\u06cc\u06a9\u067e\u0627\u0631\u0686\u0647 \u0633\u0627\u0632\u06cc Nutch 1.7 \u0628\u0627 ElasticSearch<\/p>\n
\u0642\u0627\u0628\u0644\u06cc\u062a \u06cc\u06a9\u067e\u0627\u0631\u0686\u0647 \u0633\u0627\u0632\u06cc Nutch 1.7 \u0628\u0627 ElasticSearch \u0628\u0648\u062c\u0648\u062f \u0622\u0645\u062f\u0647 \u0627\u0633\u062a.
\n\u062a\u0646\u0638\u06cc\u0645 \u06cc\u06a9\u067e\u0627\u0631\u0686\u0647 \u0633\u0627\u0632\u06cc \u0627\u0631\u0632\u0634 \u0641\u0648\u0642 \u0627\u0644\u0639\u0627\u062f\u0647 \u0627\u06cc \u062f\u0627\u0631\u062f<\/p>\n
\u0627\u06cc\u0646 \u0631\u0627\u0647\u0646\u0645\u0627 \u0628\u0631\u0627\u06cc \u0627\u0641\u0631\u0627\u062f\u06cc \u06a9\u0647 \u0628\u0627 Nutch \u0648 ElasticSearch \u06a9\u0627\u0631 \u06a9\u0631\u062f\u0647 \u0627\u0646\u062f \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u062f\u0633\u062a\u0648\u0631\u0627\u0644\u0639\u0645\u0644 \u062e\u0648\u0628\u06cc \u0628\u0627\u0634\u062f<\/p>\n
Nutch \u06a9\u0627\u0631 \u062e\u0632\u0634 (Crawl) \u060c \u0648\u0627\u06a9\u0634\u06cc (fetch) \u0648 \u062a\u062c\u0632\u06cc\u0647 (parse) \u0631\u0627 \u0628\u0631\u0627\u06cc \u0646\u0645\u0627\u06cc\u0647 \u0633\u0627\u0632\u06cc (indexing) \u0628\u0647 \u0637\u0648\u0631 \u0645\u0639\u062c\u0632\u0627 \u0622\u0633\u0627\u06cc\u06cc \u0627\u0646\u062c\u0627\u0645 \u0645\u06cc \u062f\u0647\u062f \u060c \u0648\u0644\u06cc \u0628\u0627 \u0627\u06cc\u0646 \u062d\u0627\u0644 \u06cc\u06a9\u067e\u0627\u0631\u0686\u0647 \u0646\u06cc\u0633\u062a.<\/p>\n
\u0627\u06cc\u0646 \u06a9\u0627\u0631\u06cc \u06a9\u0647 \u0627\u0646\u062c\u0627\u0645 \u0645\u06cc\u062f\u0647\u06cc\u0645 \u062a\u063a\u06cc\u06cc\u0631 \u0641\u0627\u06cc\u0644 nutch-site.xml \u062f\u0631 \u0634\u0627\u062e\u0647 conf \u062f\u0631 \u062c\u0627\u06cc\u06cc \u06a9\u0647 Nutch \u0646\u0635\u0628 \u0634\u062f\u0647 \u0627\u0633\u062a.
\n\u0627\u0648\u0644 \u0627\u0632 \u0647\u0645\u0647 \u0627\u062d\u062a\u06cc\u0627\u062c \u062f\u0627\u0631\u06cc\u0645 \u06a9\u0647 \u0627\u0641\u0632\u0648\u0646\u0647 \u0646\u0645\u0627\u06cc\u0647 \u0633\u0627\u0632 ( Indexer Plugin ) \u0631\u0627 \u0641\u0639\u0627\u0644 \u06a9\u0646\u06cc\u0645 \u06a9\u0647 \u0627\u06cc\u0646 \u06a9\u0627\u0631 \u0631\u0627 \u0628\u0627 \u062f\u0633\u062a\u0648\u0631\u0627\u062a \u0632\u06cc\u0631 \u0627\u0646\u062c\u0627\u0645 \u0645\u06cc\u062f\u0647\u06cc\u0645 :<\/p>\n
<\/p>\n
<\/p>\n
<property><\/p>\n
<name>plugin.includes<\/name><\/p>\n
<value>protocol-http|urlfilter-regex|parse-(html|tika)|index-(basic|anchor)|indexer-elastic|scoring-opic|urlnormalizer-(pass|regex|basic)<\/value><\/p>\n
<description>Regular expression naming plugin directory names to\u00a0include. Any plugin not matching this expression is excluded.<\/p>\n
In any\u00a0case<\/span><\/strong>\u00a0<\/span>you need at least include the nutch-extensionpoints plugin. By\u00a0default Nutch includes crawling just HTML and plain text via HTTP,<\/p>\n and basic indexing and search plugins. In order to use HTTPS please\u00a0enable\u00a0<\/strong><\/span>protocol-httpclient, but be aware of possible intermittent problems with the<\/p>\n underlying commons-httpclient library.