{"id":436,"date":"2024-04-22T17:59:45","date_gmt":"2024-04-22T08:59:45","guid":{"rendered":"https:\/\/chocottopro.com\/?p=436"},"modified":"2024-04-26T11:02:08","modified_gmt":"2024-04-26T02:02:08","slug":"%e3%80%90python%e3%80%91%e5%88%9d%e5%bf%83%e8%80%85%e5%90%91%e3%81%91pypdf2%e3%81%ae%e4%bd%bf%e3%81%84%e6%96%b9%e5%ae%8c%e5%85%a8%e3%82%ac%e3%82%a4%e3%83%89%ef%bc%81pdf%e3%82%92%e8%87%aa%e5%9c%a8","status":"publish","type":"post","link":"https:\/\/chocottopro.com\/?p=436","title":{"rendered":"\u3010Python\u3011\u521d\u5fc3\u8005\u5411\u3051pypdf2\u306e\u4f7f\u3044\u65b9\u5b8c\u5168\u30ac\u30a4\u30c9\uff01PDF\u3092\u81ea\u5728\u306b\u64cd\u4f5c\u3057\u3088\u3046"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">PDF\u306f\u69d8\u3005\u306a\u5834\u9762\u3067\u4f7f\u308f\u308c\u308b\u6587\u66f8\u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u3067\u3059\u304c\u3001\u305d\u306e\u307e\u307e\u3067\u306f\u7de8\u96c6\u3084\u52a0\u5de5\u304c\u96e3\u3057\u3044\u3082\u306e\u3067\u3059\u3002\u3057\u304b\u3057\u3001Python\u306epypdf2\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u4f7f\u3048\u3070\u3001PDF\u3092\u81ea\u7531\u306b\u64cd\u4f5c\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3059\u3002\u672c\u8a18\u4e8b\u3067\u306f\u3001pypdf2\u306e\u57fa\u672c\u7684\u306a\u4f7f\u3044\u65b9\u304b\u3089\u5b9f\u8df5\u7684\u306a\u6d3b\u7528\u4f8b\u307e\u3067\u3001\u521d\u5fc3\u8005\u306b\u3082\u308f\u304b\u308a\u3084\u3059\u304f\u89e3\u8aac\u3057\u307e\u3059\u3002PDF\u306e\u8aad\u307f\u8fbc\u307f\u3001\u30da\u30fc\u30b8\u306e\u62bd\u51fa\u3001\u30c6\u30ad\u30b9\u30c8\u62bd\u51fa\u3001\u6697\u53f7\u5316\u306a\u3069\u3001pypdf2\u3092\u4f7f\u3044\u3053\u306a\u3059\u305f\u3081\u306e\u30c6\u30af\u30cb\u30c3\u30af\u304c\u6e80\u8f09\u3067\u3059\u3002\u307e\u305f\u3001PDF\u306e\u69cb\u9020\u3084\u4ed5\u69d8\u306b\u3064\u3044\u3066\u306e\u77e5\u8b58\u3082\u6df1\u3081\u3089\u308c\u307e\u3059\u3002Python\u3067pdf\u64cd\u4f5c\u306e\u5b9f\u8df5\u7684\u306a\u30b9\u30ad\u30eb\u3092\u8eab\u306b\u3064\u3051\u3001\u696d\u52d9\u306e\u81ea\u52d5\u5316\u3084\u52b9\u7387\u5316\u306b\u5f79\u7acb\u3066\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n<div class=\"wp-block-sgb-block-simple sgb-box-simple sgb-box-simple--title-normal sgb-box-simple--with-border\"><div style=\"background-color:var(--wp--preset--color--sango-main);color:#FFF\" class=\"sgb-box-simple__title\">\u3053\u306e\u8a18\u4e8b\u3092\u8aad\u3093\u3060\u3089\u308f\u304b\u308b\u3053\u3068<\/div><div class=\"sgb-box-simple__body\" style=\"border-color:var(--wp--preset--color--sango-main);background-color:#FFF\">\n<p class=\"wp-block-paragraph\"><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>pypdf2\u3068\u306f\u4f55\u304b\u3092\u7406\u89e3\u3057\u3001PDF\u3092Python\u3067\u64cd\u4f5c\u3059\u308b\u305f\u3081\u306e\u57fa\u672c\u7684\u306a\u77e5\u8b58\u304c\u8eab\u306b\u3064\u304f<\/li>\n\n\n\n<li>PDF\u30d5\u30a1\u30a4\u30eb\u306e\u8aad\u307f\u8fbc\u307f\u3001\u66f8\u304d\u51fa\u3057\u3001\u30da\u30fc\u30b8\u306e\u62bd\u51fa\u30fb\u7d50\u5408\u30fb\u5206\u5272\u306a\u3069\u3001\u57fa\u672c\u7684\u306a\u64cd\u4f5c\u65b9\u6cd5\u304c\u308f\u304b\u308b<\/li>\n\n\n\n<li>\u30c6\u30ad\u30b9\u30c8\u62bd\u51fa\u3001\u900f\u304b\u3057\u8ffd\u52a0\u3001\u6697\u53f7\u5316\u306a\u3069\u3001pypdf2\u3092\u4f7f\u3063\u305fPDF\u52a0\u5de5\u306e\u65b9\u6cd5\u3092\u5b66\u3079\u308b<\/li>\n\n\n\n<li>\u5927\u91cf\u306ePDF\u3092\u4e00\u62ec\u51e6\u7406\u3059\u308b\u65b9\u6cd5\u3084\u3001PDF\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u62bd\u51fa\u3057\u3066Excel\u306b\u66f8\u304d\u51fa\u3059\u65b9\u6cd5\u306a\u3069\u3001\u5b9f\u8df5\u7684\u306a\u6d3b\u7528\u4f8b\u304c\u7406\u89e3\u3067\u304d\u308b<\/li>\n\n\n\n<li>OCR\u3092\u4f7f\u3063\u305fPDF\u306e\u30c6\u30ad\u30b9\u30c8\u62bd\u51fa\u3084\u3001\u8acb\u6c42\u66f8\u306e\u81ea\u52d5\u51e6\u7406\u306a\u3069\u3001\u9ad8\u5ea6\u306a\u51e6\u7406\u306e\u5b9f\u73fe\u65b9\u6cd5\u304c\u308f\u304b\u308b<\/li>\n\n\n\n<li>pypdf2\u3092\u4f7f\u3046\u4e0a\u3067\u306e\u6ce8\u610f\u70b9\u3084\u30c8\u30e9\u30d6\u30eb\u30b7\u30e5\u30fc\u30c6\u30a3\u30f3\u30b0\u306e\u65b9\u6cd5\u3092\u62bc\u3055\u3048\u3089\u308c\u308b<\/li>\n\n\n\n<li>PDF\u306e\u69cb\u9020\u3084\u4ed5\u69d8\u306b\u3064\u3044\u3066\u306e\u57fa\u790e\u77e5\u8b58\u304c\u8eab\u306b\u3064\u304f<\/li>\n\n\n\n<li>\u516c\u5f0f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u306e\u8aad\u307f\u65b9\u3084\u3001\u767a\u5c55\u7684\u306a\u5b66\u7fd2\u30ea\u30bd\u30fc\u30b9\u306e\u63a2\u3057\u65b9\u304c\u308f\u304b\u308b<\/li>\n\n\n\n<li>PyPI\u3084GitHub\u3092\u901a\u3058\u3066\u3001pypdf2\u306e\u6700\u65b0\u60c5\u5831\u3092\u8ffd\u3046\u65b9\u6cd5\u304c\u7406\u89e3\u3067\u304d\u308b<\/li>\n\n\n\n<li>Python\u3092\u4f7f\u3063\u305fPDF\u51e6\u7406\u306e\u5b9f\u8df5\u7684\u306a\u30b9\u30ad\u30eb\u304c\u8eab\u306b\u3064\u304d\u3001\u696d\u52d9\u306e\u81ea\u52d5\u5316\u3084\u52b9\u7387\u5316\u306b\u6d3b\u7528\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308b<\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<div class=\"toc\"><br \/>\n<b>Warning<\/b>:  Undefined array key \"is_admin\" in <b>\/home\/c7479301\/public_html\/chocottopro.com\/wp-content\/themes\/sango-theme\/library\/gutenberg\/dist\/classes\/Toc.php<\/b> on line <b>116<\/b><br \/>\n<br \/>\n<b>Warning<\/b>:  Undefined array key \"is_category_top\" in <b>\/home\/c7479301\/public_html\/chocottopro.com\/wp-content\/themes\/sango-theme\/library\/gutenberg\/dist\/classes\/Toc.php<\/b> on line <b>121<\/b><br \/>\n<br \/>\n<b>Warning<\/b>:  Undefined array key \"is_top\" in <b>\/home\/c7479301\/public_html\/chocottopro.com\/wp-content\/themes\/sango-theme\/library\/gutenberg\/dist\/classes\/Toc.php<\/b> on line <b>128<\/b><br \/>\n    <div id=\"toc_container\" class=\"sgb-toc--bullets js-smooth-scroll\" data-dialog-title=\"Table of Contents\">\n      <p class=\"toc_title\">\u76ee\u6b21 <\/p>\n      <ul class=\"toc_list\">  <li class=\"first\">    <a href=\"#i-0\">pypdf2\u3068\u306f\uff1fPDF\u3092Python\u3067\u64cd\u4f5c\u3059\u308b\u305f\u3081\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u5fb9\u5e95\u89e3\u8aac<\/a>  <\/li>  <li>    <a href=\"#i-1\">pypdf2\u306e\u57fa\u672c\u7684\u306a\u4f7f\u3044\u65b9\u3092\u30de\u30b9\u30bf\u30fc\u3057\u3088\u3046<\/a>  <\/li>  <li>    <a href=\"#i-2\">pypdf2\u306e\u5b9f\u8df5\u7684\u306a\u6d3b\u7528\u4f8b5\u9078<\/a>    <ul class=\"menu_level_1\">      <li class=\"first\">        <a href=\"#i-3\">\u5927\u91cf\u306ePDF\u30d5\u30a1\u30a4\u30eb\u3092\u4e00\u62ec\u51e6\u7406\u3059\u308b<\/a>      <\/li>      <li>        <a href=\"#i-4\">PDF\u304b\u3089\u30c7\u30fc\u30bf\u3092\u62bd\u51fa\u3057\u3066Excel\u306b\u66f8\u304d\u51fa\u3059<\/a>      <\/li>      <li>        <a href=\"#i-5\">\u8907\u6570\u306ePDF\u3092\u7d50\u5408\u3057\u30661\u3064\u306e\u30d5\u30a1\u30a4\u30eb\u306b\u307e\u3068\u3081\u308b<\/a>      <\/li>      <li>        <a href=\"#i-6\">PDF\u3092\u30b9\u30ad\u30e3\u30f3\u3057\u3066OCR\u51e6\u7406\u3092\u884c\u3046<\/a>      <\/li>      <li class=\"last\">        <a href=\"#i-7\">PyPDF2\u3092\u4f7f\u3063\u305f\u8acb\u6c42\u66f8\u306e\u81ea\u52d5\u51e6\u7406\u30b7\u30b9\u30c6\u30e0\u3092\u4f5c\u308b<\/a>      <\/li>    <\/ul>  <\/li>  <li class=\"last\">    <a href=\"#i-8\">pypdf2\u306e\u4f7f\u3044\u65b9\u307e\u3068\u3081\uff06\u767a\u5c55\u7684\u306a\u5b66\u7fd2\u30ea\u30bd\u30fc\u30b9\u306e\u7d39\u4ecb<\/a>    <ul class=\"menu_level_1\">      <li class=\"first\">        <a href=\"#i-9\">PyPDF2\u30c1\u30fc\u30c8\u30b7\u30fc\u30c8\uff08\u983b\u51fa\u3059\u308b\u64cd\u4f5c\u306e\u30b3\u30fc\u30c9\u30b5\u30f3\u30d7\u30eb\u96c6\uff09<\/a>      <\/li>      <li>        <a href=\"#i-10\">PyPDF2\u306e\u516c\u5f0f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3092\u8aad\u3082\u3046<\/a>      <\/li>      <li>        <a href=\"#i-11\">PDF\u306e\u4ed5\u69d8\u306b\u3064\u3044\u3066\u7406\u89e3\u3092\u6df1\u3081\u308b<\/a>      <\/li>      <li class=\"last\">        <a href=\"#i-12\">PDF\u306b\u95a2\u3059\u308bPython\u60c5\u5831\u3092\u30ad\u30e3\u30c3\u30c1\u30a2\u30c3\u30d7\u3057\u7d9a\u3051\u308b\u65b9\u6cd5<\/a>      <\/li>    <\/ul>  <\/li><\/ul>\n      \n    <\/div><\/div><h2 class=\"wp-block-heading\" id=\"i-0\">pypdf2\u3068\u306f\uff1fPDF\u3092Python\u3067\u64cd\u4f5c\u3059\u308b\u305f\u3081\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u5fb9\u5e95\u89e3\u8aac<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">pypdf2\u306f\u3001PDF\u3092Python\u3067\u64cd\u4f5c\u3059\u308b\u305f\u3081\u306e\u5f37\u529b\u306a\u30e9\u30a4\u30d6\u30e9\u30ea\u3067\u3059\u3002\u30da\u30fc\u30b8\u306e\u7d50\u5408\u30fb\u5206\u5272\u30fb\u62bd\u51fa\u3001\u30e1\u30bf\u30c7\u30fc\u30bf\u306e\u7de8\u96c6\u306a\u3069\u3001PDF\u306b\u95a2\u3059\u308b\u3055\u307e\u3056\u307e\u306a\u51e6\u7406\u3092\u884c\u3046\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002Pure Python\u3067\u66f8\u304b\u308c\u3066\u3044\u308b\u305f\u3081\u3001PDF\u3092Python\u306e\u30aa\u30d6\u30b8\u30a7\u30af\u30c8\u3068\u3057\u3066\u76f4\u611f\u7684\u306b\u6271\u3046\u3053\u3068\u304c\u53ef\u80fd\u3067\u3059\u3002<\/p>\n\n\n\n<div class=\"wp-block-sgb-message\"><div class=\"memo sng-shadow-0\" style=\"border-radius:0px;background-color:#fff9e6;color:#ffb36b\"><div class=\"memo_ttl dfont\"><span class=\"sng-box-msg__icon\" style=\"background:#ffb36b\"><i class=\"fas fa-pencil-alt\"><\/i><\/span><div class=\"sng-box-msg__title\">\u6ce8\u610f<\/div><\/div><div class=\"sng-box-msg__contents\">\n<p class=\"wp-block-paragraph\">\u3053\u306e\u8a18\u4e8b\u3067\u306fpypdf2 \u30d0\u30fc\u30b8\u30e7\u30f32.0.0\u306b\u3064\u3044\u3066\u89e3\u8aac\u3057\u3066\u3044\u307e\u3059\u3002\u73fe\u884c\u306e\u6700\u65b0\u30d0\u30fc\u30b8\u30e7\u30f3\u306f3.0.0\u3067\u3042\u308a\u3001\u30b3\u30fc\u30c9\u306e\u4e92\u63db\u6027\u304c\u5931\u308f\u308c\u3066\u3044\u308b\u306e\u3067\u3001\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u6642\u306f\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u3057\u3066\u304f\u3060\u3055\u3044<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">pip3 install pypdf2==2.0.0<\/pre>\n<\/div><\/div><\/div>\n\n\n\n<p class=\"wp-block-paragraph\">\u4ee5\u4e0b\u306f\u3001pypdf2\u306e\u57fa\u672c\u7684\u306a\u4f7f\u7528\u4f8b\u3067\u3059\u3002<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">from PyPDF2 import PdfFileWriter, PdfFileReader\n\n# PDF\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3080\ninput_pdf = PdfFileReader(open(\"input.pdf\", \"rb\"))\n\n# \u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3092\u4f5c\u6210\noutput_pdf = PdfFileWriter()\n\n# 1\u30da\u30fc\u30b8\u76ee\u3092\u62bd\u51fa\u3057\u3066\u65b0\u3057\u3044PDF\u306b\u8ffd\u52a0\noutput_pdf.addPage(input_pdf.getPage(0))\n\n# \u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3092\u4fdd\u5b58\nwith open(\"output.pdf\", \"wb\") as f:\n    output_pdf.write(f)<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u306e\u30b3\u30fc\u30c9\u3067\u306f\u3001<code>input.pdf<\/code>\u3068\u3044\u3046\u540d\u524d\u306ePDF\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u307f\u3001\u305d\u306e1\u30da\u30fc\u30b8\u76ee\u3092\u62bd\u51fa\u3057\u3066<code>output.pdf<\/code>\u3068\u3044\u3046\u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u306b\u4fdd\u5b58\u3057\u3066\u3044\u307e\u3059\u3002\u30da\u30fc\u30b8\u306e\u62bd\u51fa\u306f\u3001<code>getPage()<\/code>\u30e1\u30bd\u30c3\u30c9\u3092\u4f7f\u3063\u3066\u884c\u3044\u307e\u3059\u3002\u30da\u30fc\u30b8\u756a\u53f7\u306f0\u304b\u3089\u59cb\u307e\u308b\u3053\u3068\u306b\u6ce8\u610f\u3057\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">pypdf2\u306f\u3001PyPDF4\u3084pdfrw\u306a\u3069\u306e\u6d3e\u751f\u30e9\u30a4\u30d6\u30e9\u30ea\u3082\u5b58\u5728\u3057\u307e\u3059\u3002\u3053\