{"id":743,"date":"2021-07-21T14:50:36","date_gmt":"2021-07-21T05:50:36","guid":{"rendered":"https:\/\/gri.jp\/media\/entry\/743"},"modified":"2022-04-15T17:38:58","modified_gmt":"2022-04-15T08:38:58","slug":"2021-07-21-145036","status":"publish","type":"post","link":"https:\/\/gri.jp\/media\/entry\/743","title":{"rendered":"puppeteer\u3092\u4f7f\u3063\u3066Javascript\u306a\u30b5\u30a4\u30c8\u3092\u30af\u30ed\u30fc\u30eb\u3059\u308b"},"content":{"rendered":"<h3>\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb<\/h3>\n<p>\u65e9\u901f\u5b9f\u8df5\u3057\u3066\u3044\u304d\u307e\u3059<br \/>\n\u307e\u305a\u306f\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb&#8230;<\/p>\n<pre class=\"code bash\" data-lang=\"bash\" data-unlink=\"\">yarn add puppeteer\r\n# or \"npm i puppeteer\"<\/pre>\n<p>\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u304c\u5b8c\u4e86\u3059\u308c\u3070node_modules\u30d5\u30a9\u30eb\u30c0\u306e\u4e2d\u306b\u8272\u3005\u5165\u308a\u307e\u3059<\/p>\n<blockquote class=\"twitter-tweet\" data-conversation=\"none\" data-lang=\"en\">\n<p dir=\"ltr\" lang=\"en\">$ npm install <a href=\"https:\/\/t.co\/RQdSqcGXHT\">pic.twitter.com\/RQdSqcGXHT<\/a><\/p>\n<p>\u2014 Zeno Rocha (@zenorocha) <a href=\"https:\/\/twitter.com\/zenorocha\/status\/1408432082741649411?ref_src=twsrc%5Etfw\">June 25, 2021<\/a><\/p><\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>\u3053\u308c\u3067OK\u3067\u3059<\/p>\n<h3>\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb<\/h3>\n<p><a href=\"https:\/\/github.com\/puppeteer\/puppeteer\" target=\"_blank\" rel=\"noopener\">github<\/a>\u306eexample\u3092\u3055\u3089\u3044\u307e\u3059<\/p>\n<pre class=\"code lang-javascript\" data-lang=\"javascript\" data-unlink=\"\"><span class=\"synComment\">\/\/ example.js<\/span>\r\n<span class=\"synStatement\">const<\/span> puppeteer = require(<span class=\"synConstant\">'puppeteer'<\/span>);\r\n(async () =&gt; <span class=\"synIdentifier\">{<\/span>\r\n<span class=\"synStatement\">const<\/span> browser = await puppeteer.launch();\r\n<span class=\"synStatement\">const<\/span> page = await browser.newPage();\r\nawait page.<span class=\"synStatement\">goto<\/span>(<span class=\"synConstant\">'https:\/\/example.com'<\/span>);\r\nawait page.screenshot(<span class=\"synIdentifier\">{<\/span> path: <span class=\"synConstant\">'example.png'<\/span> <span class=\"synIdentifier\">}<\/span>);\r\nawait browser.close();\r\n<span class=\"synIdentifier\">}<\/span>)();\r\n<\/pre>\n<p>\u5b9f\u884c<\/p>\n<p><!