{"id":1128822,"date":"2025-01-08T20:24:02","date_gmt":"2025-01-08T12:24:02","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1128822.html"},"modified":"2025-01-08T20:24:04","modified_gmt":"2025-01-08T12:24:04","slug":"python%e5%a6%82%e4%bd%95%e8%bf%9e%e6%8e%a5%e4%b8%a4%e4%b8%aapdf%e6%96%87%e4%bb%b6%e5%a4%a7%e5%b0%8f","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1128822.html","title":{"rendered":"python\u5982\u4f55\u8fde\u63a5\u4e24\u4e2apdf\u6587\u4ef6\u5927\u5c0f"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25095430\/a72b83f8-beef-41ab-954f-6dbe1b842825.webp\" alt=\"python\u5982\u4f55\u8fde\u63a5\u4e24\u4e2apdf\u6587\u4ef6\u5927\u5c0f\" \/><\/p>\n<p><p> <strong>Python \u8fde\u63a5\u4e24\u4e2aPDF\u6587\u4ef6\u5927\u5c0f\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528PyPDF2\u3001\u4f7f\u7528pdfrw\u3001\u521b\u5efa\u4e00\u4e2a\u65b0PDF\u5e76\u5408\u5e76\u8fd9\u4e24\u4e2a\u6587\u4ef6\u3002<\/strong> \u5176\u4e2d\uff0c<strong>\u4f7f\u7528PyPDF2<\/strong>\u662f\u6700\u5e38\u89c1\u7684\u65b9\u6cd5\u4e4b\u4e00\u3002PyPDF2\u662f\u4e00\u4e2a\u7eafPython\u7f16\u5199\u7684\u5e93\uff0c\u4e13\u95e8\u7528\u4e8e\u64cd\u4f5cPDF\u6587\u4ef6\u3002\u4f7f\u7528\u5b83\u53ef\u4ee5\u8f7b\u677e\u5730\u5c06\u4e24\u4e2aPDF\u6587\u4ef6\u5408\u5e76\u4e3a\u4e00\u4e2a\u65b0\u7684PDF\u6587\u4ef6\u3002\u4e0b\u9762\u6211\u4eec\u5c06\u8be6\u7ec6\u63cf\u8ff0\u5982\u4f55\u4f7f\u7528PyPDF2\u6765\u8fde\u63a5\u4e24\u4e2aPDF\u6587\u4ef6\uff0c\u5e76\u63a2\u8ba8\u5176\u4ed6\u65b9\u6cd5\u7684\u4f7f\u7528\u3002<\/p>\n<\/p>\n<hr>\n<p><h3>\u4e00\u3001\u4f7f\u7528PyPDF2\u5e93<\/h3>\n<\/p>\n<p><h4>1. \u5b89\u88c5\u4e0e\u5bfc\u5165<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5PyPDF2\u5e93\uff0c\u53ef\u4ee5\u901a\u8fc7pip\u547d\u4ee4\u6765\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install PyPDF2<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u5728Python\u811a\u672c\u4e2d\u5bfc\u5165\u8be5\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import PyPDF2<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u6253\u5f00PDF\u6587\u4ef6<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528PyPDF2\u7684<code>PdfFileReader<\/code>\u7c7b\u6765\u6253\u5f00\u4e24\u4e2aPDF\u6587\u4ef6\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">pdf1 = open(&#39;file1.pdf&#39;, &#39;rb&#39;)<\/p>\n<p>pdf2 = open(&#39;file2.pdf&#39;, &#39;rb&#39;)<\/p>\n<p>reader1 = PyPDF2.PdfFileReader(pdf1)<\/p>\n<p>reader2 = PyPDF2.PdfFileReader(pdf2)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>3. \u521b\u5efa\u4e00\u4e2a\u65b0\u7684PDF\u6587\u4ef6<\/h4>\n<\/p>\n<p><p>\u521b\u5efa\u4e00\u4e2a<code>PdfFileWriter<\/code>\u5bf9\u8c61\uff0c\u7528\u4e8e\u5c06\u4e24\u4e2aPDF\u6587\u4ef6\u7684\u5185\u5bb9\u5199\u5165\u65b0\u7684PDF\u6587\u4ef6\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">writer = PyPDF2.PdfFileWriter()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>4. \u5408\u5e76PDF\u6587\u4ef6<\/h4>\n<\/p>\n<p><p>\u5c06\u4e24\u4e2aPDF\u6587\u4ef6\u7684\u5185\u5bb9\u9010\u9875\u6dfb\u52a0\u5230<code>PdfFileWriter<\/code>\u5bf9\u8c61\u4e2d\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for page_num in range(reader1.numPages):<\/p>\n<p>    page = reader1.getPage(page_num)<\/p>\n<p>    writer.addPage(page)<\/p>\n<p>for page_num in range(reader2.numPages):<\/p>\n<p>    