<\/p>\n <\/description><\/p>\n <\/property><\/p>\n \u0622\u06cc\u062a\u0645 \u0647\u0627\u06cc \u06a9\u0647 \u0627\u06cc\u0646\u062c\u0627 \u0627\u0636\u0627\u0641\u0647 \u0634\u062f\u0647 \u0627\u0646\u062f \u0628\u0631\u0627\u06cc \u0646\u0645\u0627\u06cc\u0647 \u0633\u0627\u0632 Elastic \u0647\u0633\u062a\u0646\u062f. <!– Elasticsearch properties –><\/p>\n <property><\/p>\n <name>elastic.host<\/name><\/p>\n <value>localhost<\/span><\/value><\/p>\n <description>The\u00a0hostname\u00a0<\/span><\/strong>to send documents to using TransportClient. Either host<\/p>\n and port must be defined or cluster.<\/description><\/p>\n <\/property><\/p>\n <property><\/p>\n <name>elastic.port<\/name><\/p>\n <value>9300<\/value><\/p>\n <description><\/p>\n <\/description><\/p>\n <\/property><\/p>\n <property><\/p>\n <name>elastic.cluster<\/name><\/p>\n <value>elasticsearch<\/value><\/p>\n <description>The cluster name to discover. Either host and potr must be defined<\/p>\n or cluster.<\/description><\/p>\n <\/property><\/p>\n <property><\/p>\n <name>elastic.index<\/name><\/p>\n <value>nutch<\/value><\/p>\n <description>Default index to send documents to.<\/description><\/p>\n <\/property><\/p>\n <property><\/p>\n <name>elastic.max.bulk.docs<\/name><\/p>\n <value>250<\/value><\/p>\n <description>Maximum size of the bulk\u00a0in\u00a0<\/strong><\/span>number of documents.<\/description><\/p>\n <\/property><\/p>\n <property><\/p>\n <name>elastic.max.bulk.size<\/name><\/p>\n <value>2500500<\/value><\/p>\n <description>Maximum size of the bulk\u00a0in\u00a0<\/strong><\/span>bytes.<\/description><\/p>\n <\/property><\/p>\n \u062f\u0631 \u0627\u06cc\u0646 \u0645\u0648\u0631\u062f \u0645\u0646 ElasticSearch \u0631\u0627 \u0631\u0648\u06cc \u0647\u0645\u0627\u0646 \u06a9\u06cc\u0633 \u0646\u0635\u0628 \u06a9\u0631\u062f\u0647 \u0627\u0645 \u060c \u0628\u0647 \u0647\u0645\u06cc\u0646 \u062f\u0644\u06cc\u0644 elastic.host \u0646\u0627\u0645 localhost \u0645\u0646 \u0647\u0633\u062a<\/p>\n \u0646\u06a9\u062a\u0647 \u0645\u0647\u0645 \u062f\u06cc\u06af\u0631 \u0646\u0627\u0645 elastic.cluster \u0627\u0633\u062a\u060c \u0627\u06af\u0631 \u0634\u0645\u0627 \u0686\u06cc\u0632\u06cc \u062f\u0631 \u0627\u06cc\u0646 \u0645\u0648\u0631\u062f \u0646\u0645\u06cc\u062f\u0627\u0646\u06cc\u062f \u0641\u0627\u06cc\u0644 elasticsearch.yml \u0631\u0627 \u062f\u0631 \u0634\u0627\u062e\u0647 \u0627\u06cc \u06a9\u0647 \u062a\u0646\u0638\u06cc\u0645\u0627\u062a \u0646\u0635\u0628 ElasticSearch \u0642\u0631\u0627\u0631 \u062f\u0627\u0631\u062f \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u067e\u06cc\u062f\u0627 \u06a9\u0646\u06cc\u062f.<\/p>\n \u067e\u0648\u0631\u062a elastic.port \u0628\u0647 \u0635\u0648\u0631\u062a \u067e\u06cc\u0634 \u0641\u0631\u0636 \u06f9\u06f3\u06f0\u06f0 \u0628\u0631\u0627\u06cc \u0648\u0627\u0633\u0637 \u0627\u0633\u062a ( \u0628\u0631\u0627\u06cc \u062e\u0631\u0645\u062c\u06cc \u0648\u0628 \u067e\u0648\u0631\u062a \u06f9\u06f2\u06f0\u06f0 \u06a9\u0647 \u0632\u0645\u0627\u0646\u06cc \u0627\u0633\u062a \u06a9\u0647 \u0628\u0627 nutch \u06cc\u06a9\u067e\u0627\u0631\u0686\u0647 \u0633\u0627\u0632\u06cc \u0646\u0634\u062f\u0647 ). \u062f\u06cc\u06af\u0631 \u0646\u06cc\u0627\u0632 \u0646\u06cc\u0633\u062a \u06a9\u0647 conf\/elasticsearch.conf \u0631\u0627 \u062a\u063a\u06cc\u06cc\u0631 \u062f\u0647\u06cc\u062f \u0648 \u06cc\u0627 \u0628\u0647 Nutch 2.x \u0627\u0631\u062a\u0642\u0627 \u062f\u0647\u06cc\u0645.