--more--><\/p>\n<pre class=\"code bash\" data-lang=\"bash\" data-unlink=\"\">node example.js<\/pre>\n<p>\u6307\u5b9a\u3057\u305fexample.com\u306e\u30da\u30fc\u30b8\u306e\u30b9\u30af\u30b7\u30e7\u306e\u4fdd\u5b58\u304c\u3067\u304d\u307e\u3057\u305f<br \/>\n\u306a\u3093\u3066\u3053\u3068\u3067\u3057\u3087\u3046\uff01 python\u3067\u540c\u69d8\u306e\u3053\u3068\u3059\u308b\u5834\u5408\u3001\u30d6\u30e9\u30a6\u30b6\u3084\u30c9\u30e9\u30a4\u30d0\u306e\u4f9d\u5b58\u95a2\u4fc2\u3068python\u3067\u306e\u8a2d\u5b9a\u306b\u8a70\u307e\u3063\u305f\u308a\u3057\u307e\u3059\u304cpuppeteer\u3092\u4f7f\u3048\u3070\u7c21\u5358\u306b\u3067\u304d\u3066\u3057\u307e\u3044\u307e\u3057\u305f<\/p>\n<h3>\u30af\u30ed\u30fc\u30eb<\/h3>\n<p>\u3067\u306f\u5b9f\u969b\u306bjavascript\u306a\u30b5\u30a4\u30c8\u306e\u30af\u30ed\u30fc\u30ea\u30f3\u30b0\u3092\u884c\u3044\u307e\u3059<\/p>\n<p>\u5bfe\u8c61\u306f\u5f0a\u793eGRI\u306e\u6280\u8853\u672c\u3092\u53d6\u5f97\u3059\u308b\u3053\u3068\u306b\u3057\u307e\u3057\u305f<br \/>\n\u4e00\u822c\u516c\u958b\u3057\u3066\u3044\u308b\u306e\u3067\u3088\u304b\u3063\u305f\u3089\u3069\u3046\u3044\u3046\u3082\u306e\u304c\u3042\u308b\u306e\u304b\u898b\u3066\u307f\u3066\u304f\u3060\u3055\u3044(\u7d50\u69cb\u3042\u308a\u307e\u3059)<br \/>\n<a href=\"https:\/\/gri.jp\/ai-info\" target=\"_blank\" rel=\"noopener\">https:\/\/gri.jp\/ai-info<\/a><\/p>\n<img loading=\"lazy\" decoding=\"async\" class=\"hatena-fotolife\" title=\"\" src=\"\/media\/wp\/wp-content\/uploads\/2021\/08\/20210721145623.png\" alt=\"f:id:gri-blog:20210721145623p:plain\" width=\"800\" height=\"600\" \/>\n<p>\u3053\u306e\u30da\u30fc\u30b8\u306e\u672c\u68da\u3092\u30af\u30ea\u30c3\u30af\u3059\u308b\u3068\u88cf\u3067javascript\u304c\u52d5\u3044\u3066\u307e\u3059(\u3042\u305f\u308a\u307e\u3048)<br \/>\n\u30da\u30fc\u30b8\u306f\u7121\u9650\u30b9\u30af\u30ed\u30fc\u30eb\u306b\u306a\u3063\u3066\u304a\u308a\u3001\u30b9\u30af\u30ed\u30fc\u30eb\u6bce\u306b\u65b0\u3057\u3044\u672c\u304c\u8868\u793a\u3055\u308c\u308b\u306e\u3067\u5358\u7d14\u306ahtml\u306e\u30ea\u30af\u30a8\u30b9\u30c8\u3060\u3068\u5168\u90e8\u306e\u672c\u306e\u53d6\u5f97\u306f\u3067\u304d\u307e\u305b\u3093<\/p>\n<p>\u3053\u3053\u3067puppeteer\u306e\u51fa\u756a<\/p>\n<p>\u307e\u305a\u306f\u3053\u306e\u30b5\u30a4\u30c8\u306b\u5165\u308b\u3053\u3068\u306b\u3057\u307e\u3057\u3087\u3046<\/p>\n<pre class=\"code lang-javascript\" data-lang=\"javascript\" data-unlink=\"\"><span class=\"synStatement\">const<\/span> puppeteer = require(<span class=\"synConstant\">'puppeteer'<\/span>);\r\n<span class=\"synStatement\">const<\/span> url = <span class=\"synConstant\">'https:\/\/gri.jp\/ai-info'<\/span>;\r\n(async () =&gt; <span class=\"synIdentifier\">{<\/span>\r\n<span class=\"synStatement\">const<\/span> browser = await puppeteer.launch();\r\n<span class=\"synStatement\">const<\/span> page = await browser.newPage();\r\nawait page.