u308c\u3089\u306f\u3001pypdf2\u3092\u30d9\u30fc\u30b9\u306b\u958b\u767a\u3055\u308c\u305f\u5225\u30d0\u30fc\u30b8\u30e7\u30f3\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u3067\u3001\u4e00\u90e8\u306e\u6a5f\u80fd\u3084\u5bfe\u5fdcPython\u30d0\u30fc\u30b8\u30e7\u30f3\u304c\u7570\u306a\u308a\u307e\u3059\u3002\u7528\u9014\u306b\u5fdc\u3058\u3066\u9069\u5207\u306a\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u9078\u629e\u3059\u308b\u5fc5\u8981\u304c\u3042\u308b\u3067\u3057\u3087\u3046\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">PDF\u51e6\u7406\u306e\u81ea\u52d5\u5316\u3084\u52b9\u7387\u5316\u306b\u5f79\u7acb\u3064\u30c4\u30fc\u30eb\u3068\u3057\u3066\u3001pypdf2\u306f\u5b66\u8853\u5206\u91ce\u3067\u3082\u6d3b\u7528\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u8ad6\u6587\u306e\u88ab\u5f15\u7528\u95a2\u4fc2\u306e\u5206\u6790\u3084PDF\u304b\u3089\u306e\u60c5\u5831\u62bd\u51fa\u306a\u3069\u3001\u7814\u7a76\u6d3b\u52d5\u306e\u69d8\u3005\u306a\u5834\u9762\u3067\u7528\u3044\u3089\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u305f\u3060\u3057\u3001\u5229\u7528\u306b\u969b\u3057\u3066\u306f\u3044\u304f\u3064\u304b\u6ce8\u610f\u70b9\u304c\u3042\u308a\u307e\u3059\u3002\u65e5\u672c\u8a9e\u3092\u542b\u3080PDF\u3067\u306f\u3001\u30c6\u30ad\u30b9\u30c8\u62bd\u51fa\u7d50\u679c\u304c\u6587\u5b57\u5316\u3051\u3059\u308b\u3053\u3068\u304c\u3042\u308a\u307e\u3059\u3002\u307e\u305f\u3001\u6697\u53f7\u5316\u3055\u308c\u305fPDF\u306e\u4e2d\u306b\u306f\u3001\u30d1\u30b9\u30ef\u30fc\u30c9\u304c\u5fc5\u8981\u306b\u306a\u308b\u5834\u5408\u3082\u3042\u308a\u307e\u3059\u3002\u30bb\u30ad\u30e5\u30ea\u30c6\u30a3\u9762\u3078\u306e\u8003\u616e\u3082\u5fc5\u8981\u3067\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4ee5\u4e0b\u306f\u3001pypdf2\u3092\u4f7f\u3063\u3066PDF\u306e\u30e1\u30bf\u30c7\u30fc\u30bf\u3092\u7de8\u96c6\u3059\u308b\u4f8b\u3067\u3059\u3002<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">from PyPDF2 import PdfFileWriter, PdfFileReader\n\n# PDF\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3080\ninput_pdf = PdfFileReader(open(\"input.pdf\", \"rb\"))\n\n# \u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3092\u4f5c\u6210\noutput_pdf = PdfFileWriter()\n\n# \u30e1\u30bf\u30c7\u30fc\u30bf\u3092\u7de8\u96c6\ninfo_dict = output_pdf._info.getObject()\ninfo_dict.update({\n    '\/Title': '\u30b5\u30f3\u30d7\u30ebPDF',\n    '\/Author': '\u5c71\u7530\u592a\u90ce', \n    '\/Subject': 'pypdf2\u306e\u30c7\u30e2\u30f3\u30b9\u30c8\u30ec\u30fc\u30b7\u30e7\u30f3',\n})\n\n# \u65e2\u5b58\u306ePDF\u306e\u5185\u5bb9\u3092\u65b0\u3057\u3044PDF\u306b\u30b3\u30d4\u30fc\nnum_pages = input_pdf.getNumPages()\nfor i in range(num_pages):\n    output_pdf.addPage(input_pdf.getPage(i))\n\n# \u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3092\u4fdd\u5b58  \nwith open(\"output_meta.pdf\", \"wb\") as f:\n    output_pdf.write(f)<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u306e\u3088\u3046\u306b\u3001<code>PdfFileWriter<\/code>\u30af\u30e9\u30b9\u306e<code>_info<\/code>\u5c5e\u6027\u3092\u901a\u3058\u3066\u3001PDF\u306e\u30e1\u30bf\u30c7\u30fc\u30bf\u3092\u81ea\u7531\u306b\u7de8\u96c6\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4ee5\u4e0a\u3001pypdf2\u306f\u3001PDF\u3092Python\u3067\u64cd\u4f5c\u3059\u308b\u305f\u3081\u306e\u5f37\u529b\u304b\u3064\u67d4\u8edf\u306a\u30c4\u30fc\u30eb\u3067\u3059\u3002\u521d\u5fc3\u8005\u3067\u3082\u76f4\u611f\u7684\u306b\u4f7f\u3048\u308b\u30b7\u30f3\u30d7\u30eb\u306a\u30a4\u30f3\u30bf\u30fc\u30d5\u30a7\u30fc\u30b9\u304c\u7279\u5fb4\u3067\u3059\u3002PDF\u306e\u52a0\u5de5\u3084\u81ea\u52d5\u51e6\u7406\u306e\u30cb\u30fc\u30ba\u304c\u3042\u308b\u5834\u5408\u306f\u3001\u305c\u3072\u691c\u8a0e\u3057\u3066\u307f\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"i-1\">pypdf2\u306e\u57fa\u672c\u7684\u306a\u4f7f\u3044\u65b9\u3092\u30de\u30b9\u30bf\u30fc\u3057\u3088\u3046<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">pypdf2\u3092\u4f7f\u3044\u3053\u306a\u3059\u306b\u306f\u3001<code>PdfFileReader<\/code>\u3068<code>PdfFileWriter<\/code>\u306e2\u3064\u306e\u30af\u30e9\u30b9\u3092\u7406\u89e3\u3059\u308b\u3053\u3068\u304c\u91cd\u8981\u3067\u3059\u3002<code>PdfFileReader<\/code>\u306f\u65e2\u5b58\u306ePDF\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3080\u305f\u3081\u306e\u30af\u30e9\u30b9\u3001<code>PdfFileWriter<\/code>\u306f\u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3092\u4f5c\u6210\u30fb\u7de8\u96c6\u3059\u308b\u305f\u3081\u306e\u30af\u30e9\u30b9\u3067\u3059\u3002\u3053\u306e2\u3064\u3092\u7d44\u307f\u5408\u308f\u305b\u308b\u3053\u3068\u3067\u3001PDF\u306e\u69d8\u3005\u306a\u64cd\u4f5c\u304c\u53ef\u80fd\u306b\u306a\u308a\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u307e\u305a\u306f\u3001PDF\u30d5\u30a1\u30a4\u30eb\u306e\u8aad\u307f\u8fbc\u307f\u3068\u66f8\u304d\u51fa\u3057\u306e\u57fa\u672c\u304b\u3089\u898b\u3066\u3044\u304d\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">from PyPDF2 import PdfFileWriter, PdfFileReader\n\n# PDF\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3080\nreader = PdfFileReader(\"input.pdf\")\n\n# \u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3092\u4f5c\u6210\nwriter = PdfFileWriter()\n\n# \u65e2\u5b58\u306ePDF\u306e\u5185\u5bb9\u3092\u65b0\u3057\u3044PDF\u306b\u30b3\u30d4\u30fc\nnum_pages = reader.getNumPages()\nfor i in range(num_pages):\n    writer.addPage(reader.getPage(i))\n\n# \u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3092\u4fdd\u5b58\nwith open(\"output.pdf\", \"wb\") as f:\n    