page = reader2.getPage(page_num)<\/p>\n<p>    writer.addPage(page)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>5. \u4fdd\u5b58\u5408\u5e76\u540e\u7684PDF\u6587\u4ef6<\/h4>\n<\/p>\n<p><p>\u5c06\u5408\u5e76\u540e\u7684\u5185\u5bb9\u5199\u5165\u65b0\u7684PDF\u6587\u4ef6\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">output_pdf = open(&#39;merged.pdf&#39;, &#39;wb&#39;)<\/p>\n<p>writer.write(output_pdf)<\/p>\n<p>output_pdf.close()<\/p>\n<p>pdf1.close()<\/p>\n<p>pdf2.close()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e8c\u3001\u4f7f\u7528pdfrw\u5e93<\/h3>\n<\/p>\n<p><h4>1. \u5b89\u88c5\u4e0e\u5bfc\u5165<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5pdfrw\u5e93\uff0c\u53ef\u4ee5\u901a\u8fc7pip\u547d\u4ee4\u6765\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install pdfrw<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u5728Python\u811a\u672c\u4e2d\u5bfc\u5165\u8be5\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from pdfrw import PdfReader, PdfWriter<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u6253\u5f00PDF\u6587\u4ef6\u5e76\u5408\u5e76<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528<code>PdfReader<\/code>\u7c7b\u6765\u6253\u5f00\u4e24\u4e2aPDF\u6587\u4ef6\uff0c\u5e76\u5c06\u5b83\u4eec\u5408\u5e76\u5230\u4e00\u4e2a\u65b0\u7684PDF\u6587\u4ef6\u4e2d\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">pdf1 = PdfReader(&#39;file1.pdf&#39;)<\/p>\n<p>pdf2 = PdfReader(&#39;file2.pdf&#39;)<\/p>\n<p>writer = PdfWriter()<\/p>\n<p>for page in pdf1.pages:<\/p>\n<p>    writer.addpage(page)<\/p>\n<p>for page in pdf2.pages:<\/p>\n<p>    writer.addpage(page)<\/p>\n<p>writer.write(&#39;merged.pdf&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u521b\u5efa\u4e00\u4e2a\u65b0PDF\u5e76\u5408\u5e76<\/h3>\n<\/p>\n<p><p>\u6709\u65f6\uff0c\u6211\u4eec\u53ef\u80fd\u9700\u8981\u521b\u5efa\u4e00\u4e2a\u65b0\u7684PDF\u6587\u4ef6\uff0c\u5e76\u5c06\u4e24\u4e2aPDF\u6587\u4ef6\u7684\u5185\u5bb9\u5408\u5e76\u5230\u8fd9\u4e2a\u65b0\u7684PDF\u6587\u4ef6\u4e2d\u3002\u53ef\u4ee5\u4f7f\u7528<code>reportlab<\/code>\u5e93\u6765\u521b\u5efa\u65b0\u7684PDF\u6587\u4ef6\uff0c\u5e76\u4f7f\u7528<code>PyPDF2<\/code>\u6216<code>pdfrw<\/code>\u5e93\u6765\u5408\u5e76\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h4>1. \u5b89\u88c5\u4e0e\u5bfc\u5165<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5reportlab\u5e93\uff0c\u53ef\u4ee5\u901a\u8fc7pip\u547d\u4ee4\u6765\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install reportlab<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u5728Python\u811a\u672c\u4e2d\u5bfc\u5165\u8be5\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from reportlab.pdfgen import canvas<\/p>\n<p>from reportlab.lib.pagesizes import letter<\/p>\n<p>import PyPDF2<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u521b\u5efa\u4e00\u4e2a\u65b0\u7684PDF\u6587\u4ef6<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528<code>reportlab<\/code>\u5e93\u521b\u5efa\u4e00\u4e2a\u65b0\u7684PDF\u6587\u4ef6\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">c = canvas.Canvas(&quot;newfile.pdf&quot;, pagesize=letter)<\/p>\n<p>c.drawString(100, 750, &quot;This is a new PDF file.