_score": 59, "homepage": "https://rvest.tidyverse.org", "language": "R", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["tidyverse/rvest"], "name": "tidyverse/rvest", "platform": ["cross-platform"], "pushed_at": "2025-09-09T10:02:49+00:00", "repo": "tidyverse/rvest", "stars": 1520, "tags": ["html-parsing", "css-selectors", "xpath", "tidyverse", "r-package", "beautiful-soup-inspired", "html-tables", "live-browser-scraping", "data-engineering", "r"], "topics": ["r", "web-scraping", "html"], "urls": [], "use_cases": ["scrape data from html web pages in r", "extract tables from a website into a data frame", "parse html with css selectors or xpath in r", "scrape javascript-rendered pages with r", "harvest product or article data from multiple pages", "extract text and attributes from html elements"], "what_it_is": "rvest is an R package from the tidyverse for scraping (harvesting) data from web pages, inspired by Beautiful Soup and RoboBrowser. It provides functions to read HTML, select elements via CSS selectors or XPath, extract text and attributes, and parse HTML tables into tibbles, with live-browser scraping support via read_html_live().", "when_to_avoid": ["you need a scraping framework in Python or another language", "you require large-scale distributed crawling with built-in politeness and scheduling", "you need to scrape sites with heavy anti-bot protections or login flows beyond simple interactions", "you want a general-purpose HTTP client rather than an HTML extraction tool"], "when_to_choose": ["you're working in R and want a Beautiful Soup-like scraping experience", "you need to extract structured data or tables from static HTML pages", "you want tidyverse-pipe-friendly web scraping code", "you need to scrape pages that require clicking or scrolling via a live browser session"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/rvest", "repo": "tidyverse/rvest", "role": "main", "score": 43}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.710524+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:31:55.722732+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bb1fd5ca3b2c7d705c8b89e50e34c531221669a69cee8501c382c730c47ae0d2", "fetched_at": "2026-08-28T04:04:57.710524+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tidyverse/rvest"}, {"content_hash": "1bda1685bcefd3eecd843662c083000720629865a2622fbab55f6c309e698f69", "fetched_at": "2026-08-29T11:35:04.319271+00:00", "kind": "homepage", "missing": false, "url": "https://rvest.tidyverse.org"}, {"content_hash": "ebf30aad5350c10d48c1103d743517572589ad9a238684fec76018e451e1773b", "fetched_at": "2026-08-29T11:35:04.322209+00:00", "kind": "site_page", "missing": false, "url": "https://rvest.tidyverse.org/news/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.710524+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:31:55.722732+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bb1fd5ca3b2c7d705c8b89e50e34c531221669a69cee8501c382c730c47ae0d2", "fetched_at": "2026-08-28T04:04:57.710524+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tidyverse/rvest"}, {"content_hash": "1bda1685bcefd3eecd843662c083000720629865a2622fbab55f6c309e698f69", "fetched_at": "2026-08-29T11:35:04.319271+00:00", "kind": "homepage", "missing": false, "url": "https://rvest.tidyverse.org"}, {"content_hash": "ebf30aad5350c10d48c1103d743517572589ad9a238684fec76018e451e1773b", "fetched_at": "2026-08-29T11:35:04.322209+00:00", "kind": "site_page", "missing": false, "url": "https://rvest.tidyverse.org/news/index.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:31:55.722732+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bb1fd5ca3b2c7d705c8b89e50e34c531221669a69cee8501c382c730c47ae0d2", "fetched_at": "2026-08-28T04:04:57.710524+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tidyverse/rvest"}, {"content_hash": "1bda1685bcefd3eecd843662c083000720629865a2622fbab55f6c309e698f69", "fetched_at": "2026-08-29T11:35:04.319271+00:00", "kind": "homepage", "missing": false, "url": "https://rvest.tidyverse.org"}, {"content_hash": "ebf30aad5350c10d48c1103d743517572589ad9a238684fec76018e451e1773b", "fetched_at": "2026-08-29T11:35:04.322209+00:00", "kind": "site_page", "missing": false, "url": "https://rvest.tidyverse.org/news/index.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.710524+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.710524+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.710524+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:31:55.722732+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bb1fd5ca3b2c7d705c8b89e50e34c531221669a69cee8501c382c730c47ae0d2", "fetched_at": "2026-08-28T04:04:57.710524+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tidyverse/rvest"}, {"content_hash": "1bda1685bcefd3eecd843662c083000720629865a2622fbab55f6c309e698f69", "fetched_at": "2026-08-29T11:35:04.319271+00:00", "kind": "homepage", "missing": false, "url": "https://rvest.tidyverse.org"}, {"content_hash": "ebf30aad5350c10d48c1103d743517572589ad9a238684fec76018e451e1773b", "fetched_at": "2026-08-29T11:35:04.322209+00:00", "kind": "site_page", "missing": false, "url": "https