{"_id":"boilerpipe","_rev":"30622","name":"boilerpipe","description":"A node.js wrapper for Boilerpipe, an excellent Java library for boilerplate removal and fulltext extraction from HTML pages.","dist-tags":{"latest":"0.0.7"},"maintainers":[{"name":"xissy","email":"xissysnd@gmail.com"}],"time":{"modified":"2017-03-28T06:10:01.000Z","created":"2013-06-26T05:39:24.316Z","0.0.7":"2014-02-14T18:17:43.336Z","0.0.4":"2013-07-13T02:43:59.733Z","0.0.3":"2013-07-13T02:42:15.714Z","0.0.2":"2013-06-27T20:53:32.002Z","0.0.1":"2013-06-26T05:39:24.316Z"},"users":{"joliva":true,"gilangh":true,"lorenzo.disidoro":true,"8legged":true,"garon":true},"author":{"name":"Taeho Kim","email":"xissysnd@gmail.com"},"repository":{"type":"git","url":"https://github.com/xissy/node-boilerpipe.git"},"versions":{"0.0.7":{"name":"boilerpipe","version":"0.0.7","author":{"name":"Taeho Kim","email":"xissysnd@gmail.com"},"main":"lib/index.js","dependencies":{"async":">= 0.2.9","java":">= 0.2.3"},"description":"A node.js wrapper for Boilerpipe, an excellent Java library for boilerplate removal and fulltext extraction from HTML pages.","repository":{"type":"git","url":"https://github.com/xissy/node-boilerpipe.git"},"bugs":{"url":"https://github.com/xissy/node-boilerpipe/issues"},"devDependencies":{"coffee-script":">= 1.6.3","should":">= 1.0.0","mocha":">= 1.3.0"},"directories":{"test":"test"},"files":["lib","jar"],"scripts":{"build":"coffee -co lib/ src/","prepublish":"coffee -co lib/ src/","postpublish":"rm -rf lib","test":"mocha --compilers coffee:coffee-script --globals lw --recursive ./test -t 10000"},"_id":"boilerpipe@0.0.7","dist":{"shasum":"019cad6198609182d690a0cb0593a49fda0f91db","size":1453441,"noattachment":false,"tarball":"https://registry.npm.taobao.org/boilerpipe/download/boilerpipe-0.0.7.tgz"},"_from":".","_npmVersion":"1.3.11","_npmUser":{"name":"xissy","email":"xissysnd@gmail.com"},"maintainers":[{"name":"xissy","email":"xissysnd@gmail.com"}],"publish_time":1392401863336,"_cnpm_publish_time":1392401863336,"_hasShrinkwrap":false},"0.0.4":{"name":"boilerpipe","version":"0.0.4","author":{"name":"Taeho Kim","email":"xissysnd@gmail.com"},"main":"./index","dependencies":{"coffee-script":">= 1.6.3","async":">= 0.2.9","java":">= 0.2.3"},"readmeFilename":"README.md","description":"A node.js wrapper for Boilerpipe, an excellent Java library for boilerplate removal and fulltext extraction from HTML pages.","repository":{"type":"git","url":"https://github.com/xissy/node-boilerpipe.git"},"bugs":{"url":"https://github.com/xissy/node-boilerpipe/issues"},"devDependencies":{"should":">= 1.0.0","mocha":">= 1.3.0"},"directories":{"test":"test"},"scripts":{"test":"mocha --compilers coffee:coffee-script --globals lw --recursive ./test -t 10000"},"_id":"boilerpipe@0.0.4","dist":{"shasum":"e64e5ee2e3ad2f9ee580cbe53234ab19bd3ab493","size":1485886,"noattachment":false,"tarball":"https://registry.npm.taobao.org/boilerpipe/download/boilerpipe-0.0.4.tgz"},"_from":".","_npmVersion":"1.2.17","_npmUser":{"name":"xissy","email":"xissysnd@gmail.com"},"maintainers":[{"name":"xissy","email":"xissysnd@gmail.com"}],"publish_time":1373683439733,"_cnpm_publish_time":1373683439733,"_hasShrinkwrap":false},"0.0.3":{"name":"boilerpipe","version":"0.0.3","author":{"name":"Taeho Kim","email":"xissysnd@gmail.com"},"main":"./index","dependencies":{"coffee-script":">= 1.6.3","async":">= 0.2.9","java":">= 0.2.3"},"readmeFilename":"README.md","description":"A node.js wrapper for Boilerpipe, an excellent Java library for boilerplate removal and fulltext extraction from HTML pages.","repository":{"type":"git","url":"https://github.com/xissy/node-boilerpipe.git"},"bugs":{"url":"https://github.com/xissy/node-boilerpipe/issues"},"devDependencies":{"should":">= 1.0.0","mocha":">= 1.3.0"},"directories":{"test":"test"},"scripts":{"test":"mocha --compilers coffee:coffee-script --globals lw --recursive ./test -t 10000"},"_id":"boilerpipe@0.0.3","dist":{"shasum":"e577fa1e3e1ac48f5e69cbef491fab3f16949c0d","size":1485889,"noattachment":false,"tarball":"https://registry.npm.taobao.org/boilerpipe/download/boilerpipe-0.0.3.tgz"},"_from":".","_npmVersion":"1.2.17","_npmUser":{"name":"xissy","email":"xissysnd@gmail.com"},"maintainers":[{"name":"xissy","email":"xissysnd@gmail.com"}],"publish_time":1373683335714,"_cnpm_publish_time":1373683335714,"_hasShrinkwrap":false},"0.0.2":{"name":"boilerpipe","version":"0.0.2","author":{"name":"Taeho Kim","email":"xissysnd@gmail.com"},"main":"lib/index","dependencies":{"coffee-script":">= 