{
  "_id": "6ac8d92ede46216d5edd85c2",
  "Package": "rdomains",
  "Title": "Get the Category of Content Hosted by a Domain",
  "Version": "0.5.0",
  "Authors@R": "person(\"Gaurav\", \"Sood\", email = \"gsood07@gmail.com\", role = c(\"aut\", \"cre\"))",
  "Description": "Get the category of content hosted by a domain. Use\nShallalist (service discontinued), 'VirusTotal' (which provides\naccess to lots of services) <https://www.virustotal.com/>,\n'DMOZ' <https://archive.org/details/dmoz-rdf-20150327>,\nUniversity Domain list\n<https://github.com/Hipo/university-domains-list>, 'OpenAI'\n'GPT' models, 'Anthropic' 'Claude' models, or validated machine\nlearning classifiers based on 'Shallalist' data to learn about\nthe kind of content hosted by a domain.",
  "VignetteBuilder": "knitr",
  "License": "MIT + file LICENSE",
  "Encoding": "UTF-8",
  "Config/roxygen2/version": "8.0.0",
  "Config/testthat/edition": "3",
  "NeedsCompilation": "no",
  "Packaged": {
    "Date": "2026-10-09 12:04:16 UTC",
    "User": "root"
  },
  "Author": "Gaurav Sood [aut, cre]",
  "Maintainer": "Gaurav Sood <gsood07@gmail.com>",
  "Config/pak/sysreqs": "libicu-dev libxml2-dev libssl-dev libx11-dev",
  "Repository": "https://soodoku.r-universe.dev",
  "Date/Publication": "2026-08-02 09:00:02 UTC",
  "RemoteUrl": "https://github.com/cran/rdomains",
  "RemoteRef": "HEAD",
  "RemoteSha": "4e5993b435a10560ed926176dfe552b4b4a763ea",
  "_user": "soodoku",
  "_type": "src",
  "_file": "rdomains_0.5.0.tar.gz",
  "_fileid": "https://r2.ropensci.org/f46f523dc5c6f62a8773ff9a8dea94ea77e5a662e0da374ce58d557219d27534",
  "_filesize": 287059,
  "_sha256": "f46f523dc5c6f62a8773ff9a8dea94ea77e5a662e0da374ce58d557219d27534",
  "_expires": "2027-01-17T12:08:12.000Z",
  "_created": "2026-10-09T12:04:16.000Z",
  "_published": "2026-10-09T12:08:14.522Z",
  "_buildurl": "https://github.com/r-universe/soodoku/actions/runs/37927328165",
  "_status": "success",
  "_host": "GitHub-Actions",
  "_jobs": [
    {
      "job": 113810490487,
      "time": 140,
      "config": "linux-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "11615135806"
    },
    {
      "job": 113810490543,
      "time": 172,
      "config": "linux-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11614970978"
    },
    {
      "job": 113810490464,
      "time": 129,
      "config": "macos-oldrel-arm64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "11614414143"
    },
    {
      "job": 113810490472,
      "time": 153,
      "config": "macos-release-arm64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11614757327"
    },
    {
      "job": 113809380936,
      "time": 190,
      "config": "source",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11614995527"
    },
    {
      "job": 113810490444,
      "time": 118,
      "config": "wasm-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "11614264676"
    },
    {
      "job": 113810490540,
      "time": 116,
      "config": "windows-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "11615475843"
    },
    {
      "job": 113810490414,
      "time": 144,
      "config": "windows-oldrel-x86_64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "11614219793"
    },
    {
      "job": 113810490495,
      "time": 111,
      "config": "windows-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11615225584"
    }
  ],
  "_upstream": "https://github.com/cran/rdomains",
  "_commit": {
    "id": "4e5993b435a10560ed926176dfe552b4b4a763ea",
    "author": "Gaurav Sood <gsood07@gmail.com>",
    "committer": "cran-robot <csardi.gabor+cran@gmail.com>",
    "message": "version 0.5.0\n",
    "time": 1785661202
  },
  "_maintainer": {
    "name": "Gaurav Sood",
    "email": "gsood07@gmail.com",
    "login": "soodoku",
    "description": "",
    "uuid": 721466
  },
  "_distro": "resolute",
  "_registered": true,
  "_dependencies": [
    {
      "package": "R",
