{
"_id": "6ae2062695ca2370cc8cc618",
"Package": "rdomains",
"Title": "Get the Category of Content Hosted by a Domain",
"Version": "0.6.0",
"Authors@R": "person(\"Gaurav\", \"Sood\", email = \"gsood07@gmail.com\", role = c(\"aut\", \"cre\"))",
"Description": "Fetch website content and classify it through the Python\n'piedomains' text model. Look up domains in 'UT-Capitole',\nSteven Black, university, archived 'Shallalist' and 'DMOZ'\nlists, or use 'VirusTotal' ,\n'OpenAI' and 'Anthropic' APIs. Report collection outcomes and\nsource provenance. Includes a historical domain-name classifier\ntrained on 'Shallalist' data.",
"URL": "https://themains.github.io/rdomains/,\nhttps://github.com/themains/rdomains",
"BugReports": "https://github.com/themains/rdomains/issues",
"VignetteBuilder": "knitr",
"License": "MIT + file LICENSE",
"Encoding": "UTF-8",
"Roxygen": "list(markdown = TRUE)",
"Config/roxygen2/version": "8.0.0",
"Config/testthat/edition": "3",
"Config/pak/sysreqs": "libicu-dev libxml2-dev libssl-dev libx11-dev",
"Repository": "https://themains.r-universe.dev",
"Date/Publication": "2026-10-27 11:36:28 UTC",
"RemoteUrl": "https://github.com/themains/rdomains",
"RemoteRef": "HEAD",
"RemoteSha": "9cb9be476c6b346189368826e228aa11e637bb6f",
"NeedsCompilation": "no",
"Packaged": {
"Date": "2026-10-28 14:05:56 UTC",
"User": "root"
},
"Author": "Gaurav Sood [aut, cre]",
"Maintainer": "Gaurav Sood ",
"_user": "themains",
"_type": "src",
"_file": "rdomains_0.6.0.tar.gz",
"_fileid": "https://r2.ropensci.org/ac9a5612e485249643f5f90ad06898f27bf1d5c0948c0c621c41418c0581865c",
"_filesize": 361391,
"_sha256": "ac9a5612e485249643f5f90ad06898f27bf1d5c0948c0c621c41418c0581865c",
"_expires": "2027-02-05T14:26:44.000Z",
"_created": "2026-10-28T14:05:56.000Z",
"_published": "2026-10-28T14:26:46.002Z",
"_upstream": "https://github.com/themains/rdomains",
"_status": "success",
"_maintainer": {
"name": "Gaurav Sood",
"email": "gsood07@gmail.com",
"login": "soodoku",
"description": "",
"uuid": 721466
},
"_jobs": [
{
"job": 122866350796,
"time": 187,
"config": "linux-devel-x86_64",
"r": "4.7.0",
"check": "OK",
"artifact": "12822801319"
},
{
"job": 122866351032,
"time": 271,
"config": "linux-release-x86_64",
"r": "4.6.1",
"check": "OK",
"artifact": "12822317707"
},
{
"job": 122866350750,
"time": 233,
"config": "macos-oldrel-arm64",
"r": "4.5.3",
"check": "OK",
"artifact": "12824485218"
},
{
"job": 122866350822,
"time": 233,
"config": "macos-release-arm64",
"r": "4.6.1",
"check": "OK",
"artifact": "12824585288"
},
{
"job": 122863328520,
"time": 312,
"config": "source",
"r": "4.6.1",
"check": "OK",
"artifact": "12821809059"
},
{
"job": 122866350676,
"time": 506,
"config": "wasm-release",
"r": "4.6.0",
"check": "OK",
"artifact": "12822597955"
},
{
"job": 122866351159,
"time": 230,
"config": "windows-devel-x86_64",
"r": "4.7.0",
"check": "OK",
"artifact": "12821909184"
},
{
"job": 122866351083,
"time": 266,
"config": "windows-oldrel-x86_64",
"r": "4.5.3",
"check": "OK",
"artifact": "12822167479"
},
{
"job": 122866350847,
"time": 476,
"config": "windows-release-x86_64",
"r": "4.6.1",
"check": "OK",
"artifact": "12823580485"
}
],
"_buildurl": "https://github.com/r-universe/themains/actions/runs/40701761158",
"_commit": {
"id": "9cb9be476c6b346189368826e228aa11e637bb6f",
"author": "gaurav <721466+soodoku@users.noreply.github.com>",
"committer": "GitHub ",
"message": "Merge pull request #19 from themains/fix/cran-description-and-badge\n\nResolve CRAN spelling note and show download count",
"time": 1793100988
},
"_distro": "resolute",
"_host": "GitHub-Actions",