writer.write(f)<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u306e\u30b3\u30fc\u30c9\u3067\u306f\u3001<code>PdfFileReader<\/code>\u3067<code>input.pdf<\/code>\u3092\u8aad\u307f\u8fbc\u307f\u3001<code>PdfFileWriter<\/code>\u3067\u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3092\u4f5c\u6210\u3057\u3066\u3044\u307e\u3059\u3002<code>getNumPages()<\/code>\u30e1\u30bd\u30c3\u30c9\u3067PDF\u306e\u30da\u30fc\u30b8\u6570\u3092\u53d6\u5f97\u3057\u3001<code>getPage()<\/code>\u30e1\u30bd\u30c3\u30c9\u3067\u5404\u30da\u30fc\u30b8\u3092\u53d6\u5f97\u3057\u307e\u3059\u3002\u53d6\u5f97\u3057\u305f\u30da\u30fc\u30b8\u306f\u3001<code>addPage()<\/code>\u30e1\u30bd\u30c3\u30c9\u3067\u65b0\u3057\u3044PDF\u306b\u8ffd\u52a0\u3057\u3066\u3044\u304d\u307e\u3059\u3002\u6700\u5f8c\u306b\u3001<code>write()<\/code>\u30e1\u30bd\u30c3\u30c9\u3067\u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3092\u4fdd\u5b58\u3057\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u6b21\u306b\u3001\u30da\u30fc\u30b8\u306e\u62bd\u51fa\u3068\u7d50\u5408\u306e\u65b9\u6cd5\u3092\u898b\u3066\u3044\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">from PyPDF2 import PdfFileWriter, PdfFileReader\n\n# PDF\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3080\nreader1 = PdfFileReader(\"input1.pdf\")\nreader2 = PdfFileReader(\"input2.pdf\")\n\n# \u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3092\u4f5c\u6210\nwriter = PdfFileWriter()\n\n# input1.pdf\u306e1\u30da\u30fc\u30b8\u76ee\u3092\u62bd\u51fa\npage1 = reader1.getPage(0)\nwriter.addPage(page1)\n\n# input2.pdf\u306e\u5168\u30da\u30fc\u30b8\u3092\u8ffd\u52a0\nnum_pages = reader2.getNumPages()\nfor i in range(num_pages):\n    writer.addPage(reader2.getPage(i))\n\n# \u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3092\u4fdd\u5b58\nwith open(\"output_merged.pdf\", \"wb\") as f:\n    writer.write(f)<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u306e\u30b3\u30fc\u30c9\u3067\u306f\u3001<code>input1.pdf<\/code>\u306e1\u30da\u30fc\u30b8\u76ee\u3092\u62bd\u51fa\u3057\u3001<code>input2.pdf<\/code>\u306e\u5168\u30da\u30fc\u30b8\u3092\u8ffd\u52a0\u3059\u308b\u3053\u3068\u3067\u30012\u3064\u306ePDF\u3092\u7d50\u5408\u3057\u3066\u3044\u307e\u3059\u3002<code>getPage()<\/code>\u30e1\u30bd\u30c3\u30c9\u3067\u30da\u30fc\u30b8\u3092\u53d6\u5f97\u3057\u3001<code>addPage()<\/code>\u30e1\u30bd\u30c3\u30c9\u3067\u65b0\u3057\u3044PDF\u306b\u8ffd\u52a0\u3057\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">PDF\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u62bd\u51fa\u3059\u308b\u306b\u306f\u3001<code>extractText()<\/code>\u30e1\u30bd\u30c3\u30c9\u3092\u4f7f\u3044\u307e\u3059\u3002<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">from PyPDF2 import PdfFileReader\n\n# PDF\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3080\nreader = PdfFileReader(\"input.pdf\")\n\n# 1\u30da\u30fc\u30b8\u76ee\u306e\u30c6\u30ad\u30b9\u30c8\u3092\u62bd\u51fa\npage = reader.getPage(0)\ntext = page.extractText()\n\nprint(text)<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u305f\u3060\u3057\u3001PDF\u306e\u30ec\u30a4\u30a2\u30a6\u30c8\u306b\u3088\u3063\u3066\u306f\u3001\u304d\u308c\u3044\u306b\u30c6\u30ad\u30b9\u30c8\u304c\u62bd\u51fa\u3067\u304d\u306a\u3044\u3053\u3068\u304c\u3042\u308a\u307e\u3059\u3002\u7279\u306b\u3001\u753b\u50cf\u3084\u30b0\u30e9\u30d5\u5185\u306e\u30c6\u30ad\u30b9\u30c8\u306f\u62bd\u51fa\u3067\u304d\u307e\u305b\u3093\u3002\u305d\u306e\u5834\u5408\u306f\u3001OCR\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u4f7f\u3046\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u6700\u5f8c\u306b\u3001PDF\u3078\u306e\u52a0\u5de5\u65b9\u6cd5\u306e\u4e00\u3064\u3068\u3057\u3066\u3001\u900f\u304b\u3057\u306e\u8ffd\u52a0\u3092\u898b\u3066\u3044\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">from PyPDF2 import PdfFileWriter, PdfFileReader\nfrom reportlab.pdfgen import canvas\nfrom io import BytesIO\n\n# \u900f\u304b\u3057\u3092\u4f5c\u6210\npacket = BytesIO()\ncan = canvas.Canvas(packet)\ncan.drawString(10, 10, \"Sample Watermark\")\ncan.save()\npacket.seek(0)\nwatermark = PdfFileReader(packet)\n\n# PDF\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3080\nreader = PdfFileReader(\"input.pdf\")\n\n# \u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3092\u4f5c\u6210\nwriter = PdfFileWriter()\n\n# \u5404\u30da\u30fc\u30b8\u306b\u900f\u304b\u3057\u3092\u8ffd\u52a0\nnum_pages = reader.getNumPages()\nfor i in range(num_pages):\n    page = reader.getPage(i)\n    page.mergePage(watermark.getPage(0))\n    writer.addPage(page)\n\n# \u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3092\u4fdd\u5b58\nwith open(\"output_watermarked.pdf\", \"wb\") as f:\n    writer.write(f)<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u306e\u30b3\u30fc\u30c9\u3067\u306f\u3001<code>reportlab<\/code>\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u4f7f\u3063\u3066\u900f\u304b\u3057\u3092\u4f5c\u6210\u3057\u3001\u5404\u30da\u30fc\u30b8\u306b\u305d\u306e\u900f\u304b\u3057\u3092\u91cd\u306d\u3066\u3044\u307e\u3059\u3002<code>mergePage()<\/code>\u30e1\u30bd\u30c3\u30c9\u3092\u4f7f\u3046\u3053\u3068\u3067\u3001\u900f\u304b\u3057\u3092\u30da\u30fc\u30b8\u4e0a\u306b\u63cf\u753b\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4ee5\u4e0a\u304c\u3001pypdf2\u306e\u57fa\u672c\u7684\u306a\u4f7f\u3044\u65b9\u306e\u6982\u8981\u3067\u3059\u3002\u30da\u30fc\u30b8\u306e\u64cd\u4f5c\u3001\u30c6\u30ad\u30b9\u30c8\u62bd\u51fa\u3001\u52a0\u5de5\u306a\u3069\u3001PDF\u306b\u95a2\u3059\u308b\u69d8\u3005\u306a\u30bf\u30b9\u30af\u3092Python\u3067\u81ea\u52d5\u5316\u3067\u304d\u307e\u3059\u3002\u305f\u3060\u3057\u3001\u30da\u30fc\u30b8\u756a\u53f7\u304c0\u304b\u3089\u59cb\u307e\u308b\u3053\u3068\u3084\u3001\u65e5\u672c\u8a9e\u3067\u306e\u6587\u5b57\u5316\u3051\u306a\u3069\u3001\u521d\u5fc3\u8005\u304c\u3064\u307e\u305a\u304d\u3084\u3059\u3044\u30dd\u30a4\u30f3\u30c8\u3082\u3042\u308b\u306e\u3067\u6ce8\u610f\u304c\u5fc5\u8981\u3067\u3059\u3002\u30b3\u30fc\u30c9\u3092\u66f8\u304f\u969b\u306f\u3001\u3053\u308c\u3089\u306e\u70b9\u306b\u6c17\u3092\u3064\u3051\u306a\u304c\u3089\u3001\u67d4\u8edf\u306b\u5bfe\u5fdc\u3057\u3066\u3044\u304d\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