{ "_id": "6a23d558530b9bc726be4d0d", "Package": "docxtractr", "Title": "Extract Data Tables and Comments from 'Microsoft' 'Word'\nDocuments", "Version": "0.6.5", "Authors@R": "c(\nperson(\"Bob\", \"Rudis\", email = \"bob@rud.is\", role = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0001-5670-2640\")),\nperson(\"Mark\", \"Dulhunty\", role = c(\"ctb\")),\nperson(\"Karlo\", \"Guidoni-Martins\", role = c(\"ctb\"), email = \"kguidonimartins@gmail.com\"),\nperson(\"Chris\", \"Muir\", email = \"chrismuirrva@gmail.com\", role = c(\"aut\", \"ctb\"))\n)", "Maintainer": "Bob Rudis ", "Description": "'Microsoft Word' 'docx' files provide an 'XML' structure\nthat is fairly straightforward to navigate, especially when it\napplies to 'Word' tables and comments. Tools are provided to\ndetermine table count/structure, comment count and also to\nextract/clean tables and comments from 'Microsoft Word' 'docx'\ndocuments. There is also nascent support for '.doc' files.", "SystemRequirements": "LibreOffice ()\nrequired to extract data from .doc files or perform .pptx\nconversion.", "URL": "http://gitlab.com/hrbrmstr/docxtractr", "BugReports": "https://gitlab.com/hrbrmstr/docxtractr/issues", "Encoding": "UTF-8", "License": "MIT + file LICENSE", "RoxygenNote": "7.1.0", "Config/pak/sysreqs": "libxml2-dev libssl-dev", "Repository": "https://hrbrmstr.r-universe.dev", "Date/Publication": "2020-07-04 12:32:47 UTC", "RemoteUrl": "https://github.com/hrbrmstr/docxtractr", "RemoteRef": "HEAD", "RemoteSha": "a2855a442d4bbe87232ebd3b023002d9e73bbc5b", "NeedsCompilation": "no", "Packaged": { "Date": "2026-06-06 08:04:37 UTC", "User": "root" }, "Author": "Bob Rudis [aut, cre] (ORCID: ),\nMark Dulhunty [ctb],\nKarlo Guidoni-Martins [ctb],\nChris Muir [aut, ctb]", "MD5sum": "3b5978fede89bbcaa77b1b32ce43a86f", "_user": "hrbrmstr", "_type": "src", "_file": "docxtractr_0.6.5.tar.gz", "_fileid": "fd14b345d8da9aaf1b71799817a4d2660bcf4c3c4b76129137dc87010868ecbf", "_filesize": 618458, "_sha256": "fd14b345d8da9aaf1b71799817a4d2660bcf4c3c4b76129137dc87010868ecbf", "_created": "2026-06-06T08:04:37.000Z", "_published": "2026-06-06T08:07:52.203Z", "_distro": "noble", "_jobs": [ { "job": 79863045036, "time": 161, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7452704946" }, { "job": 79863045032, "time": 114, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7452700068" }, { "job": 79863045042, "time": 101, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7452698698" }, { "job": 79863045041, "time": 80, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7452696300" }, { "job": 79862882896, "time": 176, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7452687514" }, { "job": 79863045031, "time": 98, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7452698089" }, { "job": 79863045052, "time": 73, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7452696140" }, { "job": 79863045055, "time": 85, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7452696863" }, { "job": 79863045056, "time": 68, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7452694977" } ], "_buildurl": "https://github.com/r-universe/hrbrmstr/actions/runs/27056905815", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/hrbrmstr/docxtractr", "_commit": { "id": "a2855a442d4bbe87232ebd3b023002d9e73bbc5b", "author": "hrbrmstr ", "committer": "hrbrmstr ", "message": "cran check errors fixes\n", "time": 1593865967 }, "_maintainer": { "name": "Bob Rudis", "email": "bob@rud.is", "login": "hrbrmstr", "mastodon": "@hrbrmstr@mastodon.social", "bluesky": "@hrbrmstr.dev", "orcid": "0000-0001-5670-2640", "description": "🇺🇦 