{"id":104457,"date":"2024-03-22T08:21:11","date_gmt":"2024-03-21T23:21:11","guid":{"rendered":"https:\/\/www.silicloud.com\/ja\/blog\/mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84\/"},"modified":"2024-03-28T14:34:35","modified_gmt":"2024-03-28T05:34:35","slug":"mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/ja\/blog\/mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84\/","title":{"rendered":"mongodb\u3067HTML\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u308a\u305f\u3044"},"content":{"rendered":"

MongoDB\u306f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u3067\u3001\u4e3b\u306b\u5927\u91cf\u306e\u975e\u69cb\u9020\u5316\u30c7\u30fc\u30bf\u3092\u683c\u7d0d\u30fb\u51e6\u7406\u3059\u308b\u305f\u3081\u306b\u4f7f\u7528\u3055\u308c\u308b\u3002HTML\u30c7\u30fc\u30bf\u306e\u8aad\u307f\u53d6\u308a\u3068\u89e3\u6790\u306b\u306f\u76f4\u63a5\u30b5\u30dd\u30fc\u30c8\u3057\u3066\u3044\u306a\u3044\u3002<\/p>\n

HTML\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u3063\u3066MongoDB\u306b\u683c\u7d0d\u3059\u308b\u5834\u5408\u3001Python\u306a\u3069\u306e\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u8a00\u8a9e\u3068\u305d\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u4f7f\u7528\u3067\u304d\u307e\u3059\u3002<\/p>\n

\u4ee5\u4e0b\u306b 1 \u3064\u306e\u8003\u3048\u3089\u308c\u308b\u5b9f\u88c5\u65b9\u6cd5\u3092\u793a\u3057\u307e\u3059\u3002<\/p>\n

    \n
  1. HTML\u30d1\u30fc\u30b5\u30fc\uff08BeautifulSoup\u7b49\uff09\u3092\u5229\u7528\u3057\u3066HTML\u30c7\u30fc\u30bf\u3092\u51e6\u7406\u3059\u308b\u3002<\/li>\n
  2. \u30d1\u30fc\u30b9\u3057\u305f\u30c7\u30fc\u30bf\u3092MongoDB\u306e\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\uff08JSON\u5f62\u5f0f\uff09\u306b\u5909\u63db\u3059\u308b\u3002<\/li>\n
  3. MongoDB\u306e\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u306b\u63a5\u7d9a\u3059\u308b\u306b\u306f\u3001MongoDB\u306e\u30c9\u30e9\u30a4\u30d0\u30fc\u307e\u305f\u306fORM\u30e9\u30a4\u30d6\u30e9\u30ea\uff08\u305f\u3068\u3048\u3070pymongo\uff09\u3092\u4f7f\u7528\u3057\u307e\u3059\u3002<\/li>\n
  4. \u5909\u63db\u3057\u305f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3092MongoDB\u306e\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u306b\u633f\u5165\u3059\u308b\u3002<\/li>\n<\/ol>\n

    \u4ee5\u4e0b\u306b\u3001\u5358\u7d14\u306a\u30b5\u30f3\u30d7\u30eb\u30b3\u30fc\u30c9\uff08Python\u3068BeautifulSoup\u3092\u4f7f\u7528\uff09\u3092\u793a\u3057\u307e\u3059\u3002<\/p>\n