"i-2\">pypdf2\u306e\u5b9f\u8df5\u7684\u306a\u6d3b\u7528\u4f8b5\u9078<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">pypdf2\u306f\u3001PDF\u306b\u95a2\u3059\u308b\u69d8\u3005\u306a\u5b9f\u8df5\u7684\u306a\u30bf\u30b9\u30af\u3092\u81ea\u52d5\u5316\u3059\u308b\u306e\u306b\u5f79\u7acb\u3061\u307e\u3059\u3002\u3053\u3053\u3067\u306f\u3001pypdf2\u3092\u4f7f\u3063\u305f5\u3064\u306e\u5b9f\u8df5\u7684\u306a\u6d3b\u7528\u4f8b\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"i-3\">\u5927\u91cf\u306ePDF\u30d5\u30a1\u30a4\u30eb\u3092\u4e00\u62ec\u51e6\u7406\u3059\u308b<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u6700\u521d\u306e\u6d3b\u7528\u4f8b\u306f\u3001\u5927\u91cf\u306ePDF\u30d5\u30a1\u30a4\u30eb\u3092\u4e00\u62ec\u51e6\u7406\u3059\u308b\u65b9\u6cd5\u3067\u3059\u3002<code>glob<\/code>\u30e2\u30b8\u30e5\u30fc\u30eb\u3092\u4f7f\u3063\u3066\u30d5\u30a9\u30eb\u30c0\u5185\u306ePDF\u30d5\u30a1\u30a4\u30eb\u3092\u53d6\u5f97\u3057\u3001PyPDF2\u3092\u4f7f\u3063\u3066\u5404PDF\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3093\u3067\u5fc5\u8981\u306a\u51e6\u7406\u3092\u884c\u3044\u307e\u3059\u3002\u51e6\u7406\u7d50\u679c\u306f\u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3068\u3057\u3066\u4fdd\u5b58\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">import os\nimport glob\nfrom PyPDF2 import PdfFileWriter, PdfFileReader\n\n# PDF\u30d5\u30a1\u30a4\u30eb\u304c\u683c\u7d0d\u3055\u308c\u305f\u30d5\u30a9\u30eb\u30c0\u306e\u30d1\u30b9\npdf_dir = \"path\/to\/pdf\/directory\"\n\n# \u51e6\u7406\u5f8c\u306ePDF\u3092\u4fdd\u5b58\u3059\u308b\u30d5\u30a9\u30eb\u30c0\u3092\u4f5c\u6210\noutput_dir = \"path\/to\/output\/directory\"\nos.makedirs(output_dir, exist_ok=True)\n\n# \u30d5\u30a9\u30eb\u30c0\u5185\u306ePDF\u30d5\u30a1\u30a4\u30eb\u3092\u53d6\u5f97\npdf_files = glob.glob(os.path.join(pdf_dir, \"*.pdf\"))\n\nfor pdf_file in pdf_files:\n    # PDF\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3080\n    with open(pdf_file, \"rb\") as f:\n        reader = PdfFileReader(f)\n        writer = PdfFileWriter()\n\n        # PDF\u306b\u5bfe\u3057\u3066\u5fc5\u8981\u306a\u51e6\u7406\u3092\u884c\u3046\uff08\u4f8b\uff1a1\u30da\u30fc\u30b8\u76ee\u306e\u307f\u62bd\u51fa\uff09\n        page = reader.getPage(0)\n        writer.addPage(page)\n\n        # \u51e6\u7406\u5f8c\u306ePDF\u3092\u4fdd\u5b58\n        output_path = os.path.join(output_dir, os.path.basename(pdf_file))\n        with open(output_path, \"wb\") as output:\n            writer.write(output)<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u306e\u30b3\u30fc\u30c9\u3067\u306f\u3001<code>pdf_dir<\/code>\u3067\u6307\u5b9a\u3057\u305f\u30d5\u30a9\u30eb\u30c0\u5185\u306e\u5168\u3066\u306ePDF\u30d5\u30a1\u30a4\u30eb\u3092\u51e6\u7406\u3057\u3001\u5404PDF\u306e1\u30da\u30fc\u30b8\u76ee\u306e\u307f\u3092\u62bd\u51fa\u3057\u3066\u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u3068\u3057\u3066\u4fdd\u5b58\u3057\u3066\u3044\u307e\u3059\u3002\u5fc5\u8981\u306b\u5fdc\u3058\u3066\u3001PDF\u306b\u5bfe\u3059\u308b\u51e6\u7406\u306e\u5185\u5bb9\u3092\u5909\u66f4\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"i-4\">PDF\u304b\u3089\u30c7\u30fc\u30bf\u3092\u62bd\u51fa\u3057\u3066Excel\u306b\u66f8\u304d\u51fa\u3059<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u6b21\u306e\u6d3b\u7528\u4f8b\u306f\u3001PDF\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u30c7\u30fc\u30bf\u3092\u62bd\u51fa\u3057\u3001Excel\u30d5\u30a1\u30a4\u30eb\u306b\u66f8\u304d\u51fa\u3059\u65b9\u6cd5\u3067\u3059\u3002PyPDF2\u3092\u4f7f\u3063\u3066PDF\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u62bd\u51fa\u3057\u3001\u6b63\u898f\u8868\u73fe\u3092\u4f7f\u3063\u3066\u5fc5\u8981\u306a\u60c5\u5831\u3092\u53d6\u308a\u51fa\u3057\u307e\u3059\u3002\u53d6\u308a\u51fa\u3057\u305f\u30c7\u30fc\u30bf\u306f\u3001<code>openpyxl<\/code>\u3092\u4f7f\u3063\u3066Excel\u30d5\u30a1\u30a4\u30eb\u306b\u66f8\u304d\u8fbc\u307f\u307e\u3059\u3002<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">import re\nfrom PyPDF2 import PdfFileReader\nfrom openpyxl import Workbook\n\n# PDF\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3080\nwith open(\"input.pdf\", \"rb\") as f:\n    reader = PdfFileReader(f)\n    page = reader.getPage(0)\n    text = page.extractText()\n\n# \u6b63\u898f\u8868\u73fe\u3092\u4f7f\u3063\u3066\u30c6\u30ad\u30b9\u30c8\u304b\u3089\u30c7\u30fc\u30bf\u3092\u62bd\u51fa\npattern = r\"(\\d{4}\u5e74\\d{1,2}\u6708\\d{1,2}\u65e5)\"\nmatches = re.findall(pattern, text)\n\n# Excel\u30d5\u30a1\u30a4\u30eb\u3092\u4f5c\u6210\nwb = Workbook()\nws = wb.active\n\n# \u62bd\u51fa\u3057\u305f\u30c7\u30fc\u30bf\u3092Excel\u306b\u66f8\u304d\u8fbc\u3080\nfor i, match in enumerate(matches, start=1):\n    ws.cell(row=i, column=1, value=match)\n\n# Excel\u30d5\u30a1\u30a4\u30eb\u3092\u4fdd\u5b58\nwb.save(\"output.xlsx\")<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u306e\u30b3\u30fc\u30c9\u3067\u306f\u3001PDF\u304b\u3089\u65e5\u4ed8\uff08\u4f8b\uff1a2023\u5e744\u67081\u65e5\uff09\u3092\u62bd\u51fa\u3057\u3001Excel\u30d5\u30a1\u30a4\u30eb\u306b\u66f8\u304d\u51fa\u3057\u3066\u3044\u307e\u3059\u3002\u6b63\u898f\u8868\u73fe\u306e\u30d1\u30bf\u30fc\u30f3\u3092\u5909\u66f4\u3059\u308b\u3053\u3068\u3067\u3001\u4ed6\u306e\u5f62\u5f0f\u306e\u30c7\u30fc\u30bf\u3082\u62bd\u51fa\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"i-5\">\u8907\u6570\u306ePDF\u3092\u7d50\u5408\u3057\u30661\u3064\u306e\u30d5\u30a1\u30a4\u30eb\u306b\u307e\u3068\u3081\u308b<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">3\u3064\u76ee\u306e\u6d3b\u7528\u4f8b\u306f\u3001\u8907\u6570\u306ePDF\u30d5\u30a1\u30a4\u30eb\u3092\u7d50\u5408\u3057\u30661\u3064\u306e\u30d5\u30a1\u30a4\u30eb\u306b\u307e\u3068\u3081\u308b\u65b9\u6cd5\u3067\u3059\u3002PyPDF2\u306e<code>PdfFileMerger<\/code>\u30af\u30e9\u30b9\u3092\u4f7f\u3046\u3053\u3068\u3067\u3001\u7c21\u5358\u306bPDF\u3092\u7d50\u5408\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">from