<span class=\"synStatement\">goto<\/span>(url);\r\nawait page.screenshot(<span class=\"synIdentifier\">{<\/span> path: <span class=\"synConstant\">'book.png'<\/span> <span class=\"synIdentifier\">}<\/span>);\r\nawait browser.close();\r\n<span class=\"synIdentifier\">}<\/span>)();\r\n<\/pre>\n<p>\u672c\u68da\u306e\u30da\u30fc\u30b8\u306f <code>ul<\/code> \u8981\u7d20\u3001\u30af\u30e9\u30b9\u540d\u304c <code>library_items<\/code> \u3068\u306a\u3063\u3066\u3044\u307e\u3059\u306d<\/p>\n<img loading=\"lazy\" decoding=\"async\" class=\"hatena-fotolife\" title=\"\" src=\"\/media\/wp\/wp-content\/uploads\/2021\/08\/20210721145648.png\" alt=\"f:id:gri-blog:20210721145648p:plain\" width=\"1200\" height=\"181\" \/>\n<p>\u3053\u306e\u8981\u7d20\u3092\u30af\u30ea\u30c3\u30af\u3057\u3066\u672c\u68da\u30da\u30fc\u30b8\u306b\u5165\u308b\u30b3\u30fc\u30c9\u3092\u66f8\u304d\u307e\u3057\u305f<\/p>\n<p>\u5404\u30d7\u30ed\u30bb\u30b9\u3092\u898b\u9003\u3057\u305f\u304f\u306a\u3044\u306e\u3067\u30c7\u30d0\u30c3\u30b0\u30e2\u30fc\u30c9\u3067\u5b9f\u884c\u3057\u307e\u3059<br \/>\nslowMo\u30921000\u3068\u3059\u308b\u3053\u3068\u3067\u30011\u30641\u3064\u306e\u547d\u4ee4\u306f1\u79d2\u304a\u304d\u306b\u5b9f\u884c\u3055\u308c\u307e\u3059<\/p>\n<pre class=\"code lang-javascript\" data-lang=\"javascript\" data-unlink=\"\"><span class=\"synStatement\">const<\/span> puppeteer = require(<span class=\"synConstant\">\"puppeteer\"<\/span>);\r\n<span class=\"synStatement\">const<\/span> url = <span class=\"synConstant\">'https:\/\/gri.jp\/ai-info'<\/span>;\r\n(async () =&gt; <span class=\"synIdentifier\">{<\/span>\r\n<span class=\"synStatement\">const<\/span> browser = await puppeteer.launch(<span class=\"synIdentifier\">{<\/span>\r\nheadless: <span class=\"synConstant\">false<\/span>,\r\ndevtools: <span class=\"synConstant\">true<\/span>,\r\nslowMo: 1000\r\n<span class=\"synIdentifier\">}<\/span>);\r\n<span class=\"synStatement\">const<\/span> page = await browser.newPage();\r\nawait page.<span class=\"synStatement\">goto<\/span>(url, <span class=\"synIdentifier\">{<\/span> waitUntil: <span class=\"synConstant\">\"domcontentloaded\"<\/span> <span class=\"synIdentifier\">}<\/span>);\r\nawait page.click(<span class=\"synConstant\">\"ul[class=library_items]\"<\/span>);\r\nawait browser.close();\r\n<span class=\"synIdentifier\">}<\/span>)();\r\n<\/pre>\n<p>\u30af\u30ea\u30c3\u30af\u5f8c\u30da\u30fc\u30b8\u304c\u5225\u30bf\u30d6\u3067\u958b\u304b\u308c\u305f\u5f8c\u30d6\u30e9\u30a6\u30b6\u3092\u9589\u3058\u3066\u3044\u308b\u306e\u304c\u898b\u3048\u305f\u3068\u601d\u3044\u307e\u3059<\/p>\n<p>\u6b21\u306f\u3001\u672c\u304c\u5168\u3066\u51fa\u3066\u304f\u308b\u307e\u3067\u30b9\u30af\u30ed\u30fc\u30eb\u3057\u3001\u7d42\u308f\u3063\u305f\u3089\u672c\u306e\u30bf\u30a4\u30c8\u30eb\u3092\u53d6\u5f97\u3059\u308b\u3088\u3046\u306b\u5b9f\u88c5<\/p>\n<p>Div\u306eid\u304c <code>front<\/code> \u306b\u306a\u3063\u3066\u3044\u308b\u8981\u7d20\u304c\u672c\u68da\u3001\u305d\u308c\u305e\u308c\u306e\u672c\u306f\u5b50\u8981\u7d20Div\u306e\u30af\u30e9\u30b9\u540d\u304c <code>item-wrapper<\/code> \u306e\u69cb\u6210\u306a\u306e\u3067\u3001<br \/>\n\u5b50\u8981\u7d20\u306e\u6570\u3092\u6bce\u30b9\u30af\u30ed\u30fc\u30eb\u6642\u306b\u30ab\u30a6\u30f3\u30c8\u3001\u5dee\u5206\u304c\u306a\u304f\u306a\u3063\u305f\u6642\u70b9\u3067\u7d42\u4e86\u3057\u5404\u8981\u7d20\u306e\u30bf\u30a4\u30c8\u30eb\u3092\u53d6\u5f97\u3059\u308b<\/p>\n<p>\u7d50\u679c\u306foutput.txt\u30d5\u30a1\u30a4\u30eb\u306b\u66f8\u304d\u8fbc\u3080\u3068\u3057\u307e\u3057\u305f<\/p>\n<p>\u307e\u305f\u3001\u672c\u68da\u30da\u30fc\u30b8\u306b\u30af\u30ea\u30c3\u30af\u3067\u98db\u3093\u3067\u305f\u306e\u3092\u76f4\u63a5\u30da\u30fc\u30b8\u3092\u898b\u306b\u3044\u304f\u3088\u3046\u306b\u5909\u66f4\u3057\u3066\u304a\u308a\u307e\u3059<\/p>\n<pre class=\"code lang-javascript\" data-lang=\"javascript\" data-unlink=\"\"><span class=\"synStatement\">const<\/span> puppeteer = require(<span class=\"synConstant\">\"puppeteer\"<\/span>);\r\n<span class=\"synStatement\">const<\/span> fs = require(<span class=\"synConstant\">'fs'<\/span>);\r\n<span class=\"synStatement\">const<\/span> url = <span class=\"synConstant\">'https:\/\/gri.jp\/ai-info'<\/span>;\r\n(async () =&gt; <span class=\"synIdentifier\">{<\/span>\r\n<span class=\"synStatement\">const<\/span> browser = await puppeteer.launch(<span class=\"synIdentifier\">{<\/span>\r\nheadless: <span class=\"synConstant\">false<\/span>\r\n<span class=\"synIdentifier\">}<\/span>);\r\n<span class=\"synStatement\">const<\/span> page = await browser.newPage();\r\nawait page.<span class=\"synStatement\">goto<\/span>(url, <span class=\"synIdentifier\">{<\/span> waitUntil: <span class=\"synConstant\">\"domcontentloaded\"<\/span> <span class=\"synIdentifier\">}<\/span>);\r\n<span class=\"synStatement\">const<\/span> bookUrl = await page.evaluate(() =&gt;\r\n<span class=\"synStatement\">document<\/span>.querySelector(<span class=\"synConstant\">'.library_item &gt; a'<\/span>).href\r\n);\r\nawait page.<span class=\"synStatement\">goto<\/span>(bookUrl, <span class=\"synIdentifier\">{<\/span> waitUntil: <span class=\"synConstant\">\"domcontentloaded\"<\/span> <span class=\"synIdentifier\">}<\/span>);\r\nawait page.waitForTimeout(1000)\r\n<span class=\"synIdentifier\">var<\/span> elemCount = 0;\r\n<span class=\"synComment\">\/\/ \u30b9\u30af\u30ed\u30fc\u30eb\u90e8\u5206<\/span>\r\n<span class=\"synStatement\">while<\/span> (<span class=\"synConstant\">true<\/span>) <span class=\"synIdentifier\">{<\/span>\r\n<span class=\"synComment\">\/\/ \u6700\u5f8c\u306e\u672c\u306e\u8981\u7d20\u3092view\u306b\u3082\u3063\u3066\u304f\u308b<\/span>\r\nawait page.