{"id":4876,"date":"2020-01-01T00:00:00","date_gmt":"2019-12-31T15:00:00","guid":{"rendered":"https:\/\/majisemi.com\/topics\/uncategorized\/4876\/"},"modified":"2020-01-01T00:00:00","modified_gmt":"2019-12-31T15:00:00","slug":"%e3%80%90oss%e6%83%85%e5%a0%b1%e3%82%a2%e3%83%bc%e3%82%ab%e3%82%a4%e3%83%96%e3%80%91apache-nutch","status":"publish","type":"post","link":"https:\/\/majisemi.com\/topics\/oss\/4876\/","title":{"rendered":"\u3010OSS\u60c5\u5831\u30a2\u30fc\u30ab\u30a4\u30d6\u3011Apache Nutch"},"content":{"rendered":"<p><small><span style=\"border-bottom: solid 5px red;\">\u203b\u5f53\u8a18\u4e8b\u306b\u8a18\u8f09\u3055\u308c\u3066\u3044\u308b\u60c5\u5831\u306f\u3001\u53e4\u304f\u306a\u3063\u3066\u3044\u308b\u5834\u5408\u304c\u3042\u308a\u307e\u3059\u3002\u30aa\u30d5\u30a3\u30b7\u30e3\u30eb\u30b5\u30a4\u30c8\u3067\u6700\u65b0\u60c5\u5831\u3092\u3054\u78ba\u8a8d\u304f\u3060\u3055\u3044\u3002<\/span><\/small><\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_82_2 counter-hierarchy ez-toc-counter ez-toc-light-blue ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">\u30b3\u30f3\u30c6\u30f3\u30c4<\/p>\n<span class=\"ez-toc-title-toggle\"><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-1'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/majisemi.com\/topics\/oss\/4876\/#%E3%80%8CApache_Nutch%E3%80%8D%E3%81%A8%E3%81%AF\" >\u300cApache Nutch\u300d\u3068\u306f<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/majisemi.com\/topics\/oss\/4876\/#%E5%9F%BA%E6%9C%AC%E6%83%85%E5%A0%B1_%E6%A6%82%E8%A6%81_Apache_Nutch%E3%82%A2%E3%83%91%E3%83%83%E3%83%81%E3%83%8A%E3%83%83%E3%83%81%E3%81%A8%E3%81%AF%E3%80%81%E3%82%AA%E3%83%BC%E3%83%97%E3%83%B3%E3%82%BD%E3%83%BC%E3%82%B9%E3%81%AEWeb%E3%82%AF%E3%83%AD%E3%83%BC%E3%83%A9%E3%83%95%E3%83%AC%E3%83%BC%E3%83%A0%E3%83%AF%E3%83%BC%E3%82%AF%E3%81%A7%E3%81%99%E3%80%82Apache_Hadoop%E3%81%AB%E3%82%88%E3%82%8B%E6%8B%A1%E5%BC%B5%E6%80%A7%E3%81%8C%E7%89%B9%E5%BE%B4%E3%81%A7%E3%81%99%E3%80%82_%E5%9F%BA%E6%9C%AC%E8%AA%AC%E6%98%8E\" >\u57fa\u672c\u60c5\u5831\n\u6982\u8981\nApache Nutch(\u30a2\u30d1\u30c3\u30c1\u30ca\u30c3\u30c1)\u3068\u306f\u3001\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u306eWeb\u30af\u30ed\u30fc\u30e9\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3059\u3002Apache Hadoop\u306b\u3088\u308b\u62e1\u5f35\u6027\u304c\u7279\u5fb4\u3067\u3059\u3002\n\u57fa\u672c\u8aac\u660e<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/majisemi.com\/topics\/oss\/4876\/#%E4%B8%BB%E3%81%AA%E7%89%B9%E5%BE%B4_%E3%82%B9%E3%83%88%E3%83%AC%E3%83%BC%E3%82%B8\" >\u4e3b\u306a\u7279\u5fb4\n\u30b9\u30c8\u30ec\u30fc\u30b8<\/a><\/li><\/ul><\/li><\/ul><\/li><\/ul><\/nav><\/div>\n<h1 class=\"h1Custom\"><span class=\"ez-toc-section\" id=\"%E3%80%8CApache_Nutch%E3%80%8D%E3%81%A8%E3%81%AF\"><\/span>\u300cApache Nutch\u300d\u3068\u306f<span class=\"ez-toc-section-end\"><\/span><\/h1>\n<div class=\"main-c\">\n<h3 class=\"h2smalltitle\">\u57fa\u672c\u60c5\u5831<\/h2>\n<h3 class=\"h2smalltitle\">\u6982\u8981<\/h2>\n<p><strong>Apache Nutch<\/strong>(\u30a2\u30d1\u30c3\u30c1\u30ca\u30c3\u30c1)\u3068\u306f\u3001\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u306eWeb\u30af\u30ed\u30fc\u30e9\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3059\u3002Apache