PyPDF2 import PdfFileMerger\n\n# PdfFileMerger\u30aa\u30d6\u30b8\u30a7\u30af\u30c8\u3092\u4f5c\u6210\nmerger = PdfFileMerger()\n\n# \u7d50\u5408\u3059\u308bPDF\u30d5\u30a1\u30a4\u30eb\u3092\u8ffd\u52a0\nmerger.append(\"file1.pdf\")\nmerger.append(\"file2.pdf\")\nmerger.append(\"file3.pdf\")\n\n# \u7d50\u5408\u3057\u305fPDF\u3092\u4fdd\u5b58\nmerger.write(\"merged_output.pdf\")\nmerger.close()<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u306e\u30b3\u30fc\u30c9\u3067\u306f\u3001<code>file1.pdf<\/code>\u3001<code>file2.pdf<\/code>\u3001<code>file3.pdf<\/code>\u306e3\u3064\u306ePDF\u30d5\u30a1\u30a4\u30eb\u3092\u7d50\u5408\u3057\u3001<code>merged_output.pdf<\/code>\u3068\u3044\u3046\u540d\u524d\u3067\u4fdd\u5b58\u3057\u3066\u3044\u307e\u3059\u3002\u7d50\u5408\u3059\u308bPDF\u30d5\u30a1\u30a4\u30eb\u306e\u6570\u3084\u540d\u524d\u306f\u81ea\u7531\u306b\u5909\u66f4\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"i-6\">PDF\u3092\u30b9\u30ad\u30e3\u30f3\u3057\u3066OCR\u51e6\u7406\u3092\u884c\u3046<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">4\u3064\u76ee\u306e\u6d3b\u7528\u4f8b\u306f\u3001\u30b9\u30ad\u30e3\u30f3\u3057\u305fPDF\u306b\u5bfe\u3057\u3066OCR\uff08\u5149\u5b66\u6587\u5b57\u8a8d\u8b58\uff09\u51e6\u7406\u3092\u884c\u3046\u65b9\u6cd5\u3067\u3059\u3002<code>pdf2image<\/code>\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u4f7f\u3063\u3066PDF\u3092\u753b\u50cf\u306b\u5909\u63db\u3057\u3001<code>pytesseract<\/code>\u3092\u4f7f\u3063\u3066\u753b\u50cf\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u62bd\u51fa\u3057\u307e\u3059\u3002\u62bd\u51fa\u3057\u305f\u30c6\u30ad\u30b9\u30c8\u306f\u3001\u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u306b\u66f8\u304d\u8fbc\u3080\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">from pdf2image import convert_from_path\nfrom PyPDF2 import PdfFileWriter, PdfFileReader\nfrom io import BytesIO\nfrom PIL import Image\nimport pytesseract\n\n# PDF\u30d5\u30a1\u30a4\u30eb\u3092\u753b\u50cf\u306b\u5909\u63db\nimages = convert_from_path(\"scanned.pdf\")\n\n# \u753b\u50cf\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u3092\u62bd\u51fa\ntext = \"\"\nfor img in images:\n    text += pytesseract.image_to_string(img, lang=\"jpn\")\n\n# \u62bd\u51fa\u3057\u305f\u30c6\u30ad\u30b9\u30c8\u3092\u65b0\u3057\u3044PDF\u306b\u66f8\u304d\u8fbc\u3080\npacket = BytesIO()\npacket.write(text.encode(\"utf-8\"))\npacket.seek(0)\nnew_pdf = PdfFileReader(packet)\n\noutput = PdfFileWriter()\noutput.addPage(new_pdf.getPage(0))\n\nwith open(\"output_ocr.pdf\", \"wb\") as f:\n    output.write(f)<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u306e\u30b3\u30fc\u30c9\u3067\u306f\u3001<code>scanned.pdf<\/code>\u3068\u3044\u3046\u30b9\u30ad\u30e3\u30f3\u3057\u305fPDF\u30d5\u30a1\u30a4\u30eb\u304b\u3089\u753b\u50cf\u3092\u53d6\u5f97\u3057\u3001<code>pytesseract<\/code>\u3092\u4f7f\u3063\u3066\u65e5\u672c\u8a9e\u306e\u30c6\u30ad\u30b9\u30c8\u3092\u62bd\u51fa\u3057\u3066\u3044\u307e\u3059\u3002\u62bd\u51fa\u3057\u305f\u30c6\u30ad\u30b9\u30c8\u306f\u3001\u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb<code>output_ocr.pdf<\/code>\u306b\u66f8\u304d\u8fbc\u307e\u308c\u307e\u3059\u3002OCR\u306e\u7cbe\u5ea6\u3092\u4e0a\u3052\u308b\u306b\u306f\u3001\u753b\u50cf\u306e\u524d\u51e6\u7406\uff08\u4e8c\u5024\u5316\u3001\u30ce\u30a4\u30ba\u9664\u53bb\u306a\u3069\uff09\u304c\u91cd\u8981\u3067\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"i-7\">PyPDF2\u3092\u4f7f\u3063\u305f\u8acb\u6c42\u66f8\u306e\u81ea\u52d5\u51e6\u7406\u30b7\u30b9\u30c6\u30e0\u3092\u4f5c\u308b<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u6700\u5f8c\u306e\u6d3b\u7528\u4f8b\u306f\u3001PyPDF2\u3092\u4f7f\u3063\u3066\u8acb\u6c42\u66f8\u306e\u81ea\u52d5\u51e6\u7406\u30b7\u30b9\u30c6\u30e0\u3092\u4f5c\u308b\u65b9\u6cd5\u3067\u3059\u3002\u8acb\u6c42\u66f8\u306ePDF\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u30c7\u30fc\u30bf\u3092\u62bd\u51fa\u3057\u3001\u6b63\u898f\u8868\u73fe\u3092\u4f7f\u3063\u3066\u8acb\u6c42\u91d1\u984d\u3084\u652f\u6255\u671f\u65e5\u306a\u3069\u306e\u60c5\u5831\u3092\u53d6\u308a\u51fa\u3057\u307e\u3059\u3002\u53d6\u308a\u51fa\u3057\u305f\u60c5\u5831\u306f\u3001\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u306b\u683c\u7d0d\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">import re\nimport sqlite3\nfrom PyPDF2 import PdfFileReader\n\n# PDF\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3080\nwith open(\"invoice.pdf\", \"rb\") as f:\n    reader = PdfFileReader(f)\n    page = reader.getPage(0)\n    text = page.extractText()\n\n# \u6b63\u898f\u8868\u73fe\u3092\u4f7f\u3063\u3066\u8acb\u6c42\u66f8\u306e\u30c7\u30fc\u30bf\u3092\u62bd\u51fa\namount_pattern = r\"\u8acb\u6c42\u91d1\u984d\uff1a(\\d+)\u5186\"\ndue_date_pattern = r\"\u652f\u6255\u671f\u65e5\uff1a(\\d{4}\u5e74\\d{1,2}\u6708\\d{1,2}\u65e5)\"\n\namount = re.search(amount_pattern, text).group(1)\ndue_date = re.search(due_date_pattern, text).group(1)\n\n# \u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u306b\u63a5\u7d9a\nconn = sqlite3.connect(\"invoice.db\")\nc = conn.cursor()\n\n# \u62bd\u51fa\u3057\u305f\u30c7\u30fc\u30bf\u3092\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u306b\u683c\u7d0d\nc.execute(\"INSERT INTO invoices (amount, due_date) VALUES (?, ?)