{
  "_id": "6ace915ef6f39cd7e29a1683",
  "Package": "zuhtml",
  "Title": "Parse 'HTML' with a Bundled 'Gumbo' Parser",
  "Version": "0.1.0.9000",
  "Authors@R": "c(\nperson(\"Pedro\", \"Baltazar\", , \"pedrobtz@gmail.com\",\nrole = c(\"aut\", \"cre\", \"cph\")),\nperson(\"Google Inc.\", role = \"cph\",\ncomment = \"Gumbo, bundled in src/vendor/gumbo\"),\nperson(\"Bjoern\", \"Hoehrmann\", role = \"cph\",\ncomment = \"UTF-8 decoder in src/vendor/gumbo/utf8.c\"))",
  "Description": "Parses real-world 'HTML' with a bundled copy of the\n'Gumbo' parser\n(<https://codeberg.org/gumbo-parser/gumbo-parser>), which\nfollows the 'WHATWG' parsing algorithm, so that no system\nlibrary is required. Documents become immutable trees navigated\nwith a documented subset of 'CSS' selectors. Attributes, text,\nlists, tables, links, forms and page metadata ('JSON-LD',\nmicrodata) are extracted into ordinary character vectors, lists\nand data frames, and nodes convert to 'Markdown'. Input is a\nstring, raw bytes, a file, a URL or a connection, and raw input\nis decoded as browsers decode it, from a byte-order mark or a\n'<meta>' declaration. Parsing is bounded by limits on input\nsize, native memory and nesting depth.",
  "License": "MIT + file LICENSE",
  "Copyright": "file inst/COPYRIGHTS",
  "URL": "https://github.com/pedrobtz/zuhtml,\nhttps://pedrobtz.github.io/zuhtml/",
  "BugReports": "https://github.com/pedrobtz/zuhtml/issues",
  "VignetteBuilder": "knitr",
  "Config/testthat/edition": "3",
  "Encoding": "UTF-8",
  "Roxygen": "list(markdown = TRUE)",
  "Config/roxygen2/version": "8.1.0",
  "Repository": "https://pedrobtz.r-universe.dev",
  "Date/Publication": "2026-10-13 19:06:00 UTC",
  "RemoteUrl": "https://github.com/pedrobtz/zuhtml",
  "RemoteRef": "HEAD",
  "RemoteSha": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
  "NeedsCompilation": "yes",
  "Packaged": {
    "Date": "2026-10-13 19:49:47 UTC",
    "User": "root"
  },
  "Author": "Pedro Baltazar [aut, cre, cph],\nGoogle Inc. [cph] (Gumbo, bundled in src/vendor/gumbo),\nBjoern Hoehrmann [cph] (UTF-8 decoder in src/vendor/gumbo/utf8.c)",
  "Maintainer": "Pedro Baltazar <pedrobtz@gmail.com>",
  "_user": "pedrobtz",
  "_type": "src",
  "_file": "zuhtml_0.1.0.9000.tar.gz",
  "_fileid": "https://r2.ropensci.org/5740c0699eb8decbe014a6cad9e390c3b01570ca4d7a0e258a96734f164636a5",
  "_filesize": 525262,
  "_sha256": "5740c0699eb8decbe014a6cad9e390c3b01570ca4d7a0e258a96734f164636a5",
  "_expires": "2027-01-21T20:15:23.000Z",
  "_created": "2026-10-13T19:49:47.000Z",
  "_published": "2026-10-13T20:15:26.154Z",
  "_buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581",
  "_status": "success",
  "_host": "GitHub-Actions",
  "_jobs": [
    {
      "job": 115505600644,
      "time": 138,
      "config": "linux-devel-arm64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "11843793244"
    },
    {
      "job": 115505600584,
      "time": 136,
      "config": "linux-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "11843873165"
    },
    {
      "job": 115505600694,
      "time": 133,
      "config": "linux-release-arm64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11844936419"
    },
    {
      "job": 115505600876,
      "time": 132,
      "config": "linux-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11844981372"
    },
    {
      "job": 115505600713,
      "time": 115,
      "config": "macos-oldrel-arm64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "11845069343"
    },
    {
      "job": 115505600836,
      "time": 180,
      "config": "macos-oldrel-x86_64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "11845617064"
    },
    {
      "job": 115505600684,
      "time": 112,
      "config": "macos-release-arm64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11844718580"
    },
    {
      "job": 115505600601,
      "time": 221,
      "config": "macos-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11844694443"
    },
    {
      "job": 115503436786,
      "time": 282,
      "config": "source",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11845340574"
