{ "_id": "6a1f18feb401979e7341ee3b", "Package": "boilerpipeR", "Version": "1.3.2", "Date": "2021-05-19", "Title": "Interface to the Boilerpipe Java Library", "Author": "See AUTHORS file.", "Maintainer": "Mario Annau ", "Description": "Generic Extraction of main text content from HTML files;\nremoval of ads, sidebars and headers using the boilerpipe\n Java library. The\nextraction heuristics from boilerpipe show a robust performance\nfor a wide range of web site templates.", "License": "Apache License (== 2.0)", "URL": "https://github.com/mannau/boilerpipeR", "BugReports": "https://github.com/mannau/boilerpipeR/issues", "RoxygenNote": "7.1.1", "Encoding": "UTF-8", "Config/pak/sysreqs": "make default-jdk", "Repository": "https://mannau.r-universe.dev", "Date/Publication": "2021-05-19 09:05:01 UTC", "RemoteUrl": "https://github.com/mannau/boilerpiper", "RemoteRef": "HEAD", "RemoteSha": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "NeedsCompilation": "no", "Packaged": { "Date": "2026-05-17 05:31:25 UTC", "User": "root" }, "MD5sum": "f44902aa1543db20e1beed6c8c22cd60", "_user": "mannau", "_type": "src", "_file": "boilerpipeR_1.3.2.tar.gz", "_fileid": "f31fb749787c84040df31713674a3c05bfed7818cf77c6bdab94d0f61b9be970", "_filesize": 1674216, "_sha256": "f31fb749787c84040df31713674a3c05bfed7818cf77c6bdab94d0f61b9be970", "_created": "2026-05-17T05:31:25.000Z", "_published": "2026-06-02T17:55:10.402Z", "_distro": "noble", "_jobs": [ { "job": 79137029449, "time": 123, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "7039644338" }, { "job": 79137029986, "time": 112, "config": "linux-release-x86_64", "r": "4.6.0", "check": "NOTE", "artifact": "7039643327" }, { "job": 79137029421, "time": 150, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "NOTE", "artifact": "7039644216" }, { "job": 79137029720, "time": 148, "config": "macos-release-arm64", "r": "4.6.0", "check": "NOTE", "artifact": "7039644224" }, { "job": 79137028480, "time": 174, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7039632267" }, { "job": 79137028709, "time": 100, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7365708867" }, { "job": 79137029467, "time": 80, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "7039640314" }, { "job": 79137029642, "time": 60, "config": "windows-oldrel", "r": "4.5.3", "check": "NOTE", "artifact": "7039638463" }, { "job": 79137029416, "time": 91, "config": "windows-release", "r": "4.6.0", "check": "NOTE", "artifact": "7039641310" } ], "_buildurl": "https://github.com/r-universe/mannau/actions/runs/25982384609", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/mannau/boilerpiper", "_commit": { "id": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "author": "mannau ", "committer": "mannau ", "message": "Add angle brackets to DESCRIPTION URL\n", "time": 1621415101 }, "_maintainer": { "name": "Mario Annau", "email": "mario.annau@gmail.com", "login": "mannau", "description": "CEO and Founder of Quantargo, certified trainer and consultant working on data science projects.", "uuid": 1262952 }, "_registered": true, "_dependencies": [ { "package": "rJava", "role": "Imports" }, { "package": "RCurl", "role": "Suggests" } ], "_owner": "mannau", "_selfowned": true, "_usedby": 0, "_updates": [], "_tags": [], "_stars": 21, "_contributors": [ { "user": "mannau", "count": 38, "uuid": 1262952 } ], "_userbio": { "uuid": 1262952, "type": "user", "name": "Mario Annau", "description": "CEO and Founder of Quantargo, certified trainer and consultant working on data science projects." }, "_downloads": { "count": 262, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/boilerpipeR" }, "_devurl": "https://github.com/mannau/boilerpiper", "_searchresults": 30, "_topics": [ "openjdk" ], "_rbuild": "4.6.0", "_assets": [ "extra/boilerpipeR.html", "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_homeurl": "https://github.com/mannau/boilerpiper", "_realowner": "mannau", "_cranurl": true, "_releases": [ { "version": "1.0", "date": "2012-12-21" }, { "version": "1.1", "date": "2014-01-11" }, { "version": "1.2", "date": "2014-05-12" }, { "version": "1.2.2", "date": "2014-08-21" }, { "version": "1.3", "date": "2015-05-11" }, { "version": "1.3.2", "date": "2021-05-19" } ], "_exports": [ "ArticleExtractor", "ArticleSentencesExtractor", "CanolaExtractor", "DefaultExtractor", "Extractor", "KeepEverythingExtractor", "LargestContentExtractor", "NumWordsRulesExtractor" ], "_datasets": [ { "name": "content", "title": "Wordpress generated Webpage (retrieved from Quantivity Blog ). Content is saved as character and ready to be extracted.", "object": "content", "file": "content.rda", "class": [ "character" ], "fields": [], "table": false, "tojson": true } ], "_help": [ { "page": "boilerpipeR-package", "title": "Extract the main content from HTML files", "topics": [ "boilerpipeR-package", "boilerpipe" ] }, { "page": "ArticleExtractor", "title": "A full-text extractor which is tuned towards news articles.", "topics": [ "ArticleExtractor" ] }, { "page": "ArticleSentencesExtractor", "title": "A full-text extractor which is tuned towards extracting sentences from news articles.", "topics": [ "ArticleSentencesExtractor" ] }, { "page": "CanolaExtractor", "title": "A full-text extractor trained on a 'krdwrd' Canola (see 'https://krdwrd.org/trac/attachment/wiki/Corpora/Canola/CANOLA.pdf'.", "topics": [ "CanolaExtractor" ] }, { "page": "content", "title": "Wordpress generated Webpage (retrieved from Quantivity Blog ). Content is saved as character and ready to be extracted.", "topics": [ "content" ] }, { "page": "DefaultExtractor", "title": "A quite generic full-text extractor.", "topics": [ "DefaultExtractor" ] }, { "page": "Extractor", "title": "Generic extraction function which calls boilerpipe extractors", "topics": [ "Extractor" ] }, { "page": "KeepEverythingExtractor", "title": "Marks everything as content.", "topics": [ "KeepEverythingExtractor" ] }, { "page": "LargestContentExtractor", "title": "A full-text extractor which extracts the largest text component of a page.", "topics": [ "LargestContentExtractor" ] }, { "page": "NumWordsRulesExtractor", "title": "A quite generic full-text extractor solely based upon the number of words per block (the current, the previous and the next block).", "topics": [ "NumWordsRulesExtractor" ] } ], "_readme": "https://github.com/mannau/boilerpiper/raw/HEAD/README.md", "_rundeps": [ "rJava" ], "_sysdeps": [ { "shlib": "libjvm", "package": "openjdk-21-jre-headless", "headers": "openjdk-21-jre-headless", "source": "openjdk", "version": "21.0.10+7-1~24.04", "name": "openjdk", "homepage": "https://openjdk.java.net/", "description": "OpenJDK Java runtime, using Hotspot JIT (headless)" } ], "_vignettes": [ { "source": "ShortIntro.Rnw", "filename": "ShortIntro.pdf", "title": "Introduction to the tm.plugin.webmining Package", "engine": "utils::Sweave", "headings": [], "created": "2013-12-31 12:37:32", "modified": "2021-05-19 07:49:05", "commits": 4 } ], "_score": 5.498310553789601, "_indexed": true, "_nocasepkg": "boilerpiper", "_universes": [ "mannau" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.3.2", "date": "2026-05-17T05:33:29.000Z", "distro": "noble", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "267bd3125deebc84df94c195d176f69858edb5adf5ff39929689192eedd0b829", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mannau/actions/runs/25982384609" }, { "r": "4.6.0", "os": "linux", "version": "1.3.2", "date": "2026-05-17T05:33:18.000Z", "distro": "noble", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "20a58e10f3a473f62c4400049b8a73dfb73ca139e68ede429e53cb4e43451f7f", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mannau/actions/runs/25982384609" }, { "r": "4.5.3", "os": "mac", "version": "1.3.2", "date": "2026-05-17T05:33:35.000Z", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "51c174e5abef6d264757b125565612c0303b58cb041b70b74c8e8d57d8871801", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mannau/actions/runs/25982384609" }, { "r": "4.6.0", "os": "mac", "version": "1.3.2", "date": "2026-05-17T05:33:30.000Z", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "ead9d043b89ecb9c5ea5cb893383111659e9e39c2b9765a7858ff26c22920e37", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mannau/actions/runs/25982384609" }, { "r": "4.7.0", "os": "win", "version": "1.3.2", "date": "2026-05-17T05:32:36.000Z", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "459bc60c93825bddbdefdb0e2edc0dedb7e0a5410166022bccda501b2a82867d", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mannau/actions/runs/25982384609" }, { "r": "4.5.3", "os": "win", "version": "1.3.2", "date": "2026-05-17T05:32:24.000Z", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "dbe1bc43aa18d567f89e1bd671a9cc7db08f70badd24e7d4fd06961d4e5f37a5", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mannau/actions/runs/25982384609" }, { "r": "4.6.0", "os": "win", "version": "1.3.2", "date": "2026-05-17T05:32:29.000Z", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "119e05b96eacad83623c610ffebe7223ed304810d3733757403714c44e121281", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mannau/actions/runs/25982384609" }, { "r": "4.6.0", "os": "wasm", "version": "1.3.2", "date": "2026-06-02T17:54:49.000Z", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "f73f448f4001b0ab4208d3dd3273c9b91b6132973c17acc62d2d6c3bdbda6b9a", "status": "success", "buildurl": "https://github.com/r-universe/mannau/actions/runs/25982384609" } ] }