\", (amount, due_date))\nconn.commit()\nconn.close()<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u306e\u30b3\u30fc\u30c9\u3067\u306f\u3001<code>invoice.pdf<\/code>\u3068\u3044\u3046\u8acb\u6c42\u66f8\u306ePDF\u30d5\u30a1\u30a4\u30eb\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u30c7\u30fc\u30bf\u3092\u62bd\u51fa\u3057\u3001\u6b63\u898f\u8868\u73fe\u3092\u4f7f\u3063\u3066\u8acb\u6c42\u91d1\u984d\u3068\u652f\u6255\u671f\u65e5\u3092\u53d6\u308a\u51fa\u3057\u3066\u3044\u307e\u3059\u3002\u53d6\u308a\u51fa\u3057\u305f\u30c7\u30fc\u30bf\u306f\u3001SQLite\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u306e<code>invoices<\/code>\u30c6\u30fc\u30d6\u30eb\u306b\u683c\u7d0d\u3055\u308c\u307e\u3059\u3002\u8acb\u6c42\u66f8\u306e\u5f62\u5f0f\u306b\u5408\u308f\u305b\u3066\u3001\u6b63\u898f\u8868\u73fe\u306e\u30d1\u30bf\u30fc\u30f3\u3092\u9069\u5b9c\u5909\u66f4\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4ee5\u4e0a\u3001pypdf2\u3092\u4f7f\u3063\u305f5\u3064\u306e\u5b9f\u8df5\u7684\u306a\u6d3b\u7528\u4f8b\u3092\u7d39\u4ecb\u3057\u307e\u3057\u305f\u3002\u3053\u308c\u3089\u306e\u4f8b\u3092\u53c2\u8003\u306b\u3001PDF\u306e\u4e00\u62ec\u51e6\u7406\u3084\u30c7\u30fc\u30bf\u62bd\u51fa\u3001OCR\u51e6\u7406\u306a\u3069\u3001\u69d8\u3005\u306a\u5834\u9762\u3067pypdf2\u3092\u6d3b\u7528\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u4ed6\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u3068\u7d44\u307f\u5408\u308f\u305b\u308b\u3053\u3068\u3067\u3001\u3088\u308a\u9ad8\u5ea6\u306a\u51e6\u7406\u3082\u5b9f\u73fe\u3067\u304d\u308b\u3067\u3057\u3087\u3046\u3002\u305c\u3072\u3001\u696d\u52d9\u306e\u81ea\u52d5\u5316\u3084\u52b9\u7387\u5316\u306bpypdf2\u3092\u5f79\u7acb\u3066\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"i-8\">pypdf2\u306e\u4f7f\u3044\u65b9\u307e\u3068\u3081\uff06\u767a\u5c55\u7684\u306a\u5b66\u7fd2\u30ea\u30bd\u30fc\u30b9\u306e\u7d39\u4ecb<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u308c\u307e\u3067\u3001pypdf2\u306e\u57fa\u672c\u7684\u306a\u4f7f\u3044\u65b9\u304b\u3089\u5b9f\u8df5\u7684\u306a\u6d3b\u7528\u4f8b\u307e\u3067\u3001\u69d8\u3005\u306a\u5074\u9762\u3092\u898b\u3066\u304d\u307e\u3057\u305f\u3002\u3053\u3053\u3067\u306f\u3001pypdf2\u3092\u4f7f\u3046\u4e0a\u3067\u62bc\u3055\u3048\u3066\u304a\u304f\u3079\u304d\u30dd\u30a4\u30f3\u30c8\u3092\u6539\u3081\u3066\u6574\u7406\u3057\u3001\u3055\u3089\u306a\u308b\u30b9\u30ad\u30eb\u30a2\u30c3\u30d7\u306b\u5f79\u7acb\u3064\u5b66\u7fd2\u30ea\u30bd\u30fc\u30b9\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"i-9\">PyPDF2\u30c1\u30fc\u30c8\u30b7\u30fc\u30c8\uff08\u983b\u51fa\u3059\u308b\u64cd\u4f5c\u306e\u30b3\u30fc\u30c9\u30b5\u30f3\u30d7\u30eb\u96c6\uff09<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">pypdf2\u3092\u4f7f\u3046\u969b\u306b\u983b\u7e41\u306b\u4f7f\u3046\u64cd\u4f5c\u3092\u30b3\u30fc\u30c9\u30b5\u30f3\u30d7\u30eb\u3068\u3068\u3082\u306b\u307e\u3068\u3081\u307e\u3057\u305f\u3002\u5fc5\u8981\u306a\u6642\u306b\u53c2\u7167\u3067\u304d\u308b\u3088\u3046\u306b\u3057\u3066\u304a\u304f\u3068\u4fbf\u5229\u3067\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">PDF\u30d5\u30a1\u30a4\u30eb\u306e\u8aad\u307f\u8fbc\u307f<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">from PyPDF2 import PdfFileReader\n\nwith open(\"input.pdf\", \"rb\") as f:\n    reader = PdfFileReader(f)<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u30da\u30fc\u30b8\u6570\u306e\u53d6\u5f97<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">num_pages = reader.getNumPages()<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u6307\u5b9a\u3057\u305f\u30da\u30fc\u30b8\u306e\u53d6\u5f97<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">page = reader.getPage(0)  # 1\u30da\u30fc\u30b8\u76ee\u3092\u53d6\u5f97<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u30c6\u30ad\u30b9\u30c8\u306e\u62bd\u51fa<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">text = page.extractText()<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u65b0\u3057\u3044PDF\u30d5\u30a1\u30a4\u30eb\u306e\u4f5c\u6210\u3068\u4fdd\u5b58<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">from PyPDF2 import PdfFileWriter\n\nwriter = PdfFileWriter()\nwriter.addPage(page)\n\nwith open(\"output.pdf\", \"wb\") as f:\n    writer.write(f)<\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u30da\u30fc\u30b8\u306e\u7d50\u5408<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">from PyPDF2 import PdfFileMerger\n\nmerger = PdfFileMerger()\nmerger.append(\"file1.pdf\")\nmerger.append(\"file2.pdf\")\nmerger.write(\"merged.pdf\")\nmerger.close()<\/pre>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"i-10\">PyPDF2\u306e\u516c\u5f0f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3092\u8aad\u3082\u3046<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">pypdf2\u306e\u4f7f\u3044\u65b9\u3092\u3088\u308a\u6df1\u304f\u7406\u89e3\u3059\u308b\u306b\u306f\u3001\u516c\u5f0f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3092\u53c2\u7167\u3059\u308b\u3053\u3068\u304c\u6b20\u304b\u305b\u307e\u305b\u3093\u3002\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3067\u306f\u3001\u5404\u30af\u30e9\u30b9\u3084\u30e1\u30bd\u30c3\u30c9\u306e\u8a73\u7d30\u306a\u8aac\u660e\u3001\u4f7f\u7528\u4f8b\u3001\u6ce8\u610f\u70b9\u306a\u3069\u304c\u7db2\u7f85\u7684\u306b\u8a18\u8f09\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">PyPDF2\u306e\u516c\u5f0f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8: https:\/\/pypdf2.readthedocs.io\/<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"i-11\">PDF\u306e\u4ed5\u69d8\u306b\u3064\u3044\u3066\u7406\u89e3\u3092\u6df1\u3081\u308b<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">PDF\u306e\u69cb\u9020\u3084\u4ed5\u69d8\u306b\u3064\u3044\u3066\u7406\u89e3\u3092\u6df1\u3081\u308b\u3053\u3068\u306f\u3001pypdf2\u3092\u4f7f\u3044\u3053\u306a\u3059\u4e0a\u3067\u5927\u5207\u3067\u3059\u3002PDF\u306e\u5185\u90e8\u69cb\u9020\u3092\u628a\u63e1\u3059\u308b\u3053\u3068\u3067\u3001\u3088\u308a\u9ad8\u5ea6\u306a\u51e6\u7406\u304c\u53ef\u80fd\u306b\u306a\u308a\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">PDF\u306e\u4ed5\u69d8\u3092\u8a73\u3057\u304f\u89e3\u8aac\u3057\u305f\u66f8\u7c4d\u3068\u3057\u3066\u3001\u4ee5\u4e0b\u3092\u304a\u3059\u3059\u3081\u3057\u307e\u3059\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u300cPDF\u69cb\u9020\u89e3\u8aac\u300d\uff08John