download_webpage_txt
saves output to a .txt file.
download_webpage_pdf
saves output to a .pdf file.
Usage
download_webpage_txt(
url,
output_filepath = NA,
output_dir = "input",
output_filename = "posting.txt",
base_dir = "."
)
download_webpage_pdf(
url,
output_filepath = NA,
output_dir = "input",
output_filename = "posting.pdf"
)
See also
Other report-dev:
find_matches_and_positions()
,
prep_term_list()
Examples
library(rvest, warn.conflicts = FALSE)
url <- "https://en.wikipedia.org/wiki/R_(programming_language)"
fil <- tempfile("file", tempdir(), fileext = ".txt")
download_webpage_txt(url, fil)
#> ✔ Writing file: ../../../../../../../tmp/Rtmp1Y1jwG/file739431d3ffb4.txt
readLines(fil, n = 1)
#> [1] "R (programming language) - Wikipedia(function(){var className=\"client-js vector-feature-language-in-header-enabled vector-feature-language-in-main-page-header-disabled vector-feature-page-tools-pinned-disabled vector-feature-toc-pinned-clientpref-1 vector-feature-main-menu-pinned-disabled vector-feature-limited-width-clientpref-1 vector-feature-limited-width-content-enabled vector-feature-custom-font-size-clientpref-1 vector-feature-appearance-pinned-clientpref-1 vector-feature-night-mode-enabled skin-theme-clientpref-day vector-sticky-header-enabled vector-toc-available\";var cookie=document.cookie.match(/(?:^|; )enwikimwclientpreferences=([^;]+)/);if(cookie){cookie[1].split('%2C').forEach(function(pref){className=className.replace(new RegExp('(^| )'+pref.replace(/-clientpref-\\w+$|[^\\w-]+/g,'')+'-clientpref-\\\\w+( |$)'),'$1'+pref+'$2');});}document.documentElement.className=className;}());RLCONF={\"wgBreakFrames\":false,\"wgSeparatorTransformTable\":[\"\",\"\"],\"wgDigitTransformTable\":[\"\",\"\"],\"wgDefaultDateFormat\":\"dmy\",\"wgMonthNames\":[\"\",\"January\",\"February\",\"March\",\"April\",\"May\",\"June\",\"July\",\"August\",\"September\",\"October\",\"November\",\"December\"],\"wgRequestId\":\"86a6ab7e-6f46-4e39-89cb-2d16698e2690\",\"wgCanonicalNamespace\":\"\",\"wgCanonicalSpecialPageName\":false,\"wgNamespaceNumber\":0,\"wgPageName\":\"R_(programming_language)\",\"wgTitle\":\"R (programming language)\",\"wgCurRevisionId\":1285232827,\"wgRevisionId\":1285232827,\"wgArticleId\":376707,\"wgIsArticle\":true,\"wgIsRedirect\":false,\"wgAction\":\"view\",\"wgUserName\":null,\"wgUserGroups\":[\"*\"],\"wgCategories\":[\"CS1 Brazilian Portuguese-language sources (pt-br)\",\"CS1 maint: publisher location\",\"Articles with short description\",\"Short description is different from Wikidata\",\"Use dmy dates from June 2018\",\"Articles containing potentially dated statements from October 2024\",\"All articles containing potentially dated statements\",\"All articles with unsourced statements\",\"Articles with unsourced statements from March 2025\",\"All articles lacking reliable references\",\"Articles lacking reliable references from April 2024\",\"Wikipedia articles needing page number citations from April 2024\",\"Articles with example R code\",\"R (programming language)\",\"Array programming languages\",\"Cross-platform free software\",\"Data mining and machine learning software\",\"Data-centric programming languages\",\"Dynamically typed programming languages\",\"Free plotting software\",\"Free statistical software\",\"Functional languages\",\"GNU Project software\",\"Literate programming\",\"Numerical analysis software for Linux\",\"Numerical analysis software for macOS\",\"Numerical analysis software for Windows\",\"Programming languages created in 1993\",\"Science software\",\"Statistical programming languages\"],\"wgPageViewLanguage\":\"en\",\"wgPageContentLanguage\":\"en\",\"wgPageContentModel\":\"wikitext\",\"wgRelevantPageName\":\"R_(programming_language)\",\"wgRelevantArticleId\":376707,\"wgIsProbablyEditable\":true,\"wgRelevantPageIsProbablyEditable\":true,\"wgRestrictionEdit\":[],\"wgRestrictionMove\":[],\"wgNoticeProject\":\"wikipedia\",\"wgCiteReferencePreviewsActive\":false,\"wgFlaggedRevsParams\":{\"tags\":{\"status\":{\"levels\":1}}},\"wgMediaViewerOnClick\":true,\"wgMediaViewerEnabledByDefault\":true,\"wgPopupsFlags\":0,\"wgVisualEditor\":{\"pageLanguageCode\":\"en\",\"pageLanguageDir\":\"ltr\",\"pageVariantFallbacks\":\"en\"},\"wgMFDisplayWikibaseDescriptions\":{\"search\":true,\"watchlist\":true,\"tagline\":false,\"nearby\":true},\"wgWMESchemaEditAttemptStepOversample\":false,\"wgWMEPageLength\":70000,\"wgEditSubmitButtonLabelPublish\":true,\"wgULSPosition\":\"interlanguage\",\"wgULSisCompactLinksEnabled\":false,\"wgVector2022LanguageInHeader\":true,\"wgULSisLanguageSelectorEmpty\":false,\"wgWikibaseItemId\":\"Q206904\",\"wgCheckUserClientHintsHeadersJsApi\":[\"brands\",\"architecture\",\"bitness\",\"fullVersionList\",\"mobile\",\"model\",\"platform\",\"platformVersion\"],\"GEHomepageSuggestedEditsEnableTopics\":true,\"wgGETopicsMatchModeEnabled\":false,\"wgGELevelingUpEnabledForUser\":false};"
unlink(fil)
url <- "https://stat.ethz.ch/R-manual/R-devel/library/utils/html/download.file.html"
fil <- tempfile("file", tempdir(), fileext = ".pdf")
download_webpage_pdf(url, fil)
unlink(fil)