://rvest.tidyverse.org/news/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.710524+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.710524+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:31:55.722732+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bb1fd5ca3b2c7d705c8b89e50e34c531221669a69cee8501c382c730c47ae0d2", "fetched_at": "2026-08-28T04:04:57.710524+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tidyverse/rvest"}, {"content_hash": "1bda1685bcefd3eecd843662c083000720629865a2622fbab55f6c309e698f69", "fetched_at": "2026-08-29T11:35:04.319271+00:00", "kind": "homepage", "missing": false, "url": "https://rvest.tidyverse.org"}, {"content_hash": "ebf30aad5350c10d48c1103d743517572589ad9a238684fec76018e451e1773b", "fetched_at": "2026-08-29T11:35:04.322209+00:00", "kind": "site_page", "missing": false, "url": "https://rvest.tidyverse.org/news/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.710524+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.710524+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.710524+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:31:55.722732+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bb1fd5ca3b2c7d705c8b89e50e34c531221669a69cee8501c382c730c47ae0d2", "fetched_at": "2026-08-28T04:04:57.710524+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tidyverse/rvest"}, {"content_hash": "1bda1685bcefd3eecd843662c083000720629865a2622fbab55f6c309e698f69", "fetched_at": "2026-08-29T11:35:04.319271+00:00", "kind": "homepage", "missing": false, "url": "https://rvest.tidyverse.org"}, {"content_hash": "ebf30aad5350c10d48c1103d743517572589ad9a238684fec76018e451e1773b", "fetched_at": "2026-08-29T11:35:04.322209+00:00", "kind": "site_page", "missing": false, "url": "https://rvest.tidyverse.org/news/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.710524+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.710524+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:31:55.722732+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bb1fd5ca3b2c7d705c8b89e50e34c531221669a69cee8501c382c730c47ae0d2", "fetched_at": "2026-08-28T04:04:57.710524+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tidyverse/rvest"}, {"content_hash": "1bda1685bcefd3eecd843662c083000720629865a2622fbab55f6c309e698f69", "fetched_at": "2026-08-29T11:35:04.319271+00:00", "kind": "homepage", "missing": false, "url": "https://rvest.tidyverse.org"}, {"content_hash": "ebf30aad5350c10d48c1103d743517572589ad9a238684fec76018e451e1773b", "fetched_at": "2026-08-29T11:35:04.322209+00:00", "kind": "site_page", "missing": false, "url": "https://rvest.tidyverse.org/news/index.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:31:55.722732+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bb1fd5ca3b2c7d705c8b89e50e34c531221669a69cee8501c382c730c47ae0d2", "fetched_at": "2026-08-28T04:04:57.710524+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tidyverse/rvest"}, {"content_hash": "1bda1685bcefd3eecd843662c083000720629865a2622fbab55f6c309e698f69", "fetched_at": "2026-08-29T11:35:04.319271+00:00", "kind": "homepage", "missing": false, "url": "https://rvest.tidyverse.org"}, {"content_hash": "ebf30aad5350c10d48c1103d743517572589ad9a238684fec76018e451e1773b", "fetched_at": "2026-08-29T11:35:04.322209+00:00", "kind": "site_page", "missing": false, "url": "https://rvest.tidyverse.org/news/index.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:31:55.722732+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bb1fd5ca3b2c7d705c8b89e50e34c531221669a69cee8501c382c730c47ae0d2", "fetched_at": "2026-08-28T04:04:57.710524+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tidyverse/rvest"}, {"content_hash": "1bda1685bcefd3eecd843662c083000720629865a2622fbab55f6c309e698f69", "fetched_at": "2026-08-29T11:35:04.319271+00:00", "kind": "homepage", "missing": false, "url": "https://rvest.tidyverse.org"}, {"content_hash": "ebf30aad5350c10d48c1103d743517572589ad9a238684fec76018e451e1773b", "fetched_at": "2026-08-29T11:35:04.322209+00:00", "kind": "site_page", "missing": false, "url": "https://rvest.tidyverse.org/news/index.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:31:55.722732+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bb1fd5ca3b2c7d705c8b89e50e34c531221669a69cee8501c382c730c47ae0d2", "fetched_at": "2026-08-28T04:04:57.710524+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tidyverse/rvest"}, {"content_hash": "1bda1685bcefd3eecd843662c083000720629865a2622fbab55f6c309e698f69", "fetched_at": "2026-08-29T11:35:04.319271+00:00", "kind": "homepage", "missing": false, "url": "https://rvest.tidyverse.org"}, {"content_hash": "ebf30aad5350c10d48c1103d743517572589ad9a238684fec76018e451e1773b", "fetched_at": "2026-08-29T11:35:04.322209+00:00", "kind": "site_page", "missing": false, "url": "https://rvest.tidyverse.org/news/index.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 41, "longevity": 100, "rhythm": 13}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4424, "days_push": 358, "days_rel": 369, "gap_med": null, "n_releases_24m": 1}, "score": 43, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}