    from<\/span> bs4 import<\/span> BeautifulSoup\r\nimport<\/span> pymongo\r\n\r\n# \u8fde\u63a5MongoDB\u6570\u636e\u5e93<\/span>\r\nclient = pymongo.MongoClient(\"mongodb:\/\/localhost:27017\/\"<\/span>)\r\ndb = client[\"mydb\"<\/span>]\r\ncollection = db[\"html_data\"<\/span>]\r\n\r\n# \u8bfb\u53d6\u548c\u89e3\u6790HTML\u6570\u636e<\/span>\r\nwith<\/span> open<\/span>(\"example.html\"<\/span>, \"r\"<\/span>) as<\/span> file:\r\n    html = file.read()\r\nsoup = BeautifulSoup(html, \"html.parser\"<\/span>)\r\n\r\n# \u8f6c\u6362\u4e3aMongoDB\u6587\u6863<\/span>\r\ndata = {\r\n    \"title\"<\/span>: soup.title.string,\r\n    \"content\"<\/span>: soup.get_text()\r\n}\r\n\r\n# \u63d2\u5165\u5230MongoDB\u96c6\u5408\u4e2d<\/span>\r\ncollection.insert_one(data)\r\n<\/code><\/pre>\n
    \u3053\u306e\u4f8b\u3067\u306f\u3001BeautifulSoup\u3068pymongo\u30e9\u30a4\u30d6\u30e9\u30ea\u304c\u3059\u3067\u306b\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3055\u308c\u3066\u304a\u308a\u3001”mydb”\u3068\u3044\u3046MongoDB\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u3068”html_data”\u3068\u3044\u3046\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u304c\u4f5c\u6210\u3055\u308c\u3066\u3044\u308b\u3053\u3068\u3092\u524d\u63d0\u3068\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n
    \u306a\u304a\u3001\u3042\u304f\u307e\u3067\u7c21\u6613\u7684\u306a\u4f8b\u3067\u3042\u308a\u3001\u81ea\u793e\u306b\u304a\u3051\u308b\u9069\u7528\u6642\u306b\u306f\u3001\u5fc5\u8981\u306b\u5fdc\u3058\u3066\u4fee\u6b63\u30fb\u62e1\u5f35\u3092\u884c\u3046\u5fc5\u8981\u304c\u3042\u308b\u70b9\u306b\u3054\u7559\u610f\u304f\u3060\u3055\u3044\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
    MongoDB\u306f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u3067\u3001\u4e3b\u306b\u5927\u91cf\u306e\u975e\u69cb\u9020\u5316\u30c7\u30fc\u30bf\u3092\u683c\u7d0d\u30fb\u51e6\u7406\u3059\u308b\u305f\u3081\u306b\u4f7f\u7528\u3055\u308c\u308b\u3002HTML\u30c7\u30fc\u30bf\u306e\u8aad\u307f\u53d6\u308a\u3068\u89e3\u6790\u306b\u306f\u76f4\u63a5\u30b5\u30dd\u30fc\u30c8\u3057\u3066\u3044\u306a\u3044\u3002 HTML\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u3063\u3066MongoDB\u306b\u683c\u7d0d\u3059\u308b\u5834\u5408\u3001P […]<\/p>\n","protected":false},"author":9,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-104457","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"\nmongodb\u3067HTML\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u308a\u305f\u3044 - Blog - Silicon Cloud<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.silicloud.com\/ja\/blog\/mongodb\u3067html\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u308a\u305f\u3044\/\" \/>\n<meta property=\"og:locale\" content=\"ja_JP\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"mongodb\u3067HTML\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u308a\u305f\u3044\" \/>\n<meta property=\"og:description\" content=\"MongoDB\u306f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u3067\u3001\u4e3b\u306b\u5927\u91cf\u306e\u975e\u69cb\u9020\u5316\u30c7\u30fc\u30bf\u3092\u683c\u7d0d\u30fb\u51e6\u7406\u3059\u308b\u305f\u3081\u306b\u4f7f\u7528\u3055\u308c\u308b\u3002HTML\u30c7\u30fc\u30bf\u306e\u8aad\u307f\u53d6\u308a\u3068\u89e3\u6790\u306b\u306f\u76f4\u63a5\u30b5\u30dd\u30fc\u30c8\u3057\u3066\u3044\u306a\u3044\u3002 HTML\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u3063\u3066MongoDB\u306b\u683c\u7d0d\u3059\u308b\u5834\u5408\u3001P […]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/ja\/blog\/mongodb\u3067html\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u308a\u305f\u3044\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2024-03-21T23:21:11+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-03-28T05:34:35+00:00\" \/>\n<meta name=\"author\" content=\"\u590f\u6a39, \u98a8\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u57f7\u7b46\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u590f\u6a39, \u98a8\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84\/\",\"url\":\"https:\/\/www.silicloud.com\/ja\/blog\/mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84\/\",\"name\":\"mongodb\u3067HTML\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u308a\u305f\u3044 - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/#website\"},\"datePublished\":\"2024-03-21T23:21:11+00:00\",\"dateModified\":\"2024-03-28T05:34:35+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/#\/schema\/person\/4e591db2661c4cc425470b461259391d\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84\/#breadcrumb\"},\"inLanguage\":\"ja\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/ja\/blog\/mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/ja\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"mongodb\u3067HTML\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u308a\u305f\u3044\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/#website\",\"url\":\"https:\/\/www.silicloud.com\/ja\/blog\/\",\"name\":\"Blog - Silicon Cloud\",\"description\":\"\",\"inLanguage\":\"ja\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/#\/schema\/person\/4e591db2661c4cc425470b461259391d\",\"name\":\"\u590f\u6a39, \u98a8\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ja\",\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/65e0ff40534461b1fa000382dc194e1716f793ab0bcb218ac3c40895551a08c5?