1.6.3","async":">= 0.2.9","java":">= 0.2.3"},"readmeFilename":"README.md","description":"A node.js wrapper for Boilerpipe, an excellent Java library for boilerplate removal and fulltext extraction from HTML pages.","repository":{"type":"git","url":"https://github.com/xissy/node-boilerpipe.git"},"bugs":{"url":"http://github.com/xissy/node-boilerpipe/issues"},"devDependencies":{"should":">= 1.0.0","mocha":">= 1.3.0"},"directories":{"test":"test"},"scripts":{"test":"mocha --compilers coffee:coffee-script --globals lw --recursive ./test -t 10000"},"_id":"boilerpipe@0.0.2","dist":{"shasum":"8084bb55962802919743894c72616510404c1ede","size":1485816,"noattachment":false,"tarball":"https://registry.npm.taobao.org/boilerpipe/download/boilerpipe-0.0.2.tgz"},"_from":".","_npmVersion":"1.2.17","_npmUser":{"name":"xissy","email":"xissysnd@gmail.com"},"maintainers":[{"name":"xissy","email":"xissysnd@gmail.com"}],"publish_time":1372366412002,"_cnpm_publish_time":1372366412002,"_hasShrinkwrap":false},"0.0.1":{"name":"boilerpipe","version":"0.0.1","author":{"name":"Taeho Kim","email":"xissysnd@gmail.com"},"main":"lib/index","dependencies":{"coffee-script":">= 1.6.3","async":">= 0.2.9","java":">= 0.2.3"},"readmeFilename":"README.md","description":"A node.js wrapper for Boilerpipe, an excellent Java library for boilerplate removal and fulltext extraction from HTML pages.","repository":{"type":"git","url":"https://github.com/xissy/node-boilerpipe.git"},"bugs":{"url":"http://github.com/xissy/node-boilerpipe/issues"},"devDependencies":{"should":">= 1.0.0","mocha":">= 1.3.0"},"directories":{"test":"test"},"scripts":{"test":"mocha --compilers coffee:coffee-script --globals lw --recursive ./test -t 10000"},"_id":"boilerpipe@0.0.1","dist":{"shasum":"528b534da9dfe3ef4d95c3c4727c364c442b26bc","size":1485769,"noattachment":false,"tarball":"https://registry.npm.taobao.org/boilerpipe/download/boilerpipe-0.0.1.tgz"},"_from":".","_npmVersion":"1.2.17","_npmUser":{"name":"xissy","email":"xissysnd@gmail.com"},"maintainers":[{"name":"xissy","email":"xissysnd@gmail.com"}],"publish_time":1372225164316,"_cnpm_publish_time":1372225164316,"_hasShrinkwrap":false}},"readme":"# node-boilerpipe\n\nA node.js wrapper for [Boilerpipe](https://code.google.com/p/boilerpipe/), an excellent Java library for boilerplate removal and fulltext extraction from HTML pages.\n\n\n## Installation\n\nnode-boilerpipe depends on [Boilerpipe](https://code.google.com/p/boilerpipe/) v1.2.0 or higher.\n\nWARNING: Don't forget to set JAVA variable referred to [node-java](https://github.com/nearinfinity/node-java).\n\nVia [npm](https://npmjs.org):\n\n $ npm install boilerpipe\n \n\n## Usage\n\n### Load in the module\n```javascript\n var Boilerpipe = require('boilerpipe');\n```\n\n### Create a new instance\nThe constructor takes a `extractor`, being one of the available boilerpipe extractor types:\n\n * DefaultExtractor\n * ArticleExtractor\n * ArticleSentencesExtractor\n * KeepEverythingExtractor\n * KeepEverythingWithMinKWordsExtractor\n * LargestContentExtractor\n * NumWordsRulesExtractor\n * CanolaExtractor\n\nIf no extractor is passed the `DefaultExtractor` will be used by default. Additional keyword arguments are either `html` for HTML text or `url`.\n```javascript\n var boilerpipe = new Boilerpipe();\n\n var boilerpipe = new Boilerpipe({\n extractor: Boilerpipe.Extractor.Canola\n });\n\n var boilerpipe = new Boilerpipe({\n extractor: Boilerpipe.Extractor.Article,\n url: 'http://...'\n });\n\n var boilerpipe = new Boilerpipe({\n extractor: Boilerpipe.Extractor.ArticleSentences,\n html: '...'\n }, function(err) {\n ...\n });\n```\n\n### Set URL or HTML\nIf you set both URL and HTML then only URL will work for you. HTML will be ignored at this case.\n```javascript\n boilerpipe.setUrl('http://...');\n\n boilerpipe.setHtml('...');\n```\n\n### Get text, html and images\n```javascript\n boilerpipe.getText(function(err, text) {\n ...\n });\n\n boilerpipe.getHtml(function(err, html) {\n ...\n });\n\n boilerpipe.getImages(function(err, images) {\n ...\n });\n```\n\n## License\n\nReleased under the MIT License\n\nCopyright (c) 2013 Taeho Kim \n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in\nall copies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.\n\n\n[![Bitdeli Badge](https://d2weczhvl823v0.cloudfront.net/xissy/node-boilerpipe/trend.png)](https://bitdeli.com/free \"Bitdeli Badge\")\n\n","_attachments":{},"bugs":{"url":"https://github.com/xissy/node-boilerpipe/issues"}}