{ "_id": "6a2e6b913efcd9bda43121a3", "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", "NeedsCompilation": "no", "Packaged": { "Date": "2026-06-14 08:49:06 UTC", "User": "root" }, "Repository": "https://cran.r-universe.dev", "Date/Publication": "2021-05-19 08:20:02 UTC", "RemoteUrl": "https://github.com/cran/boilerpipeR", "RemoteRef": "HEAD", "RemoteSha": "263b4b304db1a4169655e696e58ec329d8fb9f95", "MD5sum": "817f8e30adcb0f63d1a19670432cffec", "_user": "cran", "_type": "src", "_file": "boilerpipeR_1.3.2.tar.gz", "_fileid": "bff9f68b1a8906838947a5076f9bc443cd893da1668ff5135d2108e7ef19f1d0", "_filesize": 1673106, "_sha256": "bff9f68b1a8906838947a5076f9bc443cd893da1668ff5135d2108e7ef19f1d0", "_created": "2026-06-14T08:49:06.000Z", "_published": "2026-06-14T08:51:29.320Z", "_distro": "noble", "_jobs": [ { "job": 81263780236, "time": 107, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "7619337488" }, { "job": 81263780260, "time": 110, "config": "linux-release-x86_64", "r": "4.6.0", "check": "NOTE", "artifact": "7619338055" }, { "job": 81263633251, "time": 140, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7619322424" }, { "job": 81263780221, "time": 103, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7619336733" } ], "_buildurl": "https://github.com/r-universe/cran/actions/runs/27493661382", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/cran/boilerpipeR", "_commit": { "id": "263b4b304db1a4169655e696e58ec329d8fb9f95", "author": "Mario Annau ", "committer": "cran-robot ", "message": "version 1.3.2\n", "time": 1621412402 }, "_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": "cran", "_selfowned": false, "_usedby": 0, "_updates": [], "_tags": [], "_stars": 0, "_contributors": [ { "user": "mannau", "count": 6, "uuid": 1262952 } ], "_userbio": { "uuid": 6899542, "type": "organization", "name": "cran", "followers": 606, "description": "Unofficial read-only mirror of all CRAN R packages" }, "_downloads": { "count": 258, "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", "manual.pdf" ], "_homeurl": "https://github.com/mannau/boilerpiper", "_realowner": "mannau", "_cranurl": false, "_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" ] } ], "_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": "2012-12-13", "modified": "2021-05-19 08:20:02", "commits": 2 } ], "_score": 2.5185139398778875, "_indexed": false, "_nocasepkg": "boilerpiper", "_universes": [ "cran" ], "_indexurl": "https://mannau.r-universe.dev/boilerpipeR", "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.3.2", "date": "2026-06-14T08:50:54.000Z", "distro": "noble", "commit": "263b4b304db1a4169655e696e58ec329d8fb9f95", "fileid": "f35e5bec13e349e6d336b47992524e0c3e4e4200b7e865461d521182a632c6a8", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cran/actions/runs/27493661382" }, { "r": "4.6.0", "os": "linux", "version": "1.3.2", "date": "2026-06-14T08:50:57.000Z", "distro": "noble", "commit": "263b4b304db1a4169655e696e58ec329d8fb9f95", "fileid": "fdc410eda03dec82686be1ff3af1d4487165759b023e9e5ae2cae090bcab5bd3", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cran/actions/runs/27493661382" }, { "r": "4.6.0", "os": "wasm", "version": "1.3.2", "date": "2026-06-14T08:51:04.000Z", "commit": "263b4b304db1a4169655e696e58ec329d8fb9f95", "fileid": "14f3f91bea7f14051ce50b0b69954f63c1bae3bc8d778e38a7798d0b7da63063", "status": "success", "buildurl": "https://github.com/r-universe/cran/actions/runs/27493661382" } ] }