    },
    {
      "job": 115505600880,
      "time": 84,
      "config": "wasm-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "11844566147"
    },
    {
      "job": 115505600751,
      "time": 230,
      "config": "windows-devel-arm64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "11845281318"
    },
    {
      "job": 115505600663,
      "time": 126,
      "config": "windows-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "11843888131"
    },
    {
      "job": 115505600919,
      "time": 98,
      "config": "windows-oldrel-x86_64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "11843788127"
    },
    {
      "job": 115505600894,
      "time": 201,
      "config": "windows-release-arm64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11845466041"
    },
    {
      "job": 115505600840,
      "time": 149,
      "config": "windows-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11844991203"
    }
  ],
  "_upstream": "https://github.com/pedrobtz/zuhtml",
  "_commit": {
    "id": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
    "author": "github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>",
    "committer": "github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>",
    "message": "Update coverage badge (77.1%)\n",
    "time": 1791918360
  },
  "_maintainer": {
    "name": "Pedro Baltazar",
    "email": "pedrobtz@gmail.com",
    "login": "pedrobtz",
    "description": "\n",
    "uuid": 2864346
  },
  "_distro": "resolute",
  "_registered": true,
  "_dependencies": [
    {
      "package": "R",
      "version": ">= 4.1",
      "role": "Depends"
    },
    {
      "package": "jsonlite",
      "role": "Suggests"
    },
    {
      "package": "knitr",
      "role": "Suggests"
    },
    {
      "package": "rmarkdown",
      "role": "Suggests"
    },
    {
      "package": "testthat",
      "version": ">= 3.0.0",
      "role": "Suggests"
    },
    {
      "package": "withr",
      "role": "Suggests"
    }
  ],
  "_owner": "pedrobtz",
  "_selfowned": true,
  "_usedby": 0,
  "_updates": [
    {
      "week": "2026-39",
      "n": 42
    },
    {
      "week": "2026-40",
      "n": 1
    },
    {
      "week": "2026-42",
      "n": 2
    }
  ],
  "_tags": [
    {
      "name": "0.1.0",
      "date": "2026-09-25"
    }
  ],
  "_stars": 0,
  "_contributors": [
    {
      "user": "pedrobtz",
      "count": 62,
      "uuid": 2864346
    }
  ],
  "_userbio": {
    "uuid": 2864346,
    "type": "user",
    "name": "Pedro Z",
    "followers": 0
  },
  "_downloads": {
    "count": 132,
    "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/zuhtml"
  },
  "_devurl": "https://github.com/pedrobtz/zuhtml",
  "_pkgdown": "https://pedrobtz.github.io/zuhtml/",
  "_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/readme.html",
    "extra/readme.md",
    "extra/zuhtml.html",
    "LICENSE"
  ],
  "_homeurl": "https://github.com/pedrobtz/zuhtml",
  "_realowner": "pedrobtz",
  "_cranurl": true,
  "_releases": [
    {
      "version": "0.1.0",
      "date": "2026-10-06"
    }
  ],
  "_exports": [
    "html_ancestors",
    "html_attr",
    "html_attrs",
    "html_children",
    "html_classes",
    "html_closest",
    "html_document",
    "html_element",
    "html_elements",
    "html_filter",
    "html_forms",
    "html_fragment",
    "html_info",
    "html_json_ld",
    "html_limits",
    "html_links",
    "html_list",
    "html_markdown",
    "html_matches",
    "html_meta",
    "html_microdata",
    "html_name",
    "html_namespace",
    "html_next_sibling",
    "html_parent",
    "html_parse",
    "html_previous_sibling",
    "html_problems",
    "html_read",
    "html_root",
    "html_serialize",
    "html_strings",
    "html_table",
    "html_table_cells",
    "html_tables",
    "html_template_content",
    "html_text",
    "html_text_clean",
    "html_title",
    "html_type",
    "html_url",
    "zuhtml_info"
  ],
  "_help": [
    {
      "page": "html_attr",
      "title": "Attributes of elements",
      "concept": [
        "node values"
      ],