"_registered": true,
"_dependencies": [
{
"package": "R",
"version": ">= 4.5.0",
"role": "Depends"
},
{
"package": "Matrix",
"role": "Imports"
},
{
"package": "urltools",
"role": "Imports"
},
{
"package": "glmnet",
"role": "Imports"
},
{
"package": "stats",
"role": "Imports"
},
{
"package": "methods",
"role": "Imports"
},
{
"package": "httr2",
"role": "Imports"
},
{
"package": "xml2",
"role": "Imports"
},
{
"package": "curl",
"role": "Imports"
},
{
"package": "virustotal",
"version": ">= 0.7.0",
"role": "Imports"
},
{
"package": "jsonlite",
"role": "Imports"
},
{
"package": "R.utils",
"role": "Imports"
},
{
"package": "dplyr",
"version": ">= 1.1.0",
"role": "Imports"
},
{
"package": "purrr",
"version": ">= 1.0.0",
"role": "Imports"
},
{
"package": "tibble",
"version": ">= 3.2.0",
"role": "Imports"
},
{
"package": "stringr",
"version": ">= 1.5.0",
"role": "Imports"
},
{
"package": "rlang",
"version": ">= 1.1.0",
"role": "Imports"
},
{
"package": "cli",
"version": ">= 3.6.0",
"role": "Imports"
},
{
"package": "checkmate",
"version": ">= 2.3.0",
"role": "Imports"
},
{
"package": "glue",
"version": ">= 1.6.0",
"role": "Imports"
},
{
"package": "readr",
"version": ">= 2.1.0",
"role": "Imports"
},
{
"package": "spiderbar",
"role": "Imports"
},
{
"package": "ipaddress",
"role": "Imports"
},
{
"package": "withr",
"role": "Imports"
},
{
"package": "testthat",
"role": "Suggests"
},
{
"package": "rmarkdown",
"role": "Suggests"
},
{
"package": "knitr",
"version": ">= 1.11",
"role": "Suggests"
},
{
"package": "webfakes",
"role": "Suggests"
},
{
"package": "reticulate",
"version": ">= 1.41.0",
"role": "Suggests"
}
],
"_owner": "themains",
"_selfowned": true,
"_usedby": 0,
"_updates": [
{
"week": "2026-20",
"n": 3
},
{
"week": "2026-31",
"n": 9
},
{
"week": "2026-32",
"n": 1
},
{
"week": "2026-34",
"n": 4
},
{
"week": "2026-43",
"n": 1
},
{
"week": "2026-44",
"n": 4
}
],
"_tags": [
{
"name": "v0.5.0",
"date": "2026-08-02"
}
],
"_topics": [
"domain-classification",
"machine-learning",
"text-classification",
"website-classification"
],
"_stars": 59,
"_contributors": [
{
"user": "soodoku",
"count": 211,
"uuid": 721466
},
{
"user": "quantifiedcode-bot",
"count": 1,
"uuid": 14318904
}
],
"_userbio": {
"uuid": 32114259,
"type": "organization",
"name": "the mains",
"followers": 11,
"description": "online safety and privacy"
},
"_downloads": {
"count": 352,
"source": "https://cranlogs.r-pkg.org/downloads/total/last-month/rdomains"
},
"_devurl": "https://github.com/themains/rdomains",
"_pkgdown": "https://themains.github.io/rdomains/",
"_rbuild": "4.6.1",
"_assets": [
"extra/citation.cff",
"extra/citation.html",
"extra/citation.json",
"extra/citation.txt",
"extra/contents.json",
"extra/manual.pdf",
"extra/NEWS.html",
"extra/NEWS.txt",
"extra/rdomains.html",
"extra/readme.html",
"extra/readme.md",
"LICENSE"
],
"_homeurl": "https://github.com/themains/rdomains",
"_realowner": "themains",
"_cranurl": true,
"_releases": [
{
"version": "0.1.0",
"date": "2016-06-16"
},
{
"version": "0.1.5",
"date": "2016-11-02"
},
{
"version": "0.1.7",
"date": "2018-01-28"
},
{
"version": "0.1.9",
"date": "2020-08-11"
},
{
"version": "0.2.0",
"date": "2021-11-04"
},
{
"version": "0.2.1",
"date": "2022-01-15"
},
{
"version": "0.4.0",
"date": "2026-05-13"
},
{
"version": "0.5.0",
"date": "2026-08-02"
},
{
"version": "0.6.0",
"date": "2026-10-27"
}
],
"_exports": [
"adult_name_probability",
"cache_clear",
"claude_cat",
"collect_content",
"dmoz_cat",
"fetch_error_codes",
"fetch_report",
"get_dmoz_data",
"get_shalla_data",
"get_stevenblack_data",
"get_ut1_data",
"glm_shalla",
"html_text_content",
"news_url_signals",
"openai_cat",
"page_signals",
"pie_cat",
"rdomains_cache_dir",
"shalla_cat",
"source_vintage",
"stevenblack_cat",
"uni_cat",
"ut1_cat",
"virustotal_cat",
"web_categories"
],
"_help": [
{
"page": "rdomains-package",
"title": "rdomains: Classify Domains by their Content",
"topics": [
"rdomains-package",
"rdomains"
]
},
{
"page": "adult_name_probability",
"title": "Probability that Domain Hosts Adult Content Based on features of Domain Name and Suffix alone.",
"topics": [
"adult_name_probability"
]
},
{
"page": "cache_clear",
"title": "Empty the page cache",
"topics": [
"cache_clear"
]
},
{
"page": "classification_results",
"title": "Classification result contract",
"topics": [
"classification_results"
]
},
{
"page": "claude_cat",
"title": "Get Category from Anthropic Claude",
"topics": [
"claude_cat"
]
},
{
"page": "collect_content",
"title": "Fetch homepage HTML and text for domains",
"topics": [
"collect_content"
]
},
{
"page": "dmoz_cat",
"title": "Get Category from DMOZ",
"topics": [
"dmoz_cat"
]
},
{
"page": "fetch_error_codes",
"title": "Reasons a domain can fail to get a category",
"topics": [
"fetch_error_codes"
]
},
{
"page": "fetch_report",
"title": "Summarise the outcome of a fetch or classification run",
"topics": [
"fetch_report"
]
},
{
"page": "get_dmoz_data",
"title": "Get DMOZ Data",
"topics": [
"get_dmoz_data"
]
},
{
"page": "get_shalla_data",
"title": "Get Shalla Data",
"topics": [
"get_shalla_data"
]
},
{
"page": "get_stevenblack_data",
"title": "Get Steven Black's Host List Data",
"topics": [
"get_stevenblack_data"
]
},
{
"page": "get_ut1_data",
"title": "Download the UT-Capitole blacklists",
"topics": [
"get_ut1_data"
]
},
{
"page": "glm_shalla",
"title": "ML Model",
"topics": [
"glm_shalla"
]
},
{
"page": "html_text_content",
"title": "Extract text, title, description and language from HTML",
"topics": [
"html_text_content"
]
},
{
"page": "news_url_signals",
"title": "Detect soft- and hard-news keywords in URLs",
"topics": [
"news_url_signals"
]
},
{
"page": "openai_cat",
"title": "Get Category from OpenAI",
"topics": [
"openai_cat"
]
},
{
"page": "page_signals",
"title": "What kind of page is this?",
"topics": [
"page_signals"
]
},
{
"page": "pie_cat",
"title": "Classify fetched HTML with piedomains",
"topics": [
"pie_cat"
]
},
{
"page": "rdomains_cache_dir",
"title": "A persistent cache directory for fetched pages",
"topics": [
"rdomains_cache_dir"
]
},
{
"page": "shalla_cat",
"title": "Get Category from Shallalist",
"topics": [
"shalla_cat"
]
},
{
"page": "source_vintage",
"title": "Report what each category source is and when it was last published",
"topics": [
"source_vintage"
]
},
{
"page": "stevenblack_cat",
"title": "Get Category from Steven Black's Host List",
"topics": [
"stevenblack_cat"
]
},
{
"page": "uni_cat",
"title": "Get Category from University Domain List",
"topics": [
"uni_cat"
]
},
{
"page": "ut1_cat",
"title": "Get category from the UT-Capitole blacklists",
"topics": [
"ut1_cat"
]
},
{
"page": "virustotal_cat",
"title": "Get Category from VirusTotal",
"topics": [
"virustotal_cat"
]
},
{
"page": "web_categories",
"title": "Default categories for domain-name inference",
"topics": [
"web_categories"
]
}
],
"_readme": "https://github.com/themains/rdomains/raw/HEAD/README.md",
"_rundeps": [
"AsioHeaders",
"askpass",
"backports",
"bit",
"bit64",
"checkmate",
"cli",
"clipr",
"codetools",
"cpp11",
"crayon",
"curl",
"dplyr",
"foreach",
"generics",
"glmnet",
"glue",
"hms",
"httr2",
"ipaddress",
"iterators",
"jsonlite",
"lattice",
"lifecycle",