Whitington \u8457\u3001\u30aa\u30e9\u30a4\u30ea\u30fc\u30b8\u30e3\u30d1\u30f3\uff09<\/li>\n\n\n\n<li>PDF\u306e\u69cb\u9020\u3084\u4ed5\u69d8\u306b\u3064\u3044\u3066\u3001\u8a73\u7d30\u304b\u3064\u5b9f\u8df5\u7684\u306b\u89e3\u8aac\u3057\u305f\u66f8\u7c4d\u3067\u3059\u3002<\/li>\n\n\n\n<li>\u30ea\u30f3\u30af\uff1a<a href=\"https:\/\/www.oreilly.co.jp\/books\/9784873115498\/\">https:\/\/www.oreilly.co.jp\/books\/9784873115498\/<\/a><\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u307e\u305f\u3001Adobe\u304c\u516c\u958b\u3057\u3066\u3044\u308bPDF Reference\u3082\u6709\u76ca\u3067\u3059\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>PDF Reference: <a href=\"https:\/\/opensource.adobe.com\/dc-acrobat-sdk-docs\/pdfstandards\/pdfreference1.7old.pdf\">https:\/\/www.adobe.com\/devnet\/pdf\/pdf_reference.html<\/a><\/li>\n\n\n\n<li>PDF\u306e\u4ed5\u69d8\u3092\u7db2\u7f85\u7684\u306b\u89e3\u8aac\u3057\u305f\u516c\u5f0f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3067\u3059\u3002<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u308c\u3089\u306e\u8cc7\u6599\u3092\u901a\u3058\u3066\u3001PDF\u306b\u5bfe\u3059\u308b\u7406\u89e3\u3092\u6df1\u3081\u3066\u3044\u304d\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"i-12\">PDF\u306b\u95a2\u3059\u308bPython\u60c5\u5831\u3092\u30ad\u30e3\u30c3\u30c1\u30a2\u30c3\u30d7\u3057\u7d9a\u3051\u308b\u65b9\u6cd5<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">pypdf2\u306b\u9650\u3089\u305a\u3001Python\u3067PDF\u3092\u51e6\u7406\u3059\u308b\u65b9\u6cd5\u306f\u65e5\u3005\u9032\u5316\u3057\u3066\u3044\u307e\u3059\u3002\u65b0\u3057\u3044\u30c6\u30af\u30cb\u30c3\u30af\u3084\u52b9\u7387\u7684\u306a\u65b9\u6cd5\u3092\u5b66\u3073\u7d9a\u3051\u308b\u3053\u3068\u304c\u3001\u30b9\u30ad\u30eb\u30a2\u30c3\u30d7\u306b\u3064\u306a\u304c\u308a\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4ee5\u4e0b\u306e\u3088\u3046\u306a\u30b5\u30a4\u30c8\u3084\u30d6\u30ed\u30b0\u3092\u5b9a\u671f\u7684\u306b\u30c1\u30a7\u30c3\u30af\u3059\u308b\u3053\u3068\u3092\u304a\u3059\u3059\u3081\u3057\u307e\u3059\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Real Python: https:\/\/realpython.com\/<\/li>\n\n\n\n<li>Python\u306e\u4f7f\u3044\u65b9\u3084\u30d9\u30b9\u30c8\u30d7\u30e9\u30af\u30c6\u30a3\u30b9\u3092\u89e3\u8aac\u3059\u308b\u6709\u76ca\u306a\u8a18\u4e8b\u304c\u591a\u6570\u63b2\u8f09\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/li>\n\n\n\n<li>Towards Data Science: https:\/\/towardsdatascience.com\/<\/li>\n\n\n\n<li>\u30c7\u30fc\u30bf\u30b5\u30a4\u30a8\u30f3\u30b9\u3084Python\u306b\u95a2\u3059\u308b\u6700\u65b0\u306e\u8a18\u4e8b\u304c\u6295\u7a3f\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/li>\n\n\n\n<li>PyPI \u2013 pypdf2: https:\/\/pypi.org\/project\/PyPDF2\/<\/li>\n\n\n\n<li>pypdf2\u30d1\u30c3\u30b1\u30fc\u30b8\u306e\u6700\u65b0\u30d0\u30fc\u30b8\u30e7\u30f3\u60c5\u5831\u3084\u30ea\u30ea\u30fc\u30b9\u30ce\u30fc\u30c8\u3092\u78ba\u8a8d\u3067\u304d\u307e\u3059\u3002<\/li>\n\n\n\n<li>GitHub \u2013 pypdf2: https:\/\/github.com\/py-pdf\/PyPDF2<\/li>\n\n\n\n<li>pypdf2\u306e\u958b\u767a\u72b6\u6cc1\u3084\u3001issue\u3001\u30d7\u30eb\u30ea\u30af\u30a8\u30b9\u30c8\u306e\u5185\u5bb9\u3092\u8ffd\u3046\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u308c\u3089\u306e\u60c5\u5831\u30bd\u30fc\u30b9\u3092\u6d3b\u7528\u3057\u3001\u5e38\u306b\u6700\u65b0\u306e\u77e5\u898b\u3092\u53d6\u308a\u5165\u308c\u308b\u3088\u3046\u5fc3\u304c\u3051\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4ee5\u4e0a\u3001pypdf2\u306e\u4f7f\u3044\u65b9\u306e\u307e\u3068\u3081\u3068\u3001\u767a\u5c55\u7684\u306a\u5b66\u7fd2\u30ea\u30bd\u30fc\u30b9\u306e\u7d39\u4ecb\u3067\u3057\u305f\u3002pypdf2\u306f\u3001PDF\u3092\u51e6\u7406\u3059\u308b\u4e0a\u3067\u975e\u5e38\u306b\u5f37\u529b\u306a\u30c4\u30fc\u30eb\u3067\u3059\u3002\u57fa\u672c\u7684\u306a\u4f7f\u3044\u65b9\u3092\u30de\u30b9\u30bf\u30fc\u3057\u3064\u3064\u3001PDF\u306e\u4ed5\u69d8\u3084\u6700\u65b0\u60c5\u5831\u306b\u3082\u30a2\u30f3\u30c6\u30ca\u3092\u5f35\u3063\u3066\u304a\u304f\u3053\u3068\u3067\u3001\u3088\u308a\u9ad8\u5ea6\u306a\u51e6\u7406\u304c\u5b9f\u73fe\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308b\u3067\u3057\u3087\u3046\u3002\u305c\u3072\u3001\u696d\u52d9\u306e\u81ea\u52d5\u5316\u3084\u52b9\u7387\u5316\u306b\u6d3b\u304b\u3057\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>PDF\u306f\u69d8\u3005\u306a\u5834\u9762\u3067\u4f7f\u308f\u308c\u308b\u6587\u66f8\u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u3067\u3059\u304c\u3001\u305d\u306e\u307e\u307e\u3067\u306f\u7de8\u96c6\u3084\u52a0\u5de5\u304c\u96e3\u3057\u3044\u3082\u306e\u3067\u3059\u3002\u3057\u304b\u3057\u3001Python\u306epypdf2\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u4f7f\u3048\u3070\u3001PDF\u3092\u81ea\u7531\u306b\u64cd\u4f5c\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3059\u3002\u672c\u8a18\u4e8b\u3067\u306f\u3001pypdf2\u306e\u57fa\u672c\u7684\u306a &#8230; <\/p>\n","protected":false},"author":1,"featured_media":464,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-436","post","type-post","status-publish","format-standard","has-post-thumbnail","category-python"],"_links":{"self":[{"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/posts\/436","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=436"}],"version-history":[{"count":4,"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/posts\/436\/revisions"}],"predecessor-version":[{"id":455,"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/posts\/436\/revisions\/455"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/media\/464"}],"wp:attachment":[{"href":"https:\/\/chocottopro.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=436"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=436"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=436"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}