      "topics": [
        "html_attr",
        "html_attrs",
        "html_classes"
      ]
    },
    {
      "page": "html_children",
      "title": "Navigate a document tree",
      "concept": [
        "navigation"
      ],
      "topics": [
        "html_ancestors",
        "html_children",
        "html_document",
        "html_next_sibling",
        "html_parent",
        "html_previous_sibling",
        "html_root",
        "html_template_content"
      ]
    },
    {
      "page": "html_closest",
      "title": "Nearest ancestor matching a selector",
      "concept": [
        "navigation"
      ],
      "topics": [
        "html_closest"
      ]
    },
    {
      "page": "html_elements",
      "title": "Select elements with CSS selectors",
      "concept": [
        "navigation"
      ],
      "topics": [
        "html_element",
        "html_elements",
        "html_filter",
        "html_matches"
      ]
    },
    {
      "page": "html_forms",
      "title": "Forms and their controls",
      "concept": [
        "extraction"
      ],
      "topics": [
        "html_forms"
      ]
    },
    {
      "page": "html_fragment",
      "title": "Parse an HTML fragment",
      "concept": [
        "parsing"
      ],
      "topics": [
        "html_fragment"
      ]
    },
    {
      "page": "html_info",
      "title": "Information about a parsed document",
      "concept": [
        "parsing"
      ],
      "topics": [
        "html_info"
      ]
    },
    {
      "page": "html_json_ld",
      "title": "JSON-LD blocks",
      "concept": [
        "metadata"
      ],
      "topics": [
        "html_json_ld"
      ]
    },
    {
      "page": "html_limits",
      "title": "Resource limits for parsing and extraction",
      "concept": [
        "parsing"
      ],
      "topics": [
        "html_limits"
      ]
    },
    {
      "page": "html_links",
      "title": "Links in a document",
      "concept": [
        "extraction"
      ],
      "topics": [
        "html_links"
      ]
    },
    {
      "page": "html_list",
      "title": "Extract an HTML list",
      "concept": [
        "extraction"
      ],
      "topics": [
        "html_list"
      ]
    },
    {
      "page": "html_markdown",
      "title": "Convert HTML to Markdown",
      "concept": [
        "node values"
      ],
      "topics": [
        "html_markdown"
      ]
    },
    {
      "page": "html_meta",
      "title": "Meta tags",
      "concept": [
        "metadata"
      ],
      "topics": [
        "html_meta"
      ]
    },
    {
      "page": "html_microdata",
      "title": "Microdata items",
      "concept": [
        "metadata"
      ],
      "topics": [
        "html_microdata"
      ]
    },
    {
      "page": "html_name",
      "title": "Node names, namespaces and types",
      "concept": [
        "node values"
      ],
      "topics": [
        "html_name",
        "html_namespace",
        "html_type"
      ]
    },
    {
      "page": "html_parse",
      "title": "Parse HTML",
      "concept": [
        "parsing"
      ],
      "topics": [
        "html_parse",
        "html_read"
      ]
    },
    {
      "page": "html_problems",
      "title": "Parse problems recorded for a document",
      "concept": [
        "parsing"
      ],
      "topics": [
        "html_problems"
      ]
    },
    {
      "page": "html_serialize",
      "title": "Serialize nodes as HTML",
      "concept": [
        "node values"
      ],
      "topics": [
        "html_serialize"
      ]
    },
    {
      "page": "html_strings",
      "title": "Text pieces of nodes",
      "concept": [
        "node values"
      ],
      "topics": [
        "html_strings"
      ]
    },
    {
      "page": "html_table",
      "title": "Extract HTML tables as data frames",
      "concept": [
        "extraction"
      ],
      "topics": [
        "html_table",
        "html_tables"
      ]
    },
    {
      "page": "html_table_cells",
      "title": "Cells of an HTML table",
      "concept": [
        "extraction"
      ],
      "topics": [
        "html_table_cells"