"magrittr",
"Matrix",
"openssl",
"pillar",
"pkgconfig",
"prettyunits",
"progress",
"purrr",
"R.methodsS3",
"R.oo",
"R.utils",
"R6",
"Rcpp",
"RcppEigen",
"readr",
"rlang",
"shape",
"spiderbar",
"stringi",
"stringr",
"survival",
"sys",
"tibble",
"tidyselect",
"triebeard",
"tzdb",
"urltools",
"utf8",
"vctrs",
"virustotal",
"vroom",
"withr",
"xml2"
],
"_vignettes": [
{
"source": "rdomains.Rmd",
"filename": "rdomains.html",
"title": "Classify, compare, and resume",
"author": "Gaurav Sood",
"engine": "knitr::rmarkdown",
"headings": [
"Preserve every membership",
"Preserve identifiers when resuming",
"Distinguish page state from content classification"
],
"created": "2017-11-10 13:18:31",
"modified": "2026-10-27 04:40:11",
"commits": 9
}
],
"_score": 6.247973266361806,
"_indexed": true,
"_nocasepkg": "rdomains",
"_universes": [
"themains",
"soodoku"
],
"_binaries": [
{
"r": "4.7.0",
"os": "linux",
"version": "0.6.0",
"date": "2026-10-28T14:08:12.000Z",
"distro": "resolute",
"commit": "9cb9be476c6b346189368826e228aa11e637bb6f",
"fileid": "https://r2.ropensci.org/c9fc5f3f53aabcb0ae03546205d267ccb390f4041f3a26dac20a08225c268732",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/themains/actions/runs/40701761158"
},
{
"r": "4.6.1",
"os": "linux",
"version": "0.6.0",
"date": "2026-10-28T14:09:47.000Z",
"distro": "resolute",
"commit": "9cb9be476c6b346189368826e228aa11e637bb6f",
"fileid": "https://r2.ropensci.org/cf7c0cd656b59d077532e7f7a0a17d007470f40cb7c9022f5b1bacced2d26f5e",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/themains/actions/runs/40701761158"
},
{
"r": "4.5.3",
"os": "mac",
"version": "0.6.0",
"date": "2026-10-28T14:23:20.000Z",
"commit": "9cb9be476c6b346189368826e228aa11e637bb6f",
"fileid": "https://r2.ropensci.org/b3ae4ec2eb381102702c0bb3dfc6084d79cf5e6a92a8814f5c990c0745096130",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/themains/actions/runs/40701761158"
},
{
"r": "4.6.1",
"os": "mac",
"version": "0.6.0",
"date": "2026-10-28T14:25:04.000Z",
"commit": "9cb9be476c6b346189368826e228aa11e637bb6f",
"fileid": "https://r2.ropensci.org/7162cb36ac10843c1d835b9dd76253891f924406346742a42da240cc019a4362",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/themains/actions/runs/40701761158"
},
{
"r": "4.6.0",
"os": "wasm",
"version": "0.6.0",
"date": "2026-10-28T14:14:39.000Z",
"commit": "9cb9be476c6b346189368826e228aa11e637bb6f",
"fileid": "https://r2.ropensci.org/0534a554e3ee16406c510b823075111b2d49726e7a3f24c86da9f98cd736e0b6",
"status": "success",
"buildurl": "https://github.com/r-universe/themains/actions/runs/40701761158"
},
{
"r": "4.7.0",
"os": "win",
"version": "0.6.0",
"date": "2026-10-28T14:08:29.000Z",
"commit": "9cb9be476c6b346189368826e228aa11e637bb6f",
"fileid": "https://r2.ropensci.org/ba398cfee3ad8646bcced6ae27f965e351b145d78a25c91cb4d3672a6bf6516f",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/themains/actions/runs/40701761158"
},
{
"r": "4.5.3",
"os": "win",
"version": "0.6.0",
"date": "2026-10-28T14:08:46.000Z",
"commit": "9cb9be476c6b346189368826e228aa11e637bb6f",
"fileid": "https://r2.ropensci.org/1eaf754bd30fb0d12061f491765d58e9a5008aff3c90c1118d16b50ad4f6ee01",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/themains/actions/runs/40701761158"
},
{
"r": "4.6.1",
"os": "win",
"version": "0.6.0",
"date": "2026-10-28T14:12:31.000Z",
"commit": "9cb9be476c6b346189368826e228aa11e637bb6f",
"fileid": "https://r2.ropensci.org/5da54e42493f0ae1a02776c55cbdb3accf2306df259f487d05a850a0bce8d54c",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/themains/actions/runs/40701761158"
}
]
}