{"id":119819,"date":"2024-03-23T20:01:45","date_gmt":"2024-03-23T11:01:45","guid":{"rendered":"https:\/\/www.silicloud.com\/ja\/blog\/python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95\/"},"modified":"2024-04-05T18:41:56","modified_gmt":"2024-04-05T09:41:56","slug":"python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/ja\/blog\/python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95\/","title":{"rendered":"Python\u3067PDF\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u53d6\u5f97\u3059\u308b\u65b9\u6cd5"},"content":{"rendered":"<p>PyPDF2\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u4f7f\u7528\u3057\u3066\u3001Python\u304b\u3089PDF\u5185\u306e\u30c6\u30ad\u30b9\u30c8\u3092\u62bd\u51fa\u3067\u304d\u307e\u3059\u3002\u4ee5\u4e0b\u3067\u306f\u3001PDF\u30d5\u30a1\u30a4\u30eb\u3092\u958b\u3044\u3066\u305d\u306e\u30c6\u30ad\u30b9\u30c8\u5185\u5bb9\u3092\u62bd\u51fa\u3059\u308b\u65b9\u6cd5\u3092\u793a\u3059\u30b5\u30f3\u30d7\u30eb\u30b3\u30fc\u30c9\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"hljs-keyword\">import<\/span> PyPDF2\r\n<span class=\"hljs-keyword\">def<\/span> <span class=\"hljs-title function_\">extract_text_from_pdf<\/span>(<span class=\"hljs-params\">file_path<\/span>):\r\n<span class=\"hljs-keyword\">with<\/span> <span class=\"hljs-built_in\">open<\/span>(file_path, <span class=\"hljs-string\">'rb'<\/span>) <span class=\"hljs-keyword\">as<\/span> file:\r\npdf_reader = PyPDF2.PdfFileReader(file)\r\nnum_pages = pdf_reader.numPages\r\ntext = <span class=\"hljs-string\">''<\/span>\r\n<span class=\"hljs-keyword\">for<\/span> page_num <span class=\"hljs-keyword\">in<\/span> <span class=\"hljs-built_in\">range<\/span>(num_pages):\r\npage = pdf_reader.getPage(page_num)\r\ntext += page.extractText()\r\n<span class=\"hljs-keyword\">return<\/span> text\r\n<span class=\"hljs-comment\"># \u8c03\u7528\u51fd\u6570\u5e76\u4f20\u5165\u8981\u63d0\u53d6\u6587\u672c\u7684PDF\u6587\u4ef6\u8def\u5f84<\/span>\r\npdf_text = extract_text_from_pdf(<span class=\"hljs-string\">'example.pdf'<\/span>)\r\n<span class=\"hljs-built_in\">print<\/span>(pdf_text)\r\n<\/code><\/pre>\n<p>PDF\u6587\u66f8\u7279\u6709\u306e\u5236\u9650\u3084\u66f8\u5f0f\u306b\u3088\u308a\u3001PDF\u30c6\u30ad\u30b9\u30c8\u306e\u62bd\u51fa\u7cbe\u5ea6\u306f\u5f71\u97ff\u3092\u53d7\u3051\u308b\u53ef\u80fd\u6027\u304c\u3042\u308b\u3053\u3068\u306b\u3054\u6ce8\u610f\u304f\u3060\u3055\u3044\u3002\u4e00\u90e8\u306ePDF\u6587\u66f8\u306f\u5b8c\u5168\u306b\u306f\u62bd\u51fa\u3067\u304d\u305a\u3001\u62bd\u51fa\u3055\u308c\u305f\u30c6\u30ad\u30b9\u30c8\u306b\u306f\u3044\u304f\u3064\u304b\u306e\u4e71\u308c\u3084\u66f8\u5f0f\u306e\u554f\u984c\u304c\u542b\u307e\u308c\u3066\u3044\u308b\u5834\u5408\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>PyPDF2\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u4f7f\u7528\u3057\u3066\u3001Python\u304b\u3089PDF\u5185\u306e\u30c6\u30ad\u30b9\u30c8\u3092\u62bd\u51fa\u3067\u304d\u307e\u3059\u3002\u4ee5\u4e0b\u3067\u306f\u3001PDF\u30d5\u30a1\u30a4\u30eb\u3092\u958b\u3044\u3066\u305d\u306e\u30c6\u30ad\u30b9\u30c8\u5185\u5bb9\u3092\u62bd\u51fa\u3059\u308b\u65b9\u6cd5\u3092\u793a\u3059\u30b5\u30f3\u30d7\u30eb\u30b3\u30fc\u30c9\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002 import PyPDF2 def e [&hellip;]<\/p>\n","protected":false},"author":7,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-119819","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.5 (Yoast SEO v21.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Python\u3067PDF\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u53d6\u5f97\u3059\u308b\u65b9\u6cd5 - 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\/python\u3067pdf\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u53d6\u5f97\u3059\u308b\u65b9\u6cd5\/\" \/>\n<meta property=\"og:locale\" content=\"ja_JP\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Python\u3067PDF\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u53d6\u5f97\u3059\u308b\u65b9\u6cd5\" \/>\n<meta property=\"og:description\" content=\"PyPDF2\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u4f7f\u7528\u3057\u3066\u3001Python\u304b\u3089PDF\u5185\u306e\u30c6\u30ad\u30b9\u30c8\u3092\u62bd\u51fa\u3067\u304d\u307e\u3059\u3002\u4ee5\u4e0b\u3067\u306f\u3001PDF\u30d5\u30a1\u30a4\u30eb\u3092\u958b\u3044\u3066\u305d\u306e\u30c6\u30ad\u30b9\u30c8\u5185\u5bb9\u3092\u62bd\u51fa\u3059\u308b\u65b9\u6cd5\u3092\u793a\u3059\u30b5\u30f3\u30d7\u30eb\u30b3\u30fc\u30c9\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002 import PyPDF2 def e [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/ja\/blog\/python\u3067pdf\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u53d6\u5f97\u3059\u308b\u65b9\u6cd5\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2024-03-23T11:01:45+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-05T09:41:56+00:00\" \/>\n<meta name=\"author\" content=\"\u7d50\u8863, \u6625\u82b1\" \/>\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=\"\u7d50\u8863, \u6625\u82b1\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95\/\",\"url\":\"https:\/\/www.silicloud.com\/ja\/blog\/python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95\/\",\"name\":\"Python\u3067PDF\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u53d6\u5f97\u3059\u308b\u65b9\u6cd5 - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/#website\"},\"datePublished\":\"2024-03-23T11:01:45+00:00\",\"dateModified\":\"2024-04-05T09:41:56+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/#\/schema\/person\/e52a686063ac76fd8cc6f539d41497ac\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95\/#breadcrumb\"},\"inLanguage\":\"ja\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/ja\/blog\/python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/ja\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Python\u3067PDF\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u53d6\u5f97\u3059\u308b\u65b9\u6cd5\"}]},{\"@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\/e52a686063ac76fd8cc6f539d41497ac\",\"name\":\"\u7d50\u8863, \u6625\u82b1\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ja\",\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/c74c6e2eb915a3c8e795b3934aa25a7333e0b38e7f1c7baf52785286ad51105e?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/c74c6e2eb915a3c8e795b3934aa25a7333e0b38e7f1c7baf52785286ad51105e?s=96&d=mm&r=g\",\"caption\":\"\u7d50\u8863, \u6625\u82b1\"},\"url\":\"https:\/\/www.silicloud.com\/ja\/blog\/author\/yuiharuka\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"ja\",\"@id\":\"https:\/\/www.silicloud.com\/ja\/blog\/python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Python\u3067PDF\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u53d6\u5f97\u3059\u308b\u65b9\u6cd5 - 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\/python\u3067pdf\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u53d6\u5f97\u3059\u308b\u65b9\u6cd5\/","og_locale":"ja_JP","og_type":"article","og_title":"Python\u3067PDF\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u53d6\u5f97\u3059\u308b\u65b9\u6cd5","og_description":"PyPDF2\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u4f7f\u7528\u3057\u3066\u3001Python\u304b\u3089PDF\u5185\u306e\u30c6\u30ad\u30b9\u30c8\u3092\u62bd\u51fa\u3067\u304d\u307e\u3059\u3002\u4ee5\u4e0b\u3067\u306f\u3001PDF\u30d5\u30a1\u30a4\u30eb\u3092\u958b\u3044\u3066\u305d\u306e\u30c6\u30ad\u30b9\u30c8\u5185\u5bb9\u3092\u62bd\u51fa\u3059\u308b\u65b9\u6cd5\u3092\u793a\u3059\u30b5\u30f3\u30d7\u30eb\u30b3\u30fc\u30c9\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002 import PyPDF2 def e [&hellip;]","og_url":"https:\/\/www.silicloud.com\/ja\/blog\/python\u3067pdf\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u53d6\u5f97\u3059\u308b\u65b9\u6cd5\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2024-03-23T11:01:45+00:00","article_modified_time":"2024-04-05T09:41:56+00:00","author":"\u7d50\u8863, \u6625\u82b1","twitter_card":"summary_large_image","twitter_misc":{"\u57f7\u7b46\u8005":"\u7d50\u8863, \u6625\u82b1"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/ja\/blog\/python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95\/","url":"https:\/\/www.silicloud.com\/ja\/blog\/python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95\/","name":"Python\u3067PDF\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u53d6\u5f97\u3059\u308b\u65b9\u6cd5 - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/ja\/blog\/#website"},"datePublished":"2024-03-23T11:01:45+00:00","dateModified":"2024-04-05T09:41:56+00:00","author":{"@id":"https:\/\/www.silicloud.com\/ja\/blog\/#\/schema\/person\/e52a686063ac76fd8cc6f539d41497ac"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/ja\/blog\/python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95\/#breadcrumb"},"inLanguage":"ja","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/ja\/blog\/python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/ja\/blog\/python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/ja\/blog\/"},{"@type":"ListItem","position":2,"name":"Python\u3067PDF\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u53d6\u5f97\u3059\u308b\u65b9\u6cd5"}]},{"@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\/e52a686063ac76fd8cc6f539d41497ac","name":"\u7d50\u8863, \u6625\u82b1","image":{"@type":"ImageObject","inLanguage":"ja","@id":"https:\/\/www.silicloud.com\/ja\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/c74c6e2eb915a3c8e795b3934aa25a7333e0b38e7f1c7baf52785286ad51105e?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/c74c6e2eb915a3c8e795b3934aa25a7333e0b38e7f1c7baf52785286ad51105e?s=96&d=mm&r=g","caption":"\u7d50\u8863, \u6625\u82b1"},"url":"https:\/\/www.silicloud.com\/ja\/blog\/author\/yuiharuka\/"},{"@type":"ImageObject","inLanguage":"ja","@id":"https:\/\/www.silicloud.com\/ja\/blog\/python%e3%81%a7pdf%e3%81%8b%e3%82%89%e3%83%86%e3%82%ad%e3%82%b9%e3%83%88%e3%82%92%e5%8f%96%e5%be%97%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/posts\/119819","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\/7"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/comments?post=119819"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/posts\/119819\/revisions"}],"predecessor-version":[{"id":322944,"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/posts\/119819\/revisions\/322944"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/media?parent=119819"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/categories?post=119819"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/ja\/blog\/wp-json\/wp\/v2\/tags?post=119819"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}