{ "_id": "6ae107a6327abcdf868638fb", "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(), 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'' 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": "2026-10-27 15:46:06 UTC", "RemoteUrl": "https://github.com/pedrobtz/zuhtml", "RemoteRef": "HEAD", "RemoteSha": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-10-27 20:15:54 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 ", "_user": "pedrobtz", "_type": "src", "_file": "zuhtml_0.1.0.9000.tar.gz", "_fileid": "https://r2.ropensci.org/9e699942472b65e007a28e8cb478bd9f9f1386c438fdbae5dee197b480be71de", "_filesize": 525349, "_sha256": "9e699942472b65e007a28e8cb478bd9f9f1386c438fdbae5dee197b480be71de", "_expires": "2027-02-04T20:20:52.000Z", "_created": "2026-10-27T20:15:54.000Z", "_published": "2026-10-27T20:20:54.541Z", "_upstream": "https://github.com/pedrobtz/zuhtml", "_status": "success", "_maintainer": { "name": "Pedro Baltazar", "email": "pedrobtz@gmail.com", "login": "pedrobtz", "description": "\n", "uuid": 2864346 }, "_jobs": [ { "job": 122444362897, "time": 101, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "12766508510" }, { "job": 122444362899, "time": 123, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "12765839375" }, { "job": 122444363032, "time": 117, "config": "linux-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "12767378083" }, { "job": 122444363056, "time": 113, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "12767827253" }, { "job": 122444363015, "time": 136, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "12767897102" }, { "job": 122444363034, "time": 194, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "12767444551" }, { "job": 122444362853, "time": 106, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "12768315418" }, { "job": 122444363073, "time": 228, "config": "macos-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "12768335781" }, { "job": 122442908523, "time": 161, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "12768050395" }, { "job": 122444362941, "time": 84, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "12768450039" }, { "job": 122444363087, "time": 235, "config": "windows-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "12767464602" }, { "job": 122444363088, "time": 162, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "12766878427" }, { "job": 122444362992, "time": 104, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "12767637398" }, { "job": 122444362878, "time": 256, "config": "windows-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "12768260886" }, { "job": 122444362988, "time": 87, "config": "windows-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "12765894371" } ], "_buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400", "_commit": { "id": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "author": "Pedro Z ", "committer": "GitHub ", "message": "Post-release: zuhtml 0.1.0 [skip ci]\n\nCo-authored-by: Claude Opus 5.5 ", "time": 1793115966 }, "_distro": "resolute", "_host": "GitHub-Actions", "_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 }, { "week": "2026-44", "n": 1 } ], "_tags": [ { "name": "0.1.0", "date": "2026-09-25" } ], "_stars": 0, "_contributors": [ { "user": "pedrobtz", "count": 63, "uuid": 2864346 } ], "_userbio": { "uuid": 2864346, "type": "user", "name": "Pedro Z", "followers": 0 }, "_downloads": { "count": 324, "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": 4.903089986991944, "_indexed": true, "_nocasepkg": "zuhtml", "_universes": [ "pedrobtz" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.0.9000", "date": "2026-10-27T20:17:36.000Z", "distro": "resolute", "arch": "aarch64", "commit": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "fileid": "https://r2.ropensci.org/c2c210ea0c148b49ada9bbe287a6cc4ae2669e4d395aff8bbb7e29921f110626", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400" }, { "r": "4.7.0", "os": "linux", "version": "0.1.0.9000", "date": "2026-10-27T20:17:50.000Z", "distro": "resolute", "arch": "x86_64", "commit": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "fileid": "https://r2.ropensci.org/4dfe58c02c484ed5072c4a0706c2227e223178f5269b2d354c918952d1b342e3", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400" }, { "r": "4.6.1", "os": "linux", "version": "0.1.0.9000", "date": "2026-10-27T20:17:55.000Z", "distro": "resolute", "arch": "aarch64", "commit": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "fileid": "https://r2.ropensci.org/05de1ae4c7eb4b714cb552d6e9b1ed4aa9a7b6890dfa4aa47b768e80d376184a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400" }, { "r": "4.6.1", "os": "linux", "version": "0.1.0.9000", "date": "2026-10-27T20:17:45.000Z", "distro": "resolute", "arch": "x86_64", "commit": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "fileid": "https://r2.ropensci.org/823a095abd8fe08266c197a66949b12f384de36ac79e6640a066d0c03797a35a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400" }, { "r": "4.5.3", "os": "mac", "version": "0.1.0.9000", "date": "2026-10-27T20:18:04.000Z", "arch": "aarch64", "commit": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "fileid": "https://r2.ropensci.org/1f63dd4987fa139c513278e233975a3bd5e1c0815486f2d01ec6d9c1b8b0650a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400" }, { "r": "4.5.3", "os": "mac", "version": "0.1.0.9000", "date": "2026-10-27T20:18:48.000Z", "arch": "x86_64", "commit": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "fileid": "https://r2.ropensci.org/f7ec7f8b2f97e381ae09e7dfecb25d688b02bb7c57f2b438477506cfb94396a3", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400" }, { "r": "4.6.1", "os": "mac", "version": "0.1.0.9000", "date": "2026-10-27T20:17:38.000Z", "arch": "aarch64", "commit": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "fileid": "https://r2.ropensci.org/1318a55b37abc091eac8400a212ba4f529c0e6c19500ed5041791d42c009e327", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400" }, { "r": "4.6.1", "os": "mac", "version": "0.1.0.9000", "date": "2026-10-27T20:19:05.000Z", "arch": "x86_64", "commit": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "fileid": "https://r2.ropensci.org/d8d8811992622ce02860ec4dd8bca1c4e58db97b27f137667ffe916a0348eae7", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.0.9000", "date": "2026-10-27T20:17:38.000Z", "arch": "emscripten", "commit": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "fileid": "https://r2.ropensci.org/2d49ffa9b7ec5c3c5443606cee71f483c4c990b8c56f5ae03913fb306ada95ee", "status": "success", "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400" }, { "r": "4.7.0", "os": "win", "version": "0.1.0.9000", "date": "2026-10-27T20:19:24.000Z", "arch": "aarch64", "commit": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "fileid": "https://r2.ropensci.org/78ceac71a801f8154048586b5f88adc52028cc0eaaa9007a1e3a65c039800acb", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400" }, { "r": "4.7.0", "os": "win", "version": "0.1.0.9000", "date": "2026-10-27T20:17:21.000Z", "arch": "x86_64", "commit": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "fileid": "https://r2.ropensci.org/fe1ca2d5031af731fa96707a71e2e31e9ff4bcec7153915b6e27144173ce10fb", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400" }, { "r": "4.5.3", "os": "win", "version": "0.1.0.9000", "date": "2026-10-27T20:17:07.000Z", "arch": "x86_64", "commit": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "fileid": "https://r2.ropensci.org/b3e1fe5ab92cb181107320fe72825ddf48f61bf7fbea53d84ae6795f8d1f6aab", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400" }, { "r": "4.6.1", "os": "win", "version": "0.1.0.9000", "date": "2026-10-27T20:19:44.000Z", "arch": "aarch64", "commit": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "fileid": "https://r2.ropensci.org/c79dab946db7b995d8fe07b5b2fc9f548b59aac899fd2376d4a411ca0757ace7", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400" }, { "r": "4.6.1", "os": "win", "version": "0.1.0.9000", "date": "2026-10-27T20:17:02.000Z", "arch": "x86_64", "commit": "e3d96c07bfa9a8698aedbaf1ccbac15c812b12c3", "fileid": "https://r2.ropensci.org/9d14b135626c94301b9d7328360947513b8f32a980baa62e441b97c8a1f844b8", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pedrobtz/actions/runs/40576074400" } ] }