      "version": ">= 4.1.0",
      "role": "Depends"
    },
    {
      "package": "Matrix",
      "role": "Imports"
    },
    {
      "package": "urltools",
      "role": "Imports"
    },
    {
      "package": "glmnet",
      "role": "Imports"
    },
    {
      "package": "stats",
      "role": "Imports"
    },
    {
      "package": "methods",
      "role": "Imports"
    },
    {
      "package": "XML",
      "role": "Imports"
    },
    {
      "package": "httr",
      "role": "Imports"
    },
    {
      "package": "httr2",
      "role": "Imports"
    },
    {
      "package": "xml2",
      "role": "Imports"
    },
    {
      "package": "curl",
      "role": "Imports"
    },
    {
      "package": "virustotal",
      "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": "testthat",
      "role": "Suggests"
    },
    {
      "package": "rmarkdown",
      "role": "Suggests"
    },
    {
      "package": "knitr",
      "version": ">= 1.11",
      "role": "Suggests"
    },
    {
      "package": "withr",
      "role": "Suggests"
    }
  ],
  "_owner": "cran",
  "_selfowned": true,
  "_usedby": 0,
  "_updates": [
    {
      "week": "2026-20",
      "n": 1
    },
    {
      "week": "2026-31",
      "n": 1
    }
  ],
  "_tags": [
    {
      "name": "0.4.0",
      "date": "2026-05-13"
    },
    {
      "name": "0.5.0",
      "date": "2026-08-02"
    }
  ],
  "_stars": 0,
  "_contributors": [
    {
      "user": "soodoku",
      "count": 8,
      "uuid": 721466
    }
  ],
  "_userbio": {
    "uuid": 721466,
    "type": "user",
    "name": "gaurav",
    "followers": 289
  },
  "_downloads": {
    "count": 331,
    "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/rdomains"
  },
  "_searchresults": 9,
  "_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"
  ],
  "_realowner": "soodoku",
  "_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"
    }
  ],
  "_exports": [
    "adult_ml1_cat",
    "claude_cat",
    "collect_content",
    "dmoz_cat",
    "fetch_error_codes",
    "fetch_report",
    "get_dmoz_data",
    "get_shalla_data",
    "get_stevenblack_data",
    "glm_shalla",
    "html_text_content",
    "not_news",
    "openai_cat",
    "page_signals",
    "shalla_cat",
    "source_vintage",
    "stevenblack_cat",
    "uni_cat",
    "virustotal_cat"
  ],
  "_help": [
    {
      "page": "rdomains-package",
      "title": "rdomains: Classify Domains by their Content",
      "topics": [
        "rdomains-package",
        "rdomains"
      ]
    },
    {
      "page": "adult_ml1_cat",
      "title": "Probability that Domain Hosts Adult Content Based on features of Domain Name and Suffix alone.",
      "topics": [
        "adult_ml1_cat"
      ]
    },
    {
      "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": "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": "not_news",
      "title": "Classify News and Non-News Based on keywords in the URL",
      "topics": [
        "not_news"
      ]
    },
    {
      "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": "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": "virustotal_cat",
      "title": "Get Category from VirusTotal",
      "topics": [
        "virustotal_cat"
      ]
    }
  ],
  "_rundeps": [
    "askpass",
    "backports",
    "bit",
    "bit64",
    "checkmate",
    "cli",
    "clipr",
    "codetools",
    "cpp11",
    "crayon",
    "curl",
    "dplyr",
    "foreach",
    "generics",
    "glmnet",
    "glue",
    "hms",
    "httr",
    "httr2",
    "iterators",
    "jsonlite",
    "lattice",
    "lifecycle",
    "magrittr",
    "Matrix",
    "mime",
    "openssl",
    "pillar",
    "pkgconfig",
    "prettyunits",
    "progress",
    "purrr",
    "R.methodsS3",
    "R.oo",
    "R.utils",
    "R6",
    "Rcpp",
    "RcppEigen",
    "readr",
    "rlang",
    "shape",
    "stringi",
    "stringr",
    "survival",
    "sys",
    "tibble",