&quot;)<\/p>\n<p>c.showPage()<\/p>\n<p>c.save()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>3. \u5408\u5e76PDF\u6587\u4ef6<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528<code>PyPDF2<\/code>\u5e93\u5c06\u4e24\u4e2a\u73b0\u6709\u7684PDF\u6587\u4ef6\u5408\u5e76\u5230\u65b0\u7684PDF\u6587\u4ef6\u4e2d\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">new_pdf = open(&#39;newfile.pdf&#39;, &#39;rb&#39;)<\/p>\n<p>reader_new = PyPDF2.PdfFileReader(new_pdf)<\/p>\n<p>output_writer = PyPDF2.PdfFileWriter()<\/p>\n<p>for page_num in range(reader_new.numPages):<\/p>\n<p>    page = reader_new.getPage(page_num)<\/p>\n<p>    output_writer.addPage(page)<\/p>\n<p>for page_num in range(reader1.numPages):<\/p>\n<p>    page = reader1.getPage(page_num)<\/p>\n<p>    output_writer.addPage(page)<\/p>\n<p>for page_num in range(reader2.numPages):<\/p>\n<p>    page = reader2.getPage(page_num)<\/p>\n<p>    output_writer.addPage(page)<\/p>\n<p>output_final = open(&#39;final_merged.pdf&#39;, &#39;wb&#39;)<\/p>\n<p>output_writer.write(output_final)<\/p>\n<p>output_final.close()<\/p>\n<p>new_pdf.close()<\/p>\n<p>pdf1.close()<\/p>\n<p>pdf2.close()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u56db\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u5728\u8fd9\u7bc7\u6587\u7ae0\u4e2d\uff0c\u6211\u4eec\u8be6\u7ec6\u4ecb\u7ecd\u4e86\u5982\u4f55\u4f7f\u7528Python\u6765\u8fde\u63a5\u4e24\u4e2aPDF\u6587\u4ef6\u5927\u5c0f\u3002\u6211\u4eec\u8ba8\u8bba\u4e86\u4e09\u79cd\u4e3b\u8981\u7684\u65b9\u6cd5\uff1a\u4f7f\u7528PyPDF2\u5e93\u3001\u4f7f\u7528pdfrw\u5e93\u4ee5\u53ca\u521b\u5efa\u4e00\u4e2a\u65b0PDF\u5e76\u5408\u5e76\u3002<strong>PyPDF2\u662f\u6700\u5e38\u89c1\u4e14\u6613\u4e8e\u4f7f\u7528\u7684\u65b9\u6cd5<\/strong>\uff0c\u5b83\u80fd\u591f\u6ee1\u8db3\u5927\u591a\u6570\u5408\u5e76PDF\u6587\u4ef6\u7684\u9700\u6c42\u3002pdfrw\u5e93\u63d0\u4f9b\u4e86\u53e6\u4e00\u79cd\u9009\u62e9\uff0c\u9002\u7528\u4e8e\u66f4\u590d\u6742\u7684PDF\u64cd\u4f5c\u3002\u6700\u540e\uff0c\u6211\u4eec\u4ecb\u7ecd\u4e86\u5982\u4f55\u4f7f\u7528reportlab\u5e93\u521b\u5efa\u4e00\u4e2a\u65b0\u7684PDF\u6587\u4ef6\u5e76\u5c06\u73b0\u6709\u7684PDF\u6587\u4ef6\u5408\u5e76\u5230\u65b0\u7684PDF\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n<p><p>\u901a\u8fc7\u8fd9\u4e9b\u65b9\u6cd5\uff0c\u60a8\u53ef\u4ee5\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u6700\u9002\u5408\u7684\u65b9\u6cd5\u6765\u8fde\u63a5\u4e24\u4e2aPDF\u6587\u4ef6\u5927\u5c0f\u3002\u65e0\u8bba\u662f\u7b80\u5355\u7684\u5408\u5e76\uff0c\u8fd8\u662f\u66f4\u590d\u6742\u7684PDF\u64cd\u4f5c\uff0cPython\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u5e93\u548c\u5de5\u5177\u6765\u5e2e\u52a9\u60a8\u5b9e\u73b0\u76ee\u6807\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u5408\u5e76\u591a\u4e2aPDF\u6587\u4ef6\uff1f<\/strong><br \/>\u53ef\u4ee5\u4f7f\u7528Python\u4e2d\u7684PyPDF2\u5e93\u6765\u5408\u5e76PDF\u6587\u4ef6\u3002\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5\u8be5\u5e93\uff0c\u53ef\u4ee5\u4f7f\u7528pip\u547d\u4ee4\uff1a<code>pip install PyPDF2<\/code>\u3002\u63a5\u7740\uff0c\u5229\u7528<code>PdfFileMerger<\/code>\u7c7b\u53ef\u4ee5\u8f7b\u677e\u5730\u5c06\u591a\u4e2aPDF\u6587\u4ef6\u5408\u5e76\u4e3a\u4e00\u4e2a\u3002\u4f8b\u5982\uff1a<\/p>\n<pre><code class=\"language-python\">from PyPDF2 import PdfFileMerger\n\nmerger = PdfFileMerger()\nmerger.append(&#39;file1.pdf&#39;)\nmerger.append(&#39;file2.pdf&#39;)\nmerger.write(&#39;merged.pdf&#39;)\nmerