{"id":1000,"date":"2011-01-25T22:13:55","date_gmt":"2011-01-25T13:13:55","guid":{"rendered":"http:\/\/www.kazu.tv\/blog\/?p=1000"},"modified":"2011-01-25T22:13:55","modified_gmt":"2011-01-25T13:13:55","slug":"rubyscraping","status":"publish","type":"post","link":"https:\/\/kazu.tv\/blog\/2011\/01\/25\/rubyscraping\/","title":{"rendered":"Ruby\u3067scraping"},"content":{"rendered":"<h3>\u25a0Ruby\u3067\u30b9\u30af\u30ec\u30a4\u30d4\u30f3\u30b0\u3059\u308b\u305f\u3081\u306e\u30c4\u30fc\u30eb<\/h3>\n<p>&quot;ruby scraping&quot;\u3067\u691c\u7d22\u3059\u308b\u3068\u3053\u306e<a href=\"http:\/\/route477.net\/rubyscraping\/\" target=\"_blank\">\u30da\u30fc\u30b8<\/a>\u304c\u5f15\u3063\u304b\u304b\u308b\u3002\u3044\u304f\u3064\u304b\u306e\u30c4\u30fc\u30eb\u306e\u7d39\u4ecb\u3068\u7c21\u5358\u306a\u6bd4\u8f03\u3092\u3057\u3066\u308b\u3093\u3060\u3051\u3069\u3001\u672c\u5f53\u306b\u3055\u308f\u308a\u3060\u3051\u306a\u306e\u3067\u3084\u3063\u3071\u308a\u81ea\u5206\u3067\u3042\u308b\u7a0b\u5ea6\u8a66\u3057\u3066\u307f\u308b\u5fc5\u8981\u304c\u3042\u308b\u3002\u3042\u3068\u3001\u82e5\u5e72\u60c5\u5831\u304c\u53e4\u3044\u3002<\/p>\n<p>\u81ea\u5206\u306f\u7d50\u8ad6\u304b\u3089\u8a00\u3046\u3068<a href=\"http:\/\/mechanize.rubyforge.org\/mechanize\/\" target=\"_blank\">Mechanize<\/a>\u3092\u4f7f\u3046\u4e8b\u306b\u3057\u305f\u3002\u7406\u7531\u306f\u4ee5\u4e0b\u306e\u901a\u308a\u3002<\/p>\n<ul>\n<li>\u30da\u30fc\u30b8\u306e\u3053\u306e\u30ea\u30f3\u30af\u3092\u30af\u30ea\u30c3\u30af\u3057\u3066\u6b21\u306e\u30da\u30fc\u30b8\u3067\u30d5\u30a9\u30fc\u30e0\u306b\u3053\u308c\u3092\u5165\u308c\u3066&hellip;\u307f\u305f\u3044\u306a\u611f\u3058\u306e\u64cd\u4f5c\u3092\u3001\u6bd4\u8f03\u7684\u76f4\u611f\u7684\u306b\u30d7\u30ed\u30b0\u30e9\u30e0\u3067\u8a18\u8ff0\u3067\u304d\u308b\u3002<\/li>\n<li>\u4f9d\u5b58\u30d1\u30c3\u30b1\u30fc\u30b8\u304c\u5c11\u306a\u3044\u306e\u3067\uff08<a href=\"http:\/\/nokogiri.org\/\" target=\"_blank\">nokogiri<\/a>\u3060\u3051\uff09\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u304c\u697d<\/li>\n<li>\u5272\u3068\u30e1\u30f3\u30c6\u30ca\u30f3\u30b9\u304c\u3055\u308c\u3066\u3044\u308b<\/li>\n<\/ul>\n<p><!--more--><\/p>\n<h3>\u25a0\u4f7f\u3044\u65b9\u3067\u5206\u304b\u308a\u3065\u3089\u304b\u3063\u305f\u4e8b<\/h3>\n<p>\u4f7f\u3044\u65b9\u306f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3092\u898b\u308c\u3070\u5927\u4f53\u5206\u304b\u308b\u3068\u3057\u3066\u3001\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3060\u3068\u5206\u304b\u308a\u3065\u3089\u3044\u70b9\u3092\u3044\u304f\u3064\u304b\u7d39\u4ecb\u3002<\/p>\n<p>\u25cb\u753b\u50cf\u306e\u4fdd\u5b58<\/p>\n<pre class=\"brush: ruby; code\">\nagent = Mechanize.new do |obj|\nobj.user_agent_alias = 'Windows IE 7'\nend\n# \uff08\u4e2d\u7565\uff09\n# \u3053\u308c\u3067\u30da\u30fc\u30b8\u5185\u306eimage\u30bf\u30b0\u4e00\u89a7\u304c\u53d6\u5f97\u3067\u304d\u308b\u3002\nsomepage.images\n# \u753b\u50cf\u306e\u4e2d\u8eab\u3092\u53d6\u5f97\u3057\u3066\u30d5\u30a1\u30a4\u30eb\u306b\u4fdd\u5b58\u3059\u308b\u5834\u5408\u306f\nsomepage.images.each