Pampa • Don't look at me…I do what he does—just slower. #rstats avuncular•👨‍🍳•✝️• 💤• Distinguished Engineer @ Censys + CMU Lecturer", "uuid": 509878 }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.6.0", "role": "Depends" }, { "package": "tools", "role": "Imports" }, { "package": "xml2", "role": "Imports" }, { "package": "purrr", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "httr", "role": "Imports" }, { "package": "magrittr", "role": "Imports" }, { "package": "covr", "role": "Suggests" }, { "package": "tinytest", "role": "Suggests" } ], "_owner": "hrbrmstr", "_selfowned": true, "_usedby": 0, "_updates": [], "_tags": [], "_topics": [ "docx", "extract-tables", "microsoft-word", "table-extraction" ], "_stars": 176, "_contributors": [ { "user": "hrbrmstr", "count": 47, "uuid": 509878 }, { "user": "muschellij2", "count": 18, "uuid": 1075118 }, { "user": "chrismuir", "count": 7, "uuid": 13386824 }, { "user": "markdly", "count": 4, "uuid": 8509894 }, { "user": "jimhester", "count": 1, "uuid": 205275 }, { "user": "kguidonimartins", "count": 1, "uuid": 8163542 }, { "user": "ironholds", "count": 1, "uuid": 2487262 }, { "user": "sangeetabhatia03", "count": 1, "uuid": 15316049 } ], "_userbio": { "uuid": 509878, "type": "user", "name": "boB Rudis", "description": "🇺🇦 Pampa • Don't look at me…I do what he does—just slower. #rstats avuncular•👨‍🍳•✝️• 💤• Distinguished Engineer @ Censys + CMU Lecturer" }, "_downloads": { "count": 1125, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/docxtractr" }, "_devurl": "https://gitlab.com/hrbrmstr/docxtractr", "_searchresults": 250, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/docxtractr.html", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_homeurl": "https://github.com/hrbrmstr/docxtractr", "_realowner": "hrbrmstr", "_cranurl": true, "_releases": [ { "version": "0.1.0.9000", "date": "2015-08-29" }, { "version": "0.2.0", "date": "2016-07-20" }, { "version": "0.5.0", "date": "2018-09-18" }, { "version": "0.6.1", "date": "2019-01-09" }, { "version": "0.6.2", "date": "2020-06-13" }, { "version": "0.6.3", "date": "2020-06-13" }, { "version": "0.6.5", "date": "2020-07-05" } ], "_exports": [ "%>%", "assign_colnames", "convert_to_pdf", "docx_cmnt_count", "docx_describe_cmnts", "docx_describe_tbls", "docx_extract_all", "docx_extract_all_cmnts", "docx_extract_all_tbls", "docx_extract_tbl", "docx_tbl_count", "mcga", "read_docx", "set_libreoffice_path" ], "_help": [ { "page": "assign_colnames", "title": "Make a specific row the column names for the specified data.frame", "topics": [ "assign_colnames" ] }, { "page": "convert_to_pdf", "title": "Convert a Document (usually PowerPoint) to a PDF", "topics": [ "convert_to_pdf" ] }, { "page": "docx_cmnt_count", "title": "Get number of comments in a Word document", "topics": [ "docx_cmnt_count" ] }, { "page": "docx_describe_cmnts", "title": "Returns information about the comments in the Word document", "topics": [ "docx_describe_cmnts" ] }, { "page": "docx_describe_tbls", "title": "Returns a description of all the tables in the Word document", "topics": [ "docx_describe_tbls" ] }, { "page": "docx_extract_all", "title": "Extract all tables from a Word document", "topics": [ "docx_extract_all" ] }, { "page": "docx_extract_all_cmnts", "title": "Extract all comments from a Word document", "topics": [ "docx_extract_all_cmnts" ] }, { "page": "docx_extract_all_tbls", "title": "Extract all tables from a Word document", "topics": [ "docx_extract_all_tbls" ] }, { "page": "docx_extract_tbl", "title": "Extract a table from a Word document", "topics": [ "docx_extract_tbl" ] }, { "page": "docx_tbl_count", "title": "Get number of tables in a Word document", "topics": [ "docx_tbl_count" ] }, { "page": "docxtractr", "title": "Extract Data Tables and Comments from 'Microsoft' 'Word' Documents", "topics": [ "docxtractr" ] }, { "page": "mcga", "title": "Make Column Names Great Again", "topics": [ "mcga" ] }, { "page": "print.docx", "title": "Display information about the document", "topics": [ "print.docx" ] }, { "page": "read_docx", "title": "Read in a Word document for table extraction", "topics": [ "read_docx" ] }, { "page": "set_libreoffice_path", "title": "Point to Local soffice.exe File", "topics": [ "set_libreoffice_path" ] } ], "_readme": "https://github.com/hrbrmstr/docxtractr/raw/HEAD/README.md", "_rundeps": [ "askpass", "cli", "curl", "dplyr", "generics", "glue", "httr", "jsonlite", "lifecycle", "magrittr", "mime", "openssl", "pillar", "pkgconfig", "purrr", "R6", "rlang", "sys", "tibble", "tidyselect", "utf8", "vctrs", "withr", "xml2" ], "_score": 7.238673243283845, "_indexed": true, "_nocasepkg": "docxtractr", "_universes": [ "hrbrmstr", "gitlab-hrbrmstr" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.6.5", "date": "2026-06-06T08:07:15.000Z", "distro": "noble", "commit": "a2855a442d4bbe87232ebd3b023002d9e73bbc5b", "fileid": "260a8efabc24ef51b1418e1e14b2209f7ecc3b590332cfaa096933ce19c0164a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/hrbrmstr/actions/runs/27056905815" }, { "r": "4.6.0", "os": "linux", "version": "0.6.5", "date": "2026-06-06T08:06:29.000Z", "distro": "noble", "commit": "a2855a442d4bbe87232ebd3b023002d9e73bbc5b", "fileid": "d23c2e3c42655f9dfb183f4316462597c6c7f87d40ddb9ae8c88dbe3835e5172", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/hrbrmstr/actions/runs/27056905815" }, { "r": "4.5.3", "os": "mac", "version": "0.6.5", "date": "2026-06-06T08:06:20.000Z", "commit": "a2855a442d4bbe87232ebd3b023002d9e73bbc5b", "fileid": "3b08b830017f1b8e4555327be07a5edc704432b0b1225e847d6269b1eef3b926", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/hrbrmstr/actions/runs/27056905815" }, { "r": "4.6.0", "os": "mac", "version": "0.6.5", "date": "2026-06-06T08:06:00.000Z", "commit": "a2855a442d4bbe87232ebd3b023002d9e73bbc5b", "fileid": "edd0fc08728235a8c48870bcef8f81b98e97666dc69fa9144ce68d064cefa838", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/hrbrmstr/actions/runs/27056905815" }, { "r": "4.6.0", "os": "wasm", "version": "0.6.5", "date": "2026-06-06T08:06:28.000Z", "commit": "a2855a442d4bbe87232ebd3b023002d9e73bbc5b", "fileid": "827c10498fc4067ffb0a5404066b2adebe740d46dc9527ce5ca52ba63a1e957c", "status": "success", "buildurl": "https://github.com/r-universe/hrbrmstr/actions/runs/27056905815" }, { "r": "4.7.0", "os": "win", "version": "0.6.5", "date": "2026-06-06T08:05:48.000Z", "commit": "a2855a442d4bbe87232ebd3b023002d9e73bbc5b", "fileid": "aa54ee44692506292fa980703ce6cfdb443a373ce0c21866d7d21d1cbe35aaa9", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/hrbrmstr/actions/runs/27056905815" }, { "r": "4.5.3", "os": "win", "version": "0.6.5", "date": "2026-06-06T08:05:56.000Z", "commit": "a2855a442d4bbe87232ebd3b023002d9e73bbc5b", "fileid": "c67c20a8cd5dea4cb4f6ec9ffe74c2334221dafd1ef6942f730a4899acd89512", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/hrbrmstr/actions/runs/27056905815" }, { "r": "4.6.0", "os": "win", "version": "0.6.5", "date": "2026-06-06T08:05:37.000Z", "commit": "a2855a442d4bbe87232ebd3b023002d9e73bbc5b", "fileid": "b711be3ee2abff153b1ed53a10feb90d0c802b4f8192042efe338e4cb1aebc58", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/hrbrmstr/actions/runs/27056905815" } ] }