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/65e0ff40534461b1fa000382dc194e1716f793ab0bcb218ac3c40895551a08c5?s=96&d=mm&r=g\",\"caption\":\"\u590f\u6a39, \u98a8\"},\"url\":\"https:\/\/www.silicloud.com\/ja\/blog\/author\/natsukikaze\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"ja\",\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"mongodb\u3067HTML\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u308a\u305f\u3044 - Blog - Silicon Cloud","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.silicloud.com\/ja\/blog\/mongodb\u3067html\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u308a\u305f\u3044\/","og_locale":"ja_JP","og_type":"article","og_title":"mongodb\u3067HTML\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u308a\u305f\u3044","og_description":"MongoDB\u306f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u3067\u3001\u4e3b\u306b\u5927\u91cf\u306e\u975e\u69cb\u9020\u5316\u30c7\u30fc\u30bf\u3092\u683c\u7d0d\u30fb\u51e6\u7406\u3059\u308b\u305f\u3081\u306b\u4f7f\u7528\u3055\u308c\u308b\u3002HTML\u30c7\u30fc\u30bf\u306e\u8aad\u307f\u53d6\u308a\u3068\u89e3\u6790\u306b\u306f\u76f4\u63a5\u30b5\u30dd\u30fc\u30c8\u3057\u3066\u3044\u306a\u3044\u3002 HTML\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u3063\u3066MongoDB\u306b\u683c\u7d0d\u3059\u308b\u5834\u5408\u3001P […]","og_url":"https:\/\/www.silicloud.com\/ja\/blog\/mongodb\u3067html\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u308a\u305f\u3044\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2024-03-21T23:21:11+00:00","article_modified_time":"2024-03-28T05:34:35+00:00","author":"\u590f\u6a39, \u98a8","twitter_card":"summary_large_image","twitter_misc":{"\u57f7\u7b46\u8005":"\u590f\u6a39, \u98a8"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/ja\/blog\/mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84\/","url":"https:\/\/www.silicloud.com\/ja\/blog\/mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84\/","name":"mongodb\u3067HTML\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u308a\u305f\u3044 - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/ja\/blog\/#website"},"datePublished":"2024-03-21T23:21:11+00:00","dateModified":"2024-03-28T05:34:35+00:00","author":{"@id":"https:\/\/www.silicloud.com\/ja\/blog\/#\/schema\/person\/4e591db2661c4cc425470b461259391d"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/ja\/blog\/mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84\/#breadcrumb"},"inLanguage":"ja","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/ja\/blog\/mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/ja\/blog\/mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/ja\/blog\/"},{"@type":"ListItem","position":2,"name":"mongodb\u3067HTML\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u53d6\u308a\u305f\u3044"}]},{"@type":"WebSite","@id":"https:\/\/www.silicloud.com\/ja\/blog\/#website","url":"https:\/\/www.silicloud.com\/ja\/blog\/","name":"Blog - Silicon Cloud","description":"","inLanguage":"ja"},{"@type":"Person","@id":"https:\/\/www.silicloud.com\/ja\/blog\/#\/schema\/person\/4e591db2661c4cc425470b461259391d","name":"\u590f\u6a39, \u98a8","image":{"@type":"ImageObject","inLanguage":"ja","@id":"https:\/\/www.silicloud.com\/ja\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/65e0ff40534461b1fa000382dc194e1716f793ab0bcb218ac3c40895551a08c5?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/65e0ff40534461b1fa000382dc194e1716f793ab0bcb218ac3c40895551a08c5?s=96&d=mm&r=g","caption":"\u590f\u6a39, \u98a8"},"url":"https:\/\/www.silicloud.com\/ja\/blog\/author\/natsukikaze\/"},{"@type":"ImageObject","inLanguage":"ja","@id":"https:\/\/www.silicloud.com\/ja\/blog\/mongodb%e3%81%a7html%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8a%e3%81%9f%e3%81%84\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/posts\/104457","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/users\/9"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/comments?post=104457"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/posts\/104457\/revisions"}],"predecessor-version":[{"id":206745,"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/posts\/104457\/revisions\/206745"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/media?parent=104457"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/categories?post=104457"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/tags?post=104457"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}