$eval(<span class=\"synConstant\">'.item-wrapper:last-child'<\/span>, elem =&gt; <span class=\"synIdentifier\">{<\/span>\r\nelem.scrollIntoView();\r\n<span class=\"synIdentifier\">}<\/span>);\r\nawait page.waitForTimeout(1000)\r\n<span class=\"synComment\">\/\/ \u518d\u5ea6\u5404\u672c\u306e\u8981\u7d20\u3092\u53d6\u5f97<\/span>\r\n<span class=\"synIdentifier\">var<\/span> length = await page.$$eval(<span class=\"synConstant\">'.item-wrapper'<\/span>, elems =&gt; <span class=\"synIdentifier\">{<\/span>\r\n<span class=\"synStatement\">return<\/span> elems.length;\r\n<span class=\"synIdentifier\">}<\/span>);\r\n<span class=\"synStatement\">if<\/span> (elemCount === length) <span class=\"synIdentifier\">{<\/span>\r\n<span class=\"synStatement\">break<\/span>;\r\n<span class=\"synIdentifier\">}<\/span> <span class=\"synStatement\">else<\/span> <span class=\"synIdentifier\">{<\/span>\r\nelemCount = length;\r\n<span class=\"synIdentifier\">}<\/span>\r\n<span class=\"synIdentifier\">}<\/span>;\r\n<span class=\"synIdentifier\">var<\/span> resultElems = await page.evaluate(() =&gt; <span class=\"synIdentifier\">{<\/span>\r\n<span class=\"synStatement\">const<\/span> elems = <span class=\"synType\">Array<\/span>.from(<span class=\"synStatement\">document<\/span>.querySelectorAll(<span class=\"synConstant\">'.item-area-img'<\/span>));\r\n<span class=\"synStatement\">return<\/span> elems.map(elem =&gt; elem.title);\r\n<span class=\"synIdentifier\">}<\/span>);\r\nfs.writeFileSync(<span class=\"synConstant\">'.\/output.txt'<\/span>, resultElems.join(<span class=\"synSpecial\">'\\n'<\/span>));\r\nawait browser.close();\r\n<span class=\"synIdentifier\">}<\/span>)();\r\n<\/pre>\n<p>\u7d50\u679c<\/p>\n<img loading=\"lazy\" decoding=\"async\" class=\"hatena-fotolife\" title=\"\" src=\"\/media\/wp\/wp-content\/uploads\/2021\/08\/20210721144305.png\" alt=\"f:id:gri-blog:20210721144305p:plain\" width=\"1200\" height=\"784\" \/>\n<p>\u5168\u3066\u306e\u672c\u306e\u30bf\u30a4\u30c8\u30eb\u304c\u53d6\u5f97\u3067\u304d\u307e\u3057\u305f<\/p>\n<h3>\u307e\u3068\u3081<\/h3>\n<p>\u4eca\u56de\u306fpuppeteer\u3067\u7c21\u5358\u306bjavascript\u306e\u30b5\u30a4\u30c8\u3092\u30af\u30ed\u30fc\u30eb\u3057\u3066\u307f\u307e\u3057\u305f<br \/>\n\u30c7\u30fc\u30bf\u3092parse\u3057\u305f\u308a\u8907\u96d1\u306a\u51e6\u7406\u3092\u5fc5\u8981\u3068\u3057\u306a\u3044\u306e\u3067\u3042\u308c\u3070js\u3092\u63a1\u7528\u3057\u3066\u3082\u826f\u3044\u304b\u3082\u3057\u308c\u307e\u305b\u3093\u306d<\/p>\n<p>\u51fa\u529b\u7d50\u679c\u3092\u898b\u3066\u307f\u308b\u3068\u3001 <code>\u30b9\u30b1\u30fc\u30e9\u30d6\u30eb \u30ea\u30a2\u30eb\u30bf\u30a4\u30e0 \u30c7\u30fc\u30bf\u5206\u6790\u5165\u9580<\/code> \u3068\u3044\u3046\u8208\u5473\u3092\u305d\u305d\u308b\u672c\u3092\u898b\u3064\u3051\u305f\u306e\u3067\u3001\u62dd\u501f\u3057\u3066\u307f\u307e\u3059\u3002\u30af\u30ed\u30fc\u30eb\u304c\u5f79\u306b\u7acb\u3061\u307e\u3057\u305f<\/p>\n<p>&#8230;&#8230;&#8230;&#8230;\u7121\u304b\u3063\u305f..<\/p>\n<p>higashi kunimitsu<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb \u65e9\u901f\u5b9f\u8df5\u3057\u3066\u3044\u304d\u307e\u3059 \u307e\u305a\u306f\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb#8230; yarn add puppeteer # or &#8220;npm i puppeteer&#8221; \u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u304c\u5b8c\u4e86\u3059\u308c\u3070node_modules\u30d5\u30a9\u30eb\u30c0\u306e\u4e2d\u306b\u8272\u3005<\/p>\n","protected":false},"author":18,"featured_media":4566,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4,127],"tags":[],"class_list":["post-743","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-datascience","category-sns"],"acf":[],"meta_field":{"_edit_lock":["1650011942:42"],"_edit_last":["42"],"_wp_page_template":["default"],"_pv_count":["a:24:{i:21;i:211;i:9;i:164;i:1;i:118;i:7;i:60;i:11;i:248;i:6;i:64;i:13;i:238;i:14;i:310;i:2;i:241;i:15;i:349;i:17;i:332;i:12;i:263;i:23;i:162;i:18;i:259;i:4;i:90;i:16;i:372;i:19;i:184;i:20;i:173;i:3;i:144;i:8;i:92;i:10;i:225;i:0;i:143;i:22;i:135;i:5;i:54;}"],"pv_count":["4629"],"memo":["\u306a\u3057"],"hidden_toppage":["0"],"_hidden_toppage":["field_61933136630d2"],"note_url":[""],"_note_url":["field_61243c8278b90"],"_thumbnail_id":["4566"]},"_links":{"self":[{"href":"https:\/\/gri.jp\/media\/wp-json\/wp\/v2\/posts\/743","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/gri.jp\/media\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/gri.jp\/media\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/gri.jp\/media\/wp-json\/wp\/v2\/users\/18"}],"replies":[{"embeddable":true,"href":"https:\/\/gri.jp\/media\/wp-json\/wp\/v2\/comments?post=743"}],"version-history":[{"count":6,"href":"https:\/\/gri.jp\/media\/wp-json\/wp\/v2\/posts\/743\/revisions"}],"predecessor-version":[{"id":6611,"href":"https:\/\/gri.jp\/media\/wp-json\/wp\/v2\/posts\/743\/revisions\/6611"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/gri.jp\/media\/wp-json\/wp\/v2\/media\/4566"}],"wp:attachment":[{"href":"https:\/\/gri.jp\/media\/wp-json\/wp\/v2\/media?parent=743"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/gri.jp\/media\/wp-json\/wp\/v2\/categories?post=743"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/gri.jp\/media\/wp-json\/wp\/v2\/tags?post=743"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}