{
  "_id": "6ae3821395ca2370cc8ce84b",
  "Package": "rdomains",
  "Title": "Get the Category of Content Hosted by a Domain",
  "Version": "0.6.1",
  "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' <https://www.virustotal.com/>,\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",
  "Config/roxygen2/version": "8.0.0",
  "Config/testthat/edition": "3",
  "NeedsCompilation": "no",
  "Packaged": {
    "Date": "2026-10-29 17:24:24 UTC",
    "User": "root"
  },
  "Author": "Gaurav Sood [aut, cre]",
  "Maintainer": "Gaurav Sood <gsood07@gmail.com>",
  "Repository": "https://cran.r-universe.dev",
  "Date/Publication": "2026-10-29 08:50:11 UTC",
  "RemoteUrl": "https://github.com/cran/rdomains",
  "RemoteRef": "HEAD",
  "RemoteSha": "edd931e44fe306ea321882798db2f608790628e7",
  "_user": "cran",
  "_type": "src",
  "_file": "rdomains_0.6.1.tar.gz",
  "_fileid": "https://r2.ropensci.org/408231e833175fcac1d28ba41543a3ad2ab4873e83fff7460586499e98d56902",
  "_filesize": 358649,
  "_sha256": "408231e833175fcac1d28ba41543a3ad2ab4873e83fff7460586499e98d56902",
  "_expires": "2027-02-06T17:27:45.000Z",
  "_created": "2026-10-29T17:24:24.000Z",
  "_published": "2026-10-29T17:27:47.402Z",
  "_upstream": "https://github.com/cran/rdomains",
  "_status": "success",
  "_maintainer": {
    "name": "Gaurav Sood",
    "email": "gsood07@gmail.com",
    "login": "soodoku",
    "description": "",
    "uuid": 721466
  },
  "_jobs": [
    {
      "job": 123614152207,
      "time": 154,
      "config": "linux-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "12917764505"
    },
    {
      "job": 123614152239,
      "time": 136,
      "config": "linux-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12917764451"
    },
    {
      "job": 123611964472,
      "time": 230,
      "config": "source",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12918421648"
    },
    {
      "job": 123614151774,
      "time": 112,
      "config": "wasm-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "12918760735"
    },
    {
      "job": 123614151780,
      "time": 126,
      "config": "windows-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "12918386637"
    },
    {
      "job": 123614151895,
      "time": 124,
      "config": "windows-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12918261794"
    }
  ],
  "_buildurl": "https://github.com/r-universe/cran/actions/runs/40920394670",
  "_commit": {
    "id": "edd931e44fe306ea321882798db2f608790628e7",
    "author": "Gaurav Sood <gsood07@gmail.com>",
    "committer": "cran-robot <csardi.gabor+cran@gmail.com>",
    "message": "version 0.6.1\n",
    "time": 1793263811
  },
  "_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": "cran",
  "_selfowned": false,
  "_usedby": 0,
  "_updates": [
    {
      "week": "2026-20",
      "n": 1
    },
    {
      "week": "2026-31",
      "n": 1
    },
    {
      "week": "2026-44",
      "n": 2
    }
  ],
  "_tags": [
    {
      "name": "0.4.0",
      "date": "2026-05-13"
    },
    {
      "name": "0.5.0",
      "date": "2026-08-02"
    },
    {
      "name": "0.6.0",
      "date": "2026-10-27"
    },
    {
      "name": "0.6.1",
      "date": "2026-10-29"
    }
  ],
  "_stars": 0,
  "_contributors": [
    {
      "user": "soodoku",
      "count": 10,
      "uuid": 721466
    }
  ],
  "_userbio": {
    "uuid": 6899542,
    "type": "organization",
    "name": "cran",
    "followers": 634,
    "description": "Unofficial read-only mirror of all CRAN R packages"
  },
  "_downloads": {
    "count": 396,
    "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/rdomains"
  },
  "_devurl": "https://github.com/themains/rdomains",
  "_pkgdown": "https://themains.github.io/rdomains/",
  "_searchresults": 10,
  "_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",
    "LICENSE"
  ],
  "_homeurl": "https://github.com/themains/rdomains",
  "_realowner": "themains",
  "_cranurl": false,
  "_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"
      ]
    }
  ],
  "_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": "2016-06-16 12:37:26",
      "modified": "2026-10-27 12:30:09",
      "commits": 4
    }
  ],
  "_score": 2.4771212547196626,
  "_indexed": false,
  "_nocasepkg": "rdomains",
  "_universes": [
    "cran"
  ],
  "_indexurl": "https://themains.r-universe.dev/rdomains",
  "_previous": "0.6.0",
  "_binaries": [
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "0.6.1",
      "date": "2026-10-29T17:26:39.000Z",
      "distro": "resolute",
      "commit": "edd931e44fe306ea321882798db2f608790628e7",
      "fileid": "https://r2.ropensci.org/3a07ef58dfecce928d8c1b244f058d92b8095153e24af62041575bfd99df11c9",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/cran/actions/runs/40920394670"
    },
    {
      "r": "4.6.1",
      "os": "linux",
      "version": "0.6.1",
      "date": "2026-10-29T17:26:26.000Z",
      "distro": "resolute",
      "commit": "edd931e44fe306ea321882798db2f608790628e7",
      "fileid": "https://r2.ropensci.org/9c7a5acaf582b16dbacf14a6b0dcc734e9ea85e9783beac2c1bf3dd9fefbba49",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/cran/actions/runs/40920394670"
    },
    {
      "r": "4.6.0",
      "os": "wasm",
      "version": "0.6.1",
      "date": "2026-10-29T17:26:37.000Z",
      "commit": "edd931e44fe306ea321882798db2f608790628e7",
      "fileid": "https://r2.ropensci.org/827780bbf0f87c62def2433123b407220098b5dfcd3a2c4c5b687661d446f008",
      "status": "success",
      "buildurl": "https://github.com/r-universe/cran/actions/runs/40920394670"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "0.6.1",
      "date": "2026-10-29T17:25:50.000Z",
      "commit": "edd931e44fe306ea321882798db2f608790628e7",
      "fileid": "https://r2.ropensci.org/81a616c97569dc907a8218422641b3d18989647edde1755e133edb1745c9b1e7",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/cran/actions/runs/40920394670"
    },
    {
      "r": "4.6.1",
      "os": "win",
      "version": "0.6.1",
      "date": "2026-10-29T17:25:51.000Z",
      "commit": "edd931e44fe306ea321882798db2f608790628e7",
      "fileid": "https://r2.ropensci.org/5b26a53d9bf12ad2735f4b4d27a074a816418f0333529a584417409746ae2828",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/cran/actions/runs/40920394670"
    }
  ]
}