Hadoop\u306b\u3088\u308b\u62e1\u5f35\u6027\u304c\u7279\u5fb4\u3067\u3059\u3002<\/p>\n<h4 class=\"subtitle-h4\">\u57fa\u672c\u8aac\u660e<\/h3>\n<p>Apache Nutch\u306f\u3001\u6307\u5b9a\u3055\u308c\u305fWeb\u30ea\u30f3\u30af\u3092\u305f\u3069\u308a\u306a\u304c\u3089\u3001\u30da\u30fc\u30b8\u53ce\u96c6\/\u30b9\u30b3\u30a2\u30ea\u30f3\u30b0\u3092\u884c\u3044\u3001\u5168\u6587\u691c\u7d22(Lucene)\u7528\u306e\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u3092\u751f\u6210\u3057\u307e\u3059\u3002<\/p>\n<p>Apache Nutch\u306f\u3001Java\u88fd\u306eWeb\u30af\u30ed\u30fc\u30e9\u3067\u3001\u5168\u6587\u691c\u7d22\u30a8\u30f3\u30b8\u30f3\u300c<a href=\"http:\/\/www.ossnews.jp\/oss_info\/Apache_Lucene\" target=\"jumpsite\" rel=\"nofollow noopener\">Apache Lucene<\/a>\u300d\u306e\u30b5\u30d6\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u3068\u3057\u3066\u958b\u767a\u3055\u308c\u307e\u3057\u305f\u3002\u5168\u6587\u691c\u7d22\u30a8\u30f3\u30b8\u30f3\u300c<a href=\"http:\/\/www.ossnews.jp\/oss_info\/Apache_Solr\" target=\"jumpsite\" rel=\"nofollow noopener\">Apache Solr<\/a>\u300d\u3001\u5206\u6563\u51e6\u7406\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u300c<a href=\"http:\/\/www.ossnews.jp\/oss_info\/Apache_Hadoop\" target=\"jumpsite\" rel=\"nofollow noopener\">Apache Hadoop<\/a>\u300d\u3001\u30b3\u30f3\u30c6\u30f3\u30c4\u691c\u51fa\/\u5206\u6790\u300cApache Tika\u300d\u3001\u30a4\u30f3\u30e1\u30e2\u30ea\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\u300cApache Gora\u300d\u306a\u3069\u306eApache\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u3067\u69cb\u7bc9\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n<p>\u5927\u898f\u6a21Web\u691c\u7d22\u5411\u3051\u306b\u62e1\u5f35\u6027\u3092\u6301\u305f\u305b\u305f\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3059\u3002\u30d1\u30fc\u30b5\u6a5f\u80fd(Web\u30da\u30fc\u30b8\/PDF\u30d5\u30a1\u30a4\u30eb\/\u305d\u306e\u4ed6\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8)\u3001\u30af\u30ed\u30fc\u30e9\u6a5f\u80fd\u3001\u30ea\u30f3\u30af\u30b0\u30e9\u30d5\/\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u6a5f\u80fd\u306a\u3069\u3092\u642d\u8f09\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n<h4 class=\"subtitle-h4\">\u7d4c\u7def<\/h3>\n<p>2010\u5e744\u6708\u3001Apache\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u8ca1\u56e3\u306e\u30c8\u30c3\u30d7\u30ec\u30d9\u30eb\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306b\u6307\u5b9a\u3055\u308c\u307e\u3057\u305f\u3002<\/p>\n<h4 class=\"subtitle-h4\">2\u7cfb\u7d71<\/h3>\n<p>\u300cNutch 1.x\u300d\u7cfb\u306f\u3001\u6210\u719f\u3057\u88fd\u54c1\u5316\u6e96\u5099\u306e\u6574\u3063\u305f\u30af\u30ed\u30fc\u30e9\u3067\u3059\u3002<\/p>\n<p>\u300cNutch 2.x\u300d\u7cfb\u306f\u3001\u300cApache Gora\u300d\u3092\u7528\u3044\u308b\u3053\u3068\u3067\u30b9\u30c8\u30ec\u30fc\u30b8\u304c\u62bd\u8c61\u5316\u3055\u308c\u3001\u6c38\u7d9a\u7684\u30de\u30c3\u30d4\u30f3\u30b0\u3067\u30aa\u30d6\u30b8\u30a7\u30af\u30c8\u51e6\u7406\u3067\u304d\u307e\u3059\u3002<\/p>\n<h3 class=\"h2smalltitle\"><span class=\"ez-toc-section\" id=\"%E4%B8%BB%E3%81%AA%E7%89%B9%E5%BE%B4_%E3%82%B9%E3%83%88%E3%83%AC%E3%83%BC%E3%82%B8\"><\/span>\u4e3b\u306a\u7279\u5fb4<\/h2>\n<h4 