<\/p>\n <\/p>\n \u062a\u0631\u062c\u0645\u0647 : \u0646\u0627\u062f\u06cc \u0633\u0646\u062c\u0627\u0646\u06cc<\/p>\n \u0645\u0646\u0628\u0639 : https:\/\/www.mind-it.info\/integrating-nutch-1-7-elasticsearch<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" \u06cc\u06a9\u067e\u0627\u0631\u0686\u0647 \u0633\u0627\u0632\u06cc Nutch 1.7 \u0628\u0627 ElasticSearch \u0642\u0627\u0628\u0644\u06cc\u062a \u06cc\u06a9\u067e\u0627\u0631\u0686\u0647 \u0633\u0627\u0632\u06cc Nutch 1.7 \u0628\u0627 ElasticSearch \u0628\u0648\u062c\u0648\u062f \u0622\u0645\u062f\u0647 \u0627\u0633\u062a. \u062a\u0646\u0638\u06cc\u0645 \u06cc\u06a9\u067e\u0627\u0631\u0686\u0647 \u0633\u0627\u0632\u06cc \u0627\u0631\u0632\u0634 \u0641\u0648\u0642 \u0627\u0644\u0639\u0627\u062f\u0647 \u0627\u06cc \u062f\u0627\u0631\u062f \u0627\u06cc\u0646 \u0631\u0627\u0647\u0646\u0645\u0627 \u0628\u0631\u0627\u06cc \u0627\u0641\u0631\u0627\u062f\u06cc \u06a9\u0647 \u0628\u0627 Nutch \u0648 ElasticSearch \u06a9\u0627\u0631 \u06a9\u0631\u062f\u0647 \u0627\u0646\u062f \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u062f\u0633\u062a\u0648\u0631\u0627\u0644\u0639\u0645\u0644 \u062e\u0648\u0628\u06cc \u0628\u0627\u0634\u062f Nutch \u06a9\u0627\u0631 \u062e\u0632\u0634 (Crawl) \u060c \u0648\u0627\u06a9\u0634\u06cc (fetch) \u0648 \u062a\u062c\u0632\u06cc\u0647 (parse) \u0631\u0627 \u0628\u0631\u0627\u06cc \u0646\u0645\u0627\u06cc\u0647 \u0633\u0627\u0632\u06cc […]<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[34],"tags":[],"class_list":["post-1421","post","type-post","status-publish","format-standard","hentry","category-34","category-34-id","post-seq-1","post-parity-odd","meta-position-corners","fix"],"_links":{"self":[{"href":"https:\/\/vua.nadiran.com\/index.php?rest_route=\/wp\/v2\/posts\/1421"}],"collection":[{"href":"https:\/\/vua.nadiran.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/vua.nadiran.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/vua.nadiran.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/vua.nadiran.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1421"}],"version-history":[{"count":4,"href":"https:\/\/vua.nadiran.com\/index.php?rest_route=\/wp\/v2\/posts\/1421\/revisions"}],"predecessor-version":[{"id":1424,"href":"https:\/\/vua.nadiran.com\/index.php?rest_route=\/wp\/v2\/posts\/1421\/revisions\/1424"}],"wp:attachment":[{"href":"https:\/\/vua.nadiran.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1421"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/vua.nadiran.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1421"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/vua.nadiran.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1421"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\n\u062f\u0631 \u0645\u0631\u062d\u0644\u0647 \u062f\u0648\u0645 \u0627\u062d\u062a\u06cc\u0627\u062c \u062f\u0627\u0631\u06cc\u0645 \u06a9\u0647 \u0645\u0648\u0627\u0631\u062f \u0632\u06cc\u0631 \u0631\u0627 \u062f\u0631 nutch-site.xml \u062a\u063a\u06cc\u06cc\u0631 \u062f\u0647\u06cc\u0645<\/p>\n
\n\u062f\u0631 \u0646\u0647\u0627\u06cc\u062a \u0627\u06cc\u0646\u062f\u06a9\u0633 \u0631\u0627 \u062f\u0631 ElasticSearch \u062f\u0631 \u0641\u0627\u06cc\u0644 \u062a\u0646\u0638\u06cc\u0645\u0627\u062a elastic.index \u0628\u0633\u0627\u0632\u06cc\u062f.<\/p>\n