      ]
    },
    {
      "page": "html_text",
      "title": "Text content of nodes",
      "concept": [
        "node values"
      ],
      "topics": [
        "html_text"
      ]
    },
    {
      "page": "html_text_clean",
      "title": "Cleaned text for extraction",
      "concept": [
        "node values"
      ],
      "topics": [
        "html_text_clean"
      ]
    },
    {
      "page": "html_title",
      "title": "Document title",
      "concept": [
        "metadata"
      ],
      "topics": [
        "html_title"
      ]
    },
    {
      "page": "html_url",
      "title": "Resolve URLs in attributes",
      "concept": [
        "extraction"
      ],
      "topics": [
        "html_url"
      ]
    },
    {
      "page": "zuhtml_info",
      "title": "Report the zuhtml build configuration",
      "concept": [
        "parsing"
      ],
      "topics": [
        "zuhtml_info"
      ]
    },
    {
      "page": "zuhtml-conditions",
      "title": "Conditions raised by zuhtml",
      "topics": [
        "zuhtml-conditions"
      ]
    }
  ],
  "_readme": "https://github.com/pedrobtz/zuhtml/raw/HEAD/README.md",
  "_rundeps": [],
  "_vignettes": [
    {
      "source": "selectors.Rmd",
      "filename": "selectors.html",
      "title": "CSS selectors",
      "engine": "knitr::rmarkdown",
      "headings": [
        "What is supported",
        "What is rejected",
        "Case",
        "Where the search looks"
      ],
      "created": "2026-09-24 18:19:02",
      "modified": "2026-09-24 18:19:02",
      "commits": 1
    },
    {
      "source": "zuhtml.Rmd",
      "filename": "zuhtml.html",
      "title": "Getting started with zuhtml",
      "engine": "knitr::rmarkdown",
      "headings": [
        "A page to work with",
        "Selecting elements",
        "Values",
        "Structures",
        "What the parser repaired",
        "Where next"
      ],
      "created": "2026-09-24 18:19:02",
      "modified": "2026-09-25 01:30:48",
      "commits": 2
    },
    {
      "source": "limits-and-encoding.Rmd",
      "filename": "limits-and-encoding.html",
      "title": "Limits, encodings and safety",
      "engine": "knitr::rmarkdown",
      "headings": [
        "Every call runs under limits",
        "Encodings",
        "Errors are classed",
        "What zuhtml does not do"
      ],
      "created": "2026-09-24 18:19:02",
      "modified": "2026-09-25 01:30:48",
      "commits": 3
    },
    {
      "source": "tables-and-lists.Rmd",
      "filename": "tables-and-lists.html",
      "title": "Tables and lists",
      "engine": "knitr::rmarkdown",
      "headings": [
        "Tables",
        "Spans",
        "Headers",
        "Lists"
      ],
      "created": "2026-09-24 18:19:02",
      "modified": "2026-09-24 18:19:02",
      "commits": 1
    }
  ],
  "_score": 4.778151250383644,
  "_indexed": true,
  "_nocasepkg": "zuhtml",
  "_universes": [
    "pedrobtz"
  ],
  "_previous": "0.1.0",
  "_binaries": [
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "0.1.0.9000",
      "date": "2026-10-13T19:52:06.000Z",
      "distro": "resolute",
      "arch": "aarch64",
      "commit": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
      "fileid": "https://r2.ropensci.org/92fdd9c1ceb2b67d129642d7cde2d09f6bb12366be62bd599287b6fb4e7c3966",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581"
    },
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "0.1.0.9000",
      "date": "2026-10-13T19:52:00.000Z",
      "distro": "resolute",
      "arch": "x86_64",
      "commit": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
      "fileid": "https://r2.ropensci.org/3cd55bec01ce567812ccfed77505e726c479dc5faa6308661d80385a83f33356",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581"
    },
    {
      "r": "4.6.1",
      "os": "linux",
      "version": "0.1.0.9000",
      "date": "2026-10-13T19:52:03.000Z",
      "distro": "resolute",
      "arch": "aarch64",
      "commit": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
