{ "_id": "6a49d44bb48287dcb3fdaedf", "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": "2026-06-16 11:36:49 UTC", "User": "root" }, "_user": "mannau", "_type": "src", "_file": "boilerpipeR_1.3.2.tar.gz", "_fileid": "https://r2.ropensci.org/74b2a11a86965ecce7bd2f3a817aa18c3044d7e7c58291c24006a288a0e3f135", "_filesize": 1675092, "_sha256": "74b2a11a86965ecce7bd2f3a817aa18c3044d7e7c58291c24006a288a0e3f135", "_expires": "2026-10-13T03:49:30.000Z", "_created": "2026-06-16T11:36:49.000Z", "_published": "2026-07-05T03:49:31.750Z", "_jobs": [ { "job": 85190451627, "time": 127, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "7665634926" }, { "job": 85190451862, "time": 101, "config": "linux-release-x86_64", "r": "4.6.0", "check": "NOTE", "artifact": "7665624010" }, { "job": 85190451834, "time": 215, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "NOTE", "artifact": "7665651221" }, { "job": 85190451813, "time": 132, "config": "macos-release-arm64", "r": "4.6.0", "check": "NOTE", "artifact": "7665625535" }, { "job": 85190451506, "time": 176, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7665588568" }, { "job": 85190451570, "time": 109, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7665627977" }, { "job": 85190451753, "time": 68, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "7665612374" }, { "job": 85190451764, "time": 70, "config": "windows-oldrel", "r": "4.5.3", "check": "NOTE", "artifact": "7665614354" }, { "job": 85190451735, "time": 97, "config": "windows-release", "r": "4.6.0", "check": "NOTE", "artifact": "7665623858" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/mannau/actions/runs/27614542391", "_status": "success", "_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 }, "_distro": "noble", "_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", "followers": 37, "description": "CEO and Founder of Quantargo, certified trainer and consultant working on data science projects." }, "_downloads": { "count": 279, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/boilerpipeR" }, "_devurl": "https://github.com/mannau/boilerpiper", "_searchresults": 33, "_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": "21.0.11+10-1~24.04.2", "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": [ "Getting Started", "Implemented Extractors", "Conclusion" ], "created": "2013-12-31 12:37:32", "modified": "2021-05-19 07:49:05", "commits": 4 } ], "_score": 5.539703238947826, "_indexed": true, "_nocasepkg": "boilerpiper", "_universes": [ "mannau" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.3.2", "date": "2026-06-16T11:39:01.000Z", "distro": "noble", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "https://r2.ropensci.org/dcdd1c132a65d7ec2835c282c8e2fef96e9811756812886f1b301398d7c18d9c", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mannau/actions/runs/27614542391" }, { "r": "4.6.0", "os": "linux", "version": "1.3.2", "date": "2026-06-16T11:38:32.000Z", "distro": "noble", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "https://r2.ropensci.org/7bd1326e1cf8e25b9534a08c14024a453ac027c860cbcefd07a44811a108517b", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mannau/actions/runs/27614542391" }, { "r": "4.5.3", "os": "mac", "version": "1.3.2", "date": "2026-06-16T11:39:52.000Z", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "https://r2.ropensci.org/19e8a59518368bbfa512dcabd884a91292fc1228c2e27e6cf1a068dc0939f1bf", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mannau/actions/runs/27614542391" }, { "r": "4.6.0", "os": "mac", "version": "1.3.2", "date": "2026-06-16T11:38:39.000Z", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "https://r2.ropensci.org/4123ffbf163c2e1e68bb5ffb7cb0c86ce25e29c4fd748cab3e74ba857d0b38e1", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mannau/actions/runs/27614542391" }, { "r": "4.6.0", "os": "wasm", "version": "1.3.2", "date": "2026-06-16T11:38:58.000Z", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "https://r2.ropensci.org/5a0d54f854534c5c7b927bad0b955282b8b204e73938b6d3589c59a535a0dff7", "status": "success", "buildurl": "https://github.com/r-universe/mannau/actions/runs/27614542391" }, { "r": "4.7.0", "os": "win", "version": "1.3.2", "date": "2026-06-16T11:37:53.000Z", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "https://r2.ropensci.org/ca95ec1d0a430084a45a75756b41309e8e30dd141285ee821e768e348dc84eb5", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mannau/actions/runs/27614542391" }, { "r": "4.5.3", "os": "win", "version": "1.3.2", "date": "2026-06-16T11:37:58.000Z", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "https://r2.ropensci.org/55cdf9af0a26bb8b86687ba98867e62fc020ec5b78e5eb3a73d8886e94f52713", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mannau/actions/runs/27614542391" }, { "r": "4.6.0", "os": "win", "version": "1.3.2", "date": "2026-06-16T11:38:19.000Z", "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b", "fileid": "https://r2.ropensci.org/3723cffef3b03eae9593ad61789204a618087f52ea2687e7b0e6fd2dcf285922", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mannau/actions/runs/27614542391" } ] }