do |img|\nimgfile = agent.get(img.src)\nimgfile_path = '\/foo\/bar\/' + imgfile.filename\nimgfile.save_as(imgfile_path)\nend<\/pre>\n<p>\u25cb\u30d5\u30ec\u30fc\u30e0\u306e\u8868\u793a<\/p>\n<p>\u6700\u8fd1\u306f\u30d5\u30ec\u30fc\u30e0\u3092\u4f7f\u3063\u305f\u30da\u30fc\u30b8\u3082\u5c11\u306a\u304f\u306a\u3063\u305f\u3051\u3069\u3001\u305f\u307e\u306b\u4f7f\u3046\u6a5f\u4f1a\u304c\u3042\u308b\u304b\u3082\u3002\u30dd\u30a4\u30f3\u30c8\u306fclick\u30e1\u30bd\u30c3\u30c9\u3002<\/p>\n<pre class=\"brush: ruby; code\">\nframe = somepage.frames_with(:name =&gt; &quot;framename&quot;)[0].click\n<\/pre>\n<p>&nbsp;\u25cb\u30c7\u30d0\u30c3\u30b0<\/p>\n<p>\u30e2\u30b8\u30e5\u30fc\u30eb\u81ea\u4f53\u3092\u30c7\u30d0\u30c3\u30b0\u3057\u305f\u3044\u6642\u3001\u30ed\u30b0\u30ec\u30d9\u30eb\u3092\u5909\u66f4\u3059\u308b\u3002\u5b9f\u969b\u306b\u3053\u308c\u3092\u4f7f\u3063\u3066\u3001Mechanize\u306e\u30d0\u30b0\u3089\u3057\u304d\u7269\u3092\u767a\u898b\u3067\u304d\u305f\u3002<\/p>\n<pre class=\"brush: ruby; code\">\nrequire 'rubygems'\nrequire 'mechanize'\nrequire 'logger'\nagent = Mechanize.new do |obj|\nobj.user_agent_alias = 'Windows IE 7'\nobj.log = Logger.new(STDOUT)\nobj.log.level = Logger::DEBUG\nend\n<\/pre>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u25a0Ruby\u3067\u30b9\u30af\u30ec\u30a4\u30d4\u30f3\u30b0\u3059\u308b\u305f\u3081\u306e\u30c4\u30fc\u30eb &quot;ruby scraping&quot;\u3067\u691c\u7d22\u3059\u308b\u3068\u3053\u306e\u30da\u30fc\u30b8\u304c\u5f15\u3063\u304b\u304b\u308b\u3002\u3044\u304f\u3064\u304b\u306e\u30c4\u30fc\u30eb\u306e\u7d39\u4ecb\u3068\u7c21\u5358\u306a\u6bd4\u8f03\u3092\u3057\u3066\u308b\u3093\u3060\u3051\u3069\u3001\u672c\u5f53\u306b\u3055\u308f\u308a\u3060\u3051\u306a\u306e\u3067\u3084\u3063\u3071\u308a\u81ea\u5206\u3067\u3042&hellip;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[8],"tags":[856,313,857,858],"class_list":["post-1000","post","type-post","status-publish","format-standard","hentry","category-8","tag-mechanize","tag-ruby","tag-scraping","tag-858"],"_links":{"self":[{"href":"https:\/\/kazu.tv\/blog\/wp-json\/wp\/v2\/posts\/1000","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/kazu.tv\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/kazu.tv\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/kazu.tv\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/kazu.tv\/blog\/wp-json\/wp\/v2\/comments?post=1000"}],"version-history":[{"count":0,"href":"https:\/\/kazu.tv\/blog\/wp-json\/wp\/v2\/posts\/1000\/revisions"}],"wp:attachment":[{"href":"https:\/\/kazu.tv\/blog\/wp-json\/wp\/v2\/media?parent=1000"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/kazu.tv\/blog\/wp-json\/wp\/v2\/categories?post=1000"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/kazu.tv\/blog\/wp-json\/wp\/v2\/tags?post=1000"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}