    "tidyselect",
    "triebeard",
    "tzdb",
    "urltools",
    "utf8",
    "vctrs",
    "virustotal",
    "vroom",
    "withr",
    "XML",
    "xml2"
  ],
  "_vignettes": [
    {
      "source": "rdomains.Rmd",
      "filename": "rdomains.html",
      "title": "Using rdomains",
      "author": "Gaurav Sood",
      "engine": "knitr::rmarkdown",
      "headings": [
        "rdomains: Get the category of content hosted by a domain",
        "Install and Load the package",
        "Shalla",
        "DMOZ",
        "ML",
        "VirusTotal",
        "OpenAI GPT Models",
        "Anthropic Claude"
      ],
      "created": "2016-06-16 12:37:26",
      "modified": "2026-05-13 07:32:50",
      "commits": 3
    }
  ],
  "_score": 2.3010299956639813,
  "_indexed": true,
  "_nocasepkg": "rdomains",
  "_universes": [
    "soodoku"
  ],
  "_binaries": [
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "0.5.0",
      "date": "2026-10-09T12:06:25.000Z",
      "distro": "resolute",
      "commit": "4e5993b435a10560ed926176dfe552b4b4a763ea",
      "fileid": "https://r2.ropensci.org/30590bbfb1c32123ff6aa689d323a4100a7b8fd90cc8048bf5c0534ed842d286",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/soodoku/actions/runs/37927328165"
    },
    {
      "r": "4.6.1",
      "os": "linux",
      "version": "0.5.0",
      "date": "2026-10-09T12:06:44.000Z",
      "distro": "resolute",
      "commit": "4e5993b435a10560ed926176dfe552b4b4a763ea",
      "fileid": "https://r2.ropensci.org/9d137033e3a88561d9ad0f933ad4bc1fd86be033cf503b9276925dfe09f6a3bc",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/soodoku/actions/runs/37927328165"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "0.5.0",
      "date": "2026-10-09T12:06:31.000Z",
      "commit": "4e5993b435a10560ed926176dfe552b4b4a763ea",
      "fileid": "https://r2.ropensci.org/b8f84783031028f034efbb5912b67db622ae59e9d79e8ce9267768bfce37ef50",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/soodoku/actions/runs/37927328165"
    },
    {
      "r": "4.6.1",
      "os": "mac",
      "version": "0.5.0",
      "date": "2026-10-09T12:07:02.000Z",
      "commit": "4e5993b435a10560ed926176dfe552b4b4a763ea",
      "fileid": "https://r2.ropensci.org/5384c76edebb8ee13de090e7f1f2023f22f12dd0a999971b56836ec120dc4951",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/soodoku/actions/runs/37927328165"
    },
    {
      "r": "4.6.0",
      "os": "wasm",
      "version": "0.5.0",
      "date": "2026-10-09T12:06:32.000Z",
      "commit": "4e5993b435a10560ed926176dfe552b4b4a763ea",
      "fileid": "https://r2.ropensci.org/80768a68fe3eac3c810962d14f3b9608ddfa7f4770fa092d2ea31cba0722d1f4",
      "status": "success",
      "buildurl": "https://github.com/r-universe/soodoku/actions/runs/37927328165"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "0.5.0",
      "date": "2026-10-09T12:05:41.000Z",
      "commit": "4e5993b435a10560ed926176dfe552b4b4a763ea",
      "fileid": "https://r2.ropensci.org/3bba5e9a254c7efbcb9706bf7c2d9148e1284b49dafe3bdc7b44bcbc1f485549",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/soodoku/actions/runs/37927328165"
    },
    {
      "r": "4.5.3",
      "os": "win",
      "version": "0.5.0",
      "date": "2026-10-09T12:06:03.000Z",
      "commit": "4e5993b435a10560ed926176dfe552b4b4a763ea",
      "fileid": "https://r2.ropensci.org/50608e2f34fe9204e6f079416267fba630a4daf891b68e30e70b1a46b335b958",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/soodoku/actions/runs/37927328165"
    },
    {
      "r": "4.6.1",
      "os": "win",
      "version": "0.5.0",
      "date": "2026-10-09T12:05:27.000Z",
      "commit": "4e5993b435a10560ed926176dfe552b4b4a763ea",
      "fileid": "https://r2.ropensci.org/62d353c5ef40978dc92d664dd25924a1771b89f3ee62af7ad36955a41dd45e23",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/soodoku/actions/runs/37927328165"
    }
  ]
}