      "fileid": "https://r2.ropensci.org/d96e9b1cf4588b431ddcde54eea215cd636d2838edda5537cf00d9e4c05bab0a",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581"
    },
    {
      "r": "4.6.1",
      "os": "linux",
      "version": "0.1.0.9000",
      "date": "2026-10-13T19:51:56.000Z",
      "distro": "resolute",
      "arch": "x86_64",
      "commit": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
      "fileid": "https://r2.ropensci.org/4b08cf6591fce41fd63239afbd60638d3ba872965d7ec89d860a48b5d10a0a8a",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "0.1.0.9000",
      "date": "2026-10-13T20:12:42.000Z",
      "arch": "aarch64",
      "commit": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
      "fileid": "https://r2.ropensci.org/eba7d26c657c473fcb620886803666bad97e4e553abb94538426989096f18c35",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "0.1.0.9000",
      "date": "2026-10-13T20:14:12.000Z",
      "arch": "x86_64",
      "commit": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
      "fileid": "https://r2.ropensci.org/14a808a1741e420ef55789099a9993d2b2c2df53bfb6de670a2db2d54e78f9d6",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581"
    },
    {
      "r": "4.6.1",
      "os": "mac",
      "version": "0.1.0.9000",
      "date": "2026-10-13T20:07:23.000Z",
      "arch": "aarch64",
      "commit": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
      "fileid": "https://r2.ropensci.org/e6be86d4b40e6a2945afa09189d472d8e656622a2ae63218c4ff33285a150442",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581"
    },
    {
      "r": "4.6.1",
      "os": "mac",
      "version": "0.1.0.9000",
      "date": "2026-10-13T20:12:17.000Z",
      "arch": "x86_64",
      "commit": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
      "fileid": "https://r2.ropensci.org/02d61689165061d554838bbce953b44228acafb7459ad15da1ed2969b0e338c6",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581"
    },
    {
      "r": "4.6.0",
      "os": "wasm",
      "version": "0.1.0.9000",
      "date": "2026-10-13T19:51:32.000Z",
      "arch": "emscripten",
      "commit": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
      "fileid": "https://r2.ropensci.org/5a358216fbcc94889d0c15892478601ee8bb5c3a5308823c37f085cffbe95e68",
      "status": "success",
      "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "0.1.0.9000",
      "date": "2026-10-13T19:53:11.000Z",
      "arch": "aarch64",
      "commit": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
      "fileid": "https://r2.ropensci.org/4055a75c9ddfad04f8741b10f50a79a2c066372c3127f1e301fb1ed755394385",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "0.1.0.9000",
      "date": "2026-10-13T19:51:04.000Z",
      "arch": "x86_64",
      "commit": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
      "fileid": "https://r2.ropensci.org/08fece2552bdd3ebefb906f64112216f886ffb6f473c120e6739ad03151a36bf",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581"
    },
    {
      "r": "4.5.3",
      "os": "win",
      "version": "0.1.0.9000",
      "date": "2026-10-13T19:51:02.000Z",
      "arch": "x86_64",
      "commit": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
      "fileid": "https://r2.ropensci.org/dd126886f752b4f90ffe73d39668e4f69d533f4ec8e3959896844e2d8e567f22",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581"
    },
    {
      "r": "4.6.1",
      "os": "win",
      "version": "0.1.0.9000",
      "date": "2026-10-13T19:52:47.000Z",
      "arch": "aarch64",
      "commit": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
      "fileid": "https://r2.ropensci.org/539aa45e8b98c1bda0199338fa23d5ee05ecd8cff0d74e822ff371b348bee52c",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581"
    },
    {
      "r": "4.6.1",
      "os": "win",
      "version": "0.1.0.9000",
      "date": "2026-10-13T19:51:38.000Z",
      "arch": "x86_64",
      "commit": "e9f7a2078ca16bb7c89a9847db9d187840da9971",
      "fileid": "https://r2.ropensci.org/d0dc65a5f0c391b21efe7523751161e9f8b4b5c32e40c62c0edca30f52efce67",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/38457287581"
    }
  ]
}