{"id":7352,"date":"2017-06-20T14:13:41","date_gmt":"2017-06-20T12:13:41","guid":{"rendered":"http:\/\/www.b.shuttle.de\/hayek\/hayek\/jochen\/wp\/blog-en\/?p=7352"},"modified":"2017-06-20T14:13:41","modified_gmt":"2017-06-20T12:13:41","slug":"apache-nutch","status":"publish","type":"post","link":"https:\/\/wp.jochen.hayek.name\/blog-en\/2017\/06\/20\/apache-nutch\/","title":{"rendered":"&#8220;Apache Nutch&#8221; is a highly extensible and scalable open source web crawler software project"},"content":{"rendered":"<ul>\n<li><a href=\"https:\/\/en.wikipedia.org\/wiki\/Apache_Nutch\">https:\/\/en.wikipedia.org\/wiki\/Apache_Nutch<\/a><\/li>\n<li><a href=\"https:\/\/en.wikipedia.org\/wiki\/Web_crawler\">https:\/\/en.wikipedia.org\/wiki\/Web_crawler<\/a><\/li>\n<li><a href=\"https:\/\/nutch.apache.org\">https:\/\/nutch.apache.org<\/a>\u00a0\u2013\u00a0official website<\/li>\n<li><a href=\"https:\/\/wiki.apache.org\/nutch\">https:\/\/wiki.apache.org\/nutch<\/a> \u2013 official wiki<\/li>\n<li><a href=\"https:\/\/wiki.apache.org\/nutch\/Nutch2Crawling\">https:\/\/wiki.apache.org\/nutch\/Nutch2Crawling<\/a> \u2013 &#8220;a\u00a0description of the crawling jobs and field to database mappings&#8221;<\/li>\n<li><a href=\"https:\/\/www.amazon.de\/dp\/1590596870\">https:\/\/www.amazon.de\/dp\/1590596870<\/a>\u00a0\u2013 apress:\u00a0Building Search Applications with Lucene and Nutch<\/li>\n<li><a href=\"https:\/\/www.amazon.de\/dp\/1783286857\">https:\/\/www.amazon.de\/dp\/1783286857<\/a>\u00a0\u2013 PACKT:\u00a0Web Crawling and Data Mining with Apache Nutch (2017-06-20: PACKT do not list this product any longer \u2013 but still date 2014-\u2026 and available &#8220;somewhere&#8221;)<\/li>\n<li><a href=\"https:\/\/www.amazon.de\/dp\/1156025532\">https:\/\/www.amazon.de\/dp\/1156025532<\/a>\u00a0\u2013 LLC Books:\u00a0Free Search Engine Software: Lucene, Apache Solr, Yacy, Dataparksearch, Nutch, Pubchemsr, Sciencenet, Xapian, Opensearchserver, Grub, Ht&#8212;Dig<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>https:\/\/en.wikipedia.org\/wiki\/Apache_Nutch https:\/\/en.wikipedia.org\/wiki\/Web_crawler https:\/\/nutch.apache.org\u00a0\u2013\u00a0official website https:\/\/wiki.apache.org\/nutch \u2013 official wiki https:\/\/wiki.apache.org\/nutch\/Nutch2Crawling \u2013 &#8220;a\u00a0description of the crawling jobs and field to database mappings&#8221; https:\/\/www.amazon.de\/dp\/1590596870\u00a0\u2013 apress:\u00a0Building Search Applications with Lucene and Nutch https:\/\/www.amazon.de\/dp\/1783286857\u00a0\u2013 PACKT:\u00a0Web Crawling and Data Mining with Apache Nutch (2017-06-20: PACKT do not list this product any longer \u2013 but still date 2014-\u2026 and available &#8220;somewhere&#8221;) https:\/\/www.amazon.de\/dp\/1156025532\u00a0\u2013 [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_crdt_document":"","jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2},"_share_on_mastodon":"0"},"categories":[695,700],"tags":[],"class_list":["post-7352","post","type-post","status-publish","format-standard","hentry","category-web-crawling","category-web-scraping"],"share_on_mastodon":{"url":"","error":""},"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/paO0kP-1UA","jetpack_likes_enabled":true,"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/wp.jochen.hayek.name\/blog-en\/wp-json\/wp\/v2\/posts\/7352","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wp.jochen.hayek.name\/blog-en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wp.jochen.hayek.name\/blog-en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wp.jochen.hayek.name\/blog-en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/wp.jochen.hayek.name\/blog-en\/wp-json\/wp\/v2\/comments?post=7352"}],"version-history":[{"count":0,"href":"https:\/\/wp.jochen.hayek.name\/blog-en\/wp-json\/wp\/v2\/posts\/7352\/revisions"}],"wp:attachment":[{"href":"https:\/\/wp.jochen.hayek.name\/blog-en\/wp-json\/wp\/v2\/media?parent=7352"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wp.jochen.hayek.name\/blog-en\/wp-json\/wp\/v2\/categories?post=7352"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wp.jochen.hayek.name\/blog-en\/wp-json\/wp\/v2\/tags?post=7352"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}