[{"@context":"http:\/\/schema.org\/","@type":"BlogPosting","@id":"https:\/\/wiki.edu.vn\/all2jp\/wiki47\/archives\/11040#BlogPosting","mainEntityOfPage":"https:\/\/wiki.edu.vn\/all2jp\/wiki47\/archives\/11040","headline":"Apache Nutch-\u30a6\u30a3\u30ad\u30da\u30c7\u30a3\u30a2\u3001\u7121\u6599\u200b\u200b\u767e\u79d1\u4e8b\u5178","name":"Apache Nutch-\u30a6\u30a3\u30ad\u30da\u30c7\u30a3\u30a2\u3001\u7121\u6599\u200b\u200b\u767e\u79d1\u4e8b\u5178","description":"before-content-x4 Apache nutch – \u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u3001\u62e1\u5f35\u53ef\u80fd\u3067\u30b9\u30b1\u30fc\u30e9\u30d6\u30eb\u306a\u30a4\u30f3\u30bf\u30fc\u30cd\u30c3\u30c8\u30ed\u30dc\u30c3\u30c8\uff08Web\u30b5\u30a4\u30c8\u3092\u691c\u7d22\u304a\u3088\u3073\u5206\u6790\u3059\u308b\u305f\u3081\u306e\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30fc\u30d7\u30ed\u30b0\u30e9\u30e0\uff09Apache Foundation\u306e\u30b1\u30a2\u306e\u4e0b\u3067\u958b\u767a\u3055\u308c\u305f [2] \u3002 after-content-x4 Nutch\u30b7\u30b9\u30c6\u30e0\u306e\u7279\u5fb4\uff08Yadav\u3068Goyal\u306b\u3088\u308b [3] \uff09\uff1a \u591a\u6570\u306e\u6a5f\u80fd\u3068\u30b7\u30b9\u30c6\u30e0\u64cd\u4f5c\u3092\u67d4\u8edf\u306b\u69cb\u6210\u3059\u308b\u6a5f\u80fd [4] [5] \u3001 \u30b7\u30b9\u30c6\u30e0\u6a5f\u80fd\u3092\u62e1\u5f35\u3059\u308b\u53ef\u80fd\u6027\uff08\u30d7\u30e9\u30b0\u30b7\u30b9\u30c6\u30e0\u3092\u4f7f\u7528\uff09 [4] [6] \u3001","datePublished":"2022-06-03","dateModified":"2022-06-03","author":{"@type":"Person","@id":"https:\/\/wiki.edu.vn\/all2jp\/wiki47\/archives\/author\/lordneo#Person","name":"lordneo","url":"https:\/\/wiki.edu.vn\/all2jp\/wiki47\/archives\/author\/lordneo","image":{"@type":"ImageObject","@id":"https:\/\/secure.gravatar.com\/avatar\/44a4cee54c4c053e967fe3e7d054edd4?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/44a4cee54c4c053e967fe3e7d054edd4?s=96&d=mm&r=g","height":96,"width":96}},"publisher":{"@type":"Organization","name":"Enzyklop\u00e4die","logo":{"@type":"ImageObject","@id":"https:\/\/wiki.edu.vn\/wiki4\/wp-content\/uploads\/2023\/08\/download.jpg","url":"https:\/\/wiki.edu.vn\/wiki4\/wp-content\/uploads\/2023\/08\/download.jpg","width":600,"height":60}},"image":{"@type":"ImageObject","@id":"https:\/\/pl.wikipedia.org\/wiki\/Special:CentralAutoLogin\/start?type=1x1","url":"https:\/\/pl.wikipedia.org\/wiki\/Special:CentralAutoLogin\/start?type=1x1","height":"1","width":"1"},"url":"https:\/\/wiki.edu.vn\/all2jp\/wiki47\/archives\/11040","wordCount":1376,"articleBody":" (adsbygoogle = window.adsbygoogle || []).push({});before-content-x4Apache nutch – \u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u3001\u62e1\u5f35\u53ef\u80fd\u3067\u30b9\u30b1\u30fc\u30e9\u30d6\u30eb\u306a\u30a4\u30f3\u30bf\u30fc\u30cd\u30c3\u30c8\u30ed\u30dc\u30c3\u30c8\uff08Web\u30b5\u30a4\u30c8\u3092\u691c\u7d22\u304a\u3088\u3073\u5206\u6790\u3059\u308b\u305f\u3081\u306e\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30fc\u30d7\u30ed\u30b0\u30e9\u30e0\uff09Apache Foundation\u306e\u30b1\u30a2\u306e\u4e0b\u3067\u958b\u767a\u3055\u308c\u305f [2] \u3002 (adsbygoogle = window.adsbygoogle || []).push({});after-content-x4Nutch\u30b7\u30b9\u30c6\u30e0\u306e\u7279\u5fb4\uff08Yadav\u3068Goyal\u306b\u3088\u308b [3] \uff09\uff1a \u591a\u6570\u306e\u6a5f\u80fd\u3068\u30b7\u30b9\u30c6\u30e0\u64cd\u4f5c\u3092\u67d4\u8edf\u306b\u69cb\u6210\u3059\u308b\u6a5f\u80fd [4] [5] \u3001 \u30b7\u30b9\u30c6\u30e0\u6a5f\u80fd\u3092\u62e1\u5f35\u3059\u308b\u53ef\u80fd\u6027\uff08\u30d7\u30e9\u30b0\u30b7\u30b9\u30c6\u30e0\u3092\u4f7f\u7528\uff09 [4] [6] \u3001 Tika\u3084Solr\u306a\u3069\u306eApache\u30a8\u30b3\u30b7\u30b9\u30c6\u30e0\u306e\u4ed6\u306e\u8981\u7d20\u3001\u307e\u305f\u306fHadoop\u30d7\u30e9\u30c3\u30c8\u30d5\u30a9\u30fc\u30e0\u3068\u306e\u7c21\u5358\u306a\u7d71\u5408\u3001 \u9ad8\u3044\u30b9\u30b1\u30fc\u30e9\u30d3\u30ea\u30c6\u30a3\u3068\u640d\u50b7\u306b\u5bfe\u3059\u308b\u62b5\u6297\u3001 \u5206\u6563\u30ad\u30fc\u30d0\u30eb\u30d6\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u306b\u30c7\u30fc\u30bf\u3092\u4fdd\u5b58\u3059\u308b\u53ef\u80fd\u6027\u3001\u4f8b\uff1aHBase\uff08\u30d0\u30fc\u30b8\u30e7\u30f32.0\u304b\u3089\uff09\u3001 \u30ed\u30dc\u30c3\u30c8\u9664\u5916\u30d7\u30ed\u30c8\u30b3\u30eb\u30e1\u30ab\u30cb\u30ba\u30e0\u306e\u30eb\u30fc\u30eb\u3092\u8003\u616e\u3057\u3066\uff08\u30d5\u30a1\u30a4\u30eb\u306eWeb\u30da\u30fc\u30b8\u306b\u4fdd\u5b58\u3055\u308c\u3066\u3044\u307e\u3059 robots.txt \uff09\uff09 [2] \u3001 \u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30b3\u30df\u30e5\u30cb\u30c6\u30a3\u306e\u826f\u3044\u30b5\u30dd\u30fc\u30c8\u3002 Nutch\u306f\u5b8c\u5168\u306bJava\u3067\u66f8\u304b\u308c\u3066\u3044\u307e\u3059 [3] \u3001\u3057\u304b\u3057\u3001\u5f7c\u306e\u30c7\u30fc\u30bf\u306f\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u8a00\u8a9e\u3068\u306f\u7121\u95a2\u4fc2\u306b\u5f62\u5f0f\u3067\u4fdd\u5b58\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u30b7\u30b9\u30c6\u30e0\u306e\u69cb\u9020\u306f\u30e2\u30b8\u30e5\u30fc\u30eb\u5f0f\u3067\u3042\u308b\u305f\u3081\u3001\u64cd\u4f5c\u3092\u5909\u66f4\u3057\u3066\u4ed6\u306e\u30c4\u30fc\u30eb\u3084\u30e9\u30a4\u30d6\u30e9\u30ea\u306b\u63a5\u7d9a\u3067\u304d\u307e\u3059\u3002 Nutch\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306e\u4e00\u90e8\u3068\u3057\u3066\u3001API\u30a4\u30f3\u30bf\u30fc\u30d5\u30a7\u30a4\u30b9\u304c\u4f5c\u6210\u3055\u308c\u307e\u3057\u305f\u3002\u30d7\u30e9\u30b0\u30a4\u30f3\u306e\u5f62\u6210\uff08\u82f1\u8a9e \u30d7\u30e9\u30b0\u30a4\u30f3 \uff09\u30b7\u30b9\u30c6\u30e0\u3078\u3002\u5229\u7528\u53ef\u80fd\u306aAPI\u30a4\u30f3\u30bf\u30fc\u30d5\u30a7\u30a4\u30b9\u306e1\u3064\u306fREST API\u3067\u3059\u3002\u3053\u308c\u306b\u3088\u308a\u3001\u30b0\u30e9\u30d5\u30a3\u30c3\u30af\u30a4\u30f3\u30bf\u30fc\u30d5\u30a7\u30a4\u30b9\u3084\u30b3\u30de\u30f3\u30c9\u3092\u4f7f\u7528\u3059\u308b\u3053\u3068\u306a\u304f\u3001\u30b7\u30b9\u30c6\u30e0\u64cd\u4f5c\u306e\u30a4\u30f3\u30bf\u30e9\u30af\u30c6\u30a3\u30d6\u306a\u5236\u5fa1\u304c\u53ef\u80fd\u306b\u306a\u308a\u307e\u3059\u3002 [7] \u3002 \u305d\u306e\u88dc\u52a9\u30bf\u30b9\u30af\u306e\u591a\u304f\u3067\u306f\u3001Nutch\u306f\u65e2\u5b58\u306e\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u306b\u57fa\u3065\u3044\u3066\u3044\u307e\u3059 [6] \uff1a (adsbygoogle = window.adsbygoogle || []).push({});after-content-x4Hadoop\uff1a\u30b9\u30b1\u30fc\u30e9\u30d3\u30ea\u30c6\u30a3\u3001\u30bf\u30b9\u30af\u3001\u30c7\u30fc\u30bf\u30b7\u30ea\u30fc\u30ba\uff081.x\u884c\uff09 Tika\uff1a\u30d5\u30a1\u30a4\u30eb\u5f62\u5f0f\u306e\u8a8d\u8b58 Solr\u3001Elasticsearch\uff1a\u4fdd\u5b58\u3055\u308c\u305f\u30c7\u30fc\u30bf\u3067\u691c\u7d22\u3057\u307e\u3059 Gora\u3001Hbase\u3001Cassandra\uff1a\u30c7\u30fc\u30bf\u53ce\u96c6\uff082.x\u884c\uff09 \u30af\u30ed\u30fc\u30e9\u30fc\u30b3\u30e2\u30f3\u30ba [8] \uff1a\u30d5\u30a1\u30a4\u30eb\u51e6\u7406 robots.txt Nutch Project\u306f\u3001Doug Cutting\u306e\u5354\u529b\uff08\u3068\u308a\u308f\u3051Lucene Platforms\u306e\u4f5c\u6210\u8005\uff09\u3068Mike Cafarelli\u306e\u4e00\u74b0\u3068\u3057\u30662002\u5e74\u306b\u958b\u59cb\u3055\u308c\u307e\u3057\u305f\u3002 