class=\"subtitle-h4\">\u30b9\u30c8\u30ec\u30fc\u30b8<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u5927\u898f\u6a21\u30b9\u30c8\u30ec\u30fc\u30b8\u30d7\u30e9\u30c3\u30c8\u30d5\u30a9\u30fc\u30e0(Apache Accumulo\/Apache Avro\/Apache Cassandra\/Apache HBase\/Apache HDFS)\u3084\u3001SQL\u30d9\u30fc\u30b9\u30b9\u30c8\u30ec\u30fc\u30b8\u30b7\u30b9\u30c6\u30e0\u306b\u5bfe\u3057\u3066\u3001\u30b9\u30c8\u30ec\u30fc\u30b8\u306e\u62bd\u8c61\u30ec\u30a4\u30e4\u3068\u3057\u3066\u8ffd\u52a0\u3067\u304d\u307e\u3059\u3002<\/p>\n<p>Gora\u306b\u3088\u308b\u30a4\u30f3\u30e1\u30e2\u30ea\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\u3092\u7528\u3044\u3066\u3001NoSQL\/SQL\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u3092\u62bd\u8c61\u5316\u3057\u3066\u5229\u7528\u3067\u304d\u307e\u3059\u3002<\/p>\n<h4 class=\"subtitle-h4\">\u30a4\u30f3\u30c7\u30c3\u30af\u30b9<\/h3>\n<p>Nutch\u306e\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u306f\u3001Lucene\u306e\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u3067\u3042\u308b\u305f\u3081\u3001Lucene\u7528\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u7ba1\u7406GUI\u30c4\u30fc\u30eb\u3092\u4f7f\u7528\u3057\u3066\u5185\u5bb9\u3092\u78ba\u8a8d\u3067\u304d\u307e\u3059\u3002<\/p>\n<h4 class=\"subtitle-h4\">\u30d7\u30e9\u30b0\u30a4\u30f3\u6a5f\u80fd<\/h3>\n<p>\u30d7\u30e9\u30b0\u30a4\u30f3\u3067\u3055\u307e\u3056\u307e\u306a\u6a5f\u80fd\u8ffd\u52a0\u3092\u884c\u3048\u307e\u3059\u3002<\/p>\n<p>\u30d1\u30fc\u30b9\/\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\/\u8a55\u4fa1\u30d5\u30a3\u30eb\u30bf\u306a\u3069\u306e\u62e1\u5f35\u30a4\u30f3\u30bf\u30fc\u30d5\u30a7\u30fc\u30b9\u3092\u63d0\u4f9b\u3057\u3066\u3044\u307e\u3059\u3002\u30d1\u30fc\u30b9\u30ab\u30b9\u30bf\u30e0\u5b9f\u88c5\/\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u6a5f\u80fd\u306a\u3069\u3092\u8ffd\u52a0\u3067\u304d\u307e\u3059\u3002<\/p>\n<p>Web\u30da\u30fc\u30b8\u306e\u8a00\u8a9e\u5224\u5b9a\u3092\u884c\u3044\u3001\u691c\u7d22\u30ad\u30fc\u3068\u3057\u3066\u8a00\u8a9e\u3092\u6307\u5b9a\u3067\u304d\u308b\u3088\u3046\u306b\u3059\u308b\u3053\u3068\u3082\u53ef\u80fd\u3067\u3059\u3002<\/p>\n<h4 class=\"subtitle-h4\">\u8ca0\u8377\u5206\u6563<\/h3>\n<p>Nutch\u306f\u5206\u6563\u7ba1\u7406\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u300cApache Hadoop\u300d\u3092\u63a1\u7528\u3057\u3066\u307e\u3059\u3002Google\u304c\u63d0\u5531\u3057\u305f\u5206\u6563\u51e6\u7406\u30b7\u30b9\u30c6\u30e0\u300cMapReduce\u300d\u304c\u5143\u306b\u306a\u3063\u3066\u3044\u307e\u3059\u3002<\/p>\n<p>Hadoop\u30af\u30e9\u30b9\u30bf\u3092\u69cb\u6210\u3059\u308b\u3053\u3068\u306b\u3088\u308a\u3001\u60c5\u5831\u91cf\u304c\u5897\u3048\u3066\u3082\u5206\u6563\u5bfe\u5fdc\u3057\u3001\u5927\u898f\u6a21\u306a\u30af\u30ed\u30fc\u30eb\u30c7\u30fc\u30bf\u3092\u8907\u6570\u30b5\u30fc\u30d0\u4e0a\u306b\u5206\u6563\u4fdd\u6301\u3067\u304d\u307e\u3059\u3002<\/p>\n<p>\u5c0f\u898f\u6a21\u30af\u30ed\u30fc\u30e9\u304b\u3089\u5927\u898f\u6a21Web\u30af\u30ed\u30fc\u30e9\u307e\u3067\u3001\u3055\u307e\u3056\u307e\u306a\u30e6\u30fc\u30b9\u30b1\u30fc\u30b9\u3092\u30ab\u30d0\u30fc\u3067\u304d\u307e\u3059\u3002<\/p>\n<h4 class=\"subtitle-h4\">URL\u30d5\u30a3\u30eb\u30bf\u6a5f\u80fd<\/h3>\n<p>URL\u30d5\u30a3\u30eb\u30bf\u8a2d\u5b9a\u3092\u884c\u3046\u3053\u3068\u3067\u300c\u4efb\u610f\u306e\u30b5\u30a4\u30c8\u306e\u65b0\u7740\u60c5\u5831\u306e\u307f\u30af\u30ed\u30fc\u30eb\u3059\u308b\u300d\u3088\u3046\u306a\u3053\u3068\u3092\u884c\u3048\u307e\u3059\u3002<\/p>\n<h3 class=\"h2smalltitle\">\u540c\u69d8\u88fd\u54c1<\/h2>\n<p>\u540c\u69d8\u306a\u6a5f\u80fd\u3092\u63d0\u4f9b\u3059\u308b\u88fd\u54c1\u3068\u3057\u3066\u3001\u6b21\u306e\u3088\u3046\u306a\u3082\u306e\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n<p>\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u88fd\u54c1\uff1a\u300c<a href=\"http:\/\/www.ossnews.jp\/oss_info\/Apache_ManifoldCF\" target=\"jumpsite\" rel=\"nofollow noopener\">Apache ManifoldCF<\/a>\u300d\u300cHeritrix\u300d\u300cS2Robot\u300d\u306a\u3069\u3002<\/p>\n<h3 class=\"h2smalltitle\">\u30e9\u30a4\u30bb\u30f3\u30b9\u60c5\u5831<\/h2>\n<p>Apache Nutch\u306e\u30e9\u30a4\u30bb\u30f3\u30b9\u306f\u300cApache License 2.0\u300d\u3067\u3059\u3002\u3053\u306e\u30e9\u30a4\u30bb\u30f3\u30b9\u306b\u5f93\u3046\u3053\u3068\u3092\u6761\u4ef6\u3068\u3057\u3066\u3001\u30bd\u30fc\u30b9\u30b3\u30fc\u30c9\u306e\u6539\u5909\u3068\u516c\u958b\u304c\u8a31\u53ef\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n<h3 class=\"h2smalltitle\">\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9<\/h2>\n<p><a href=\"http:\/\/nutch.apache.org\/\" target=\"jumpsite\" rel=\"nofollow noopener\">\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u30da\u30fc\u30b8<\/a><\/p>\n<p class=\"text80\">\u203b\u5b9a\u671f\u7684\u306b\u30e1\u30f3\u30c6\u30ca\u30f3\u30b9\u3092\u5b9f\u65bd\u3057\u3066\u304a\u308a\u307e\u3059\u304c\u3001\u4e00\u90e8\u60c5\u5831\u304c\u53e4\u3044\u5834\u5408\u304c\u3054\u3056\u3044\u307e\u3059\u3002\u3054\u4e86\u627f\u304f\u3060\u3055\u3044\u3002<\/p>\n<\/div>\n<p><!-- main-c--><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Apache Nutch(\u30a2\u30d1\u30c3\u30c1\u30ca\u30c3\u30c1)\u3002\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u306eWeb\u30af\u30ed\u30fc\u30e9\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3059\u3002Apache Hadoop\u306b\u3088\u308b\u62e1\u5f35\u6027\u304c\u7279\u5fb4\u3067\u3059\u3002<\/p>\n","protected":false},"author":4,"featured_media":3972,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[243],"tags":[547],"class_list":["post-4876","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-oss","tag-apache-nutch"],"acf":[],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/majisemi.com\/topics\/wp-json\/wp\/v2\/posts\/4876","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/majisemi.com\/topics\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/majisemi.com\/topics\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/majisemi.com\/topics\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/majisemi.com\/topics\/wp-json\/wp\/v2\/comments?post=4876"}],"version-history":[{"count":0,"href":"https:\/\/majisemi.com\/topics\/wp-json\/wp\/v2\/posts\/4876\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/majisemi.com\/topics\/wp-json\/wp\/v2\/media\/3972"}],"wp:attachment":[{"href":"https:\/\/majisemi.com\/topics\/wp-json\/wp\/v2\/media?parent=4876"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/majisemi.com\/topics\/wp-json\/wp\/v2\/categories?post=4876"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/majisemi.com\/topics\/wp-json\/wp\/v2\/tags?post=4876"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}