{
  "_id": "6acf4b6cd9de2f3f33fca672",
  "Package": "boilerpipeR",
  "Version": "1.3.2",
  "Date": "2021-05-19",
  "Title": "Interface to the Boilerpipe Java Library",
  "Author": "See AUTHORS file.",
  "Maintainer": "Mario Annau <mario.annau@gmail.com>",
  "Description": "Generic Extraction of main text content from HTML files;\nremoval of ads, sidebars and headers using the boilerpipe\n<https://github.com/kohlschutter/boilerpipe> 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": "2026-10-14 08:29:26 UTC",
    "User": "root"
  },
  "_user": "mannau",
  "_type": "src",
  "_file": "boilerpipeR_1.3.2.tar.gz",
  "_fileid": "https://r2.ropensci.org/c851ee991e8e7e86cf10e035c3482f5e99a285ecee2a181c96772061be56ec8c",
  "_filesize": 1675096,
  "_sha256": "c851ee991e8e7e86cf10e035c3482f5e99a285ecee2a181c96772061be56ec8c",
  "_expires": "2027-01-22T09:29:14.000Z",
  "_created": "2026-10-14T08:29:26.000Z",
  "_published": "2026-10-14T09:29:16.614Z",
  "_buildurl": "https://github.com/r-universe/mannau/actions/runs/38535141977",
  "_status": "success",
  "_host": "GitHub-Actions",
  "_jobs": [
    {
      "job": 115757296512,
      "time": 101,
      "config": "linux-devel-x86_64",
      "r": "4.7.0",
      "check": "NOTE",
      "artifact": "11879408548"
    },
    {
      "job": 115757296720,
      "time": 133,
      "config": "linux-release-x86_64",
      "r": "4.6.1",
      "check": "NOTE",
      "artifact": "11879863964"
    },
    {
      "job": 115757296367,
      "time": 197,
      "config": "macos-oldrel-arm64",
      "r": "4.5.3",
      "check": "NOTE",
      "artifact": "11882099717"
    },
    {
      "job": 115757296408,
      "time": 155,
      "config": "macos-release-arm64",
      "r": "4.6.1",
      "check": "NOTE",
      "artifact": "11882443998"
    },
    {
      "job": 115756232871,
      "time": 162,
      "config": "source",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11879103551"
    },
    {
      "job": 115757296546,
      "time": 98,
      "config": "wasm-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "11880063206"
    },
    {
      "job": 115757296485,
      "time": 70,
      "config": "windows-devel-x86_64",
      "r": "4.7.0",
      "check": "NOTE",
      "artifact": "11879173684"
    },
    {
      "job": 115757296678,
      "time": 66,
      "config": "windows-oldrel-x86_64",
      "r": "4.5.3",
      "check": "NOTE",
      "artifact": "11880270897"
    },
    {
      "job": 115757296741,
      "time": 83,
      "config": "windows-release-x86_64",
      "r": "4.6.1",
      "check": "NOTE",
      "artifact": "11879283776"
    }
  ],
  "_upstream": "https://github.com/mannau/boilerpiper",
  "_commit": {
    "id": "5cbc092cac7717a776bef1b54d3021959c4bcc7b",
    "author": "mannau <mario.annau@quantargo.com>",
    "committer": "mannau <mario.annau@quantargo.com>",
    "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": "resolute",
  "_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": 38,
    "description": "CEO and Founder of Quantargo, certified trainer and consultant working on data science projects."
  },
  "_downloads": {
    "count": 386,
    "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/boilerpipeR"
  },
  "_devurl": "https://github.com/mannau/boilerpiper",
  "_searchresults": 32,
  "_topics": [
    "openjdk"
  ],
  "_rbuild": "4.6.1",
  "_assets": [
    "extra/boilerpipeR.html",
    "extra/citation.cff",
    "extra/citation.html",
    "extra/citation.json",
    "extra/citation.txt",
    "extra/contents.json",
    "extra/manual.pdf",
    "extra/NEWS.html",
    "extra/NEWS.txt",
    "extra/readme.html",
    "extra/readme.md"
  ],
  "_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 <https://quantivity.wordpress.com>). 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 <https://quantivity.wordpress.com>). 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-25-jre-headless",
      "headers": "openjdk-25-jre-headless",
      "source": "openjdk",
      "version": "25.0.4.1+1-1~26.04.4",
      "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": 5.5263392773898445,
  "_indexed": true,
  "_nocasepkg": "boilerpiper",
  "_universes": [
    "mannau"
  ],
  "_binaries": [
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "1.3.2",
      "date": "2026-10-14T08:31:13.000Z",
      "distro": "resolute",
      "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b",
      "fileid": "https://r2.ropensci.org/5d4cc572be1aa3fff0091208f5ff3f1db3131f7c7cfdf18d6f66c0b2576d529b",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/mannau/actions/runs/38535141977"
    },
    {
      "r": "4.6.1",
      "os": "linux",
      "version": "1.3.2",
      "date": "2026-10-14T08:31:46.000Z",
      "distro": "resolute",
      "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b",
      "fileid": "https://r2.ropensci.org/e70f9eaf7abb4dccc712d25a0161222b94d2ad69cf1da59582daf918b1369d6f",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/mannau/actions/runs/38535141977"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "1.3.2",
      "date": "2026-10-14T09:26:29.000Z",
      "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b",
      "fileid": "https://r2.ropensci.org/3b613b605ee55adfdc03bc05f3edab2abc6a4336eef4ade1a8c1ac3f6cd895fc",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/mannau/actions/runs/38535141977"
    },
    {
      "r": "4.6.1",
      "os": "mac",
      "version": "1.3.2",
      "date": "2026-10-14T09:28:06.000Z",
      "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b",
      "fileid": "https://r2.ropensci.org/88ec67cdf26499b4dc254a16ac2c5e7930b616e224c3f2d9163c58863b3fbd19",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/mannau/actions/runs/38535141977"
    },
    {
      "r": "4.6.0",
      "os": "wasm",
      "version": "1.3.2",
      "date": "2026-10-14T08:31:24.000Z",
      "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b",
      "fileid": "https://r2.ropensci.org/225de8840ac10de73d13c9231df704f13aa5c42dafc5da3a62a638e640fb7608",
      "status": "success",
      "buildurl": "https://github.com/r-universe/mannau/actions/runs/38535141977"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "1.3.2",
      "date": "2026-10-14T08:30:35.000Z",
      "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b",
      "fileid": "https://r2.ropensci.org/a949adf699323f986d8d7d2067b8d71959b772f01b2877411213020b28a254e3",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/mannau/actions/runs/38535141977"
    },
    {
      "r": "4.5.3",
      "os": "win",
      "version": "1.3.2",
      "date": "2026-10-14T08:30:33.000Z",
      "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b",
      "fileid": "https://r2.ropensci.org/f8abed5da0f8286ae74306db24871f1b8173f60463c02aadeb5b7d45b8248786",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/mannau/actions/runs/38535141977"
    },
    {
      "r": "4.6.1",
      "os": "win",
      "version": "1.3.2",
      "date": "2026-10-14T08:30:48.000Z",
      "commit": "5cbc092cac7717a776bef1b54d3021959c4bcc7b",
      "fileid": "https://r2.ropensci.org/845a9fa09606190820fea35c67feb41ca3fe219b05528ac3dba59fbd60972d5a",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/mannau/actions/runs/38535141977"
    }
  ]
}