2004\u5e74\u30682005\u5e74\u306e\u5909\u308f\u308a\u76ee\u306b\u3001Nutch\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306fMapReduce\u95a2\u6570\u306b\u3088\u3063\u3066\u5b9f\u88c5\u3055\u308c\u3001\u5206\u6563\u30d5\u30a1\u30a4\u30eb\u30b7\u30b9\u30c6\u30e0\u304c\u5c0e\u5165\u3055\u308c\u307e\u3057\u305f\uff08\u3053\u308c\u306f\u5f8c\u3067\u4ed6\u306e\u8981\u7d20\u3068\u5225\u306eHadoop\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u3068\u3057\u3066\u5206\u96e2\u3055\u308c\u307e\u3057\u305f\uff09\u3002\u3053\u308c\u306b\u3088\u308a\u3001\u591a\u304f\u306e\u30c7\u30d0\u30a4\u30b9\u3067\u306e\u30c7\u30fc\u30bf\u306e\u51e6\u7406\u3068\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u4f5c\u6210\u304c\u53ef\u80fd\u306b\u306a\u308a\u307e\u3057\u305f\u3002 2005\u5e741\u6708\u3001Nutch\u306fApache Software Foundation\uff08ASF\uff09\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306b\u53c2\u52a0\u3057\u307e\u3057\u305f – \u6700\u521d\u306fSo -Called\u306b\u3088\u3063\u3066\u30ab\u30d0\u30fc\u3055\u308c\u3066\u3044\u307e\u3059\u540c\u3058\u5e74\u306e6\u6708\u306b\u30eb\u30fc\u30bb\u30f3\u306e\u30b5\u30d6\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306b\u306a\u308b\u305f\u3081\u306e\u30a4\u30f3\u30ad\u30e5\u30d9\u30fc\u30b7\u30e7\u30f3 [6] \u3002 2010\u5e74\u3001Nutch\u306f\u6700\u9ad8\u30ec\u30d9\u30eb\u3067\u72ec\u7acb\u3057\u305fASF\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306b\u306a\u308a\u307e\u3057\u305f [9] \u3002 2014\u5e742\u6708\u3001Common Crawl\u30d7\u30ed\u30b8\u30a7\u30af\u30c8 [\u5341] \u5f7c\u306f\u3001\u5927\u898f\u6a21\u306a\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u4f5c\u6210\u306e\u305f\u3081\u306e\u5f7c\u306e\u30aa\u30fc\u30d7\u30f3\u30c4\u30fc\u30eb\u3068\u3057\u3066Nutch\u3092\u53d7\u3051\u5165\u308c\u307e\u3057\u305f [11] \u3002 \u2191 Apache Nutch – \u975e\u5e38\u306b\u62e1\u5f35\u53ef\u80fd\u3067\u3001\u975e\u5e38\u306b\u30b9\u30b1\u30fc\u30e9\u30d6\u30eb\u306aWeb\u30af\u30ed\u30fc\u30e9\u30fc \u3001nutch.apache.org [\u30a2\u30af\u30bb\u30b92020-05-02] \u3002 \u2191 a b \u30de\u30a4\u30af\u30fb\u30ab\u30d5\u30a1\u30ec\u30e9\u3001\u30c0\u30b0\u30fb\u30ab\u30c3\u30c6\u30a3\u30f3\u30b0\u3002 Building Nutch\uff1a\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u691c\u7d22 \u3002 \u300cACM\u30ad\u30e5\u30fc\u300d\u3002 2\uff082\uff09\u3001s\u3002 54-61\u30012004\u3002 \uff08 \u3002 \uff09\uff09 \u3002 \u2191 a b \u30e2\u30cb\u30ab\u30fb\u30e4\u30c0\u30d6\u3001\u30cd\u30cf\u30fb\u30b4\u30e4\u30eb\u3002 \u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30af\u30ed\u30fc\u30e9\u30fc\u306e\u6bd4\u8f03 – \u30ec\u30d3\u30e5\u30fc \u3002 \u300c\u79d1\u5b66\u304a\u3088\u3073\u5de5\u5b66\u7814\u7a76\u306e\u56fd\u969b\u30b8\u30e3\u30fc\u30ca\u30eb\u300d\u3002 2229\uff085518\uff09\u3001s\u3002 1544-1551\u30012015\u3002 \uff08 \u3002 \uff09\uff09 \u3002 \u2191 a b Nutchtutorial -Nutch -Apache Software Foundation \u3001cwiki.apache.org [\u30a2\u30af\u30bb\u30b92020-05-03] \u3002 \u2191 L. A.\u30ed\u30da\u30b9\u3001R\u3002Duerr\u3001S\u3002J\u3002S. Khalsa\u300d \u5927\u898f\u6a21\u306b\u30c9\u30e1\u30a4\u30f3\u56fa\u6709\u306e\u30af\u30ed\u30fc\u30eb\u306e\u305f\u3081\u306eApacheNutch\u3092\u6700\u9069\u5316\u3059\u308b \u3001\u300d 2015 IEEE\u56fd\u969b\u30d3\u30c3\u30b0\u30c7\u30fc\u30bf\u306b\u95a2\u3059\u308b\u4f1a\u8b70\uff08\u30d3\u30c3\u30b0\u30c7\u30fc\u30bf\uff09 \u3001\u30ab\u30ea\u30d5\u30a9\u30eb\u30cb\u30a2\u5dde\u30b5\u30f3\u30bf\u30af\u30e9\u30e9\u30012015\u5e74\u3001pp\u3002 1967-1971\u3002 \u2191 a b c \u30bb\u30d0\u30b9\u30c1\u30e3\u30f3\u30fb\u30ca\u30fc\u30b2\u30eb\uff1a Apache nutch\u3067raw\u3046\u30a6\u30a7\u30d6 \u3002 2014\u5e74\u3002 \uff08 \u3002 \uff09\uff09 \u3002 \u2191 Nutchrestapi -Nutch -Apache Software Foundation \u3001cwiki.apache.org [\u30a2\u30af\u30bb\u30b92020-05-05] \u3002 \u2191 github \u3001 \u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30ea\u30dd\u30b8\u30c8\u30ea\uff1aCrawler-Commons \u3001Crawler-Commons\u30013 Maja 2020 [\u30a2\u30af\u30bb\u30b92020-05-04] \u3002 \u2191 nutch.apache.org \u3001 Apache Nutch\u2122 – \u30cb\u30e5\u30fc\u30b9 \u3001nutch.apache.org [\u30a2\u30af\u30bb\u30b92020-05-01] \u3002 \u2191 \u3088\u304f\u3042\u308b\u8cea\u554f – \u4e00\u822c\u7684\u306a\u30af\u30ed\u30fc\u30eb [\u30a2\u30af\u30bb\u30b92020-05-04] \uff08 \u3002 \uff09\uff09 \u3002 \u2191 Common Crawl’s Move to Nutch – Common Crawl [\u30a2\u30af\u30bb\u30b92020-05-01] \uff08 \u3002 \uff09\uff09 \u3002 (adsbygoogle = window.adsbygoogle || []).push({});after-content-x4"},{"@context":"http:\/\/schema.org\/","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"item":{"@id":"https:\/\/wiki.edu.vn\/all2jp\/wiki47\/#breadcrumbitem","name":"Enzyklop\u00e4die"}},{"@type":"ListItem","position":2,"item":{"@id":"https:\/\/wiki.edu.vn\/all2jp\/wiki47\/archives\/11040#breadcrumbitem","name":"Apache Nutch-\u30a6\u30a3\u30ad\u30da\u30c7\u30a3\u30a2\u3001\u7121\u6599\u200b\u200b\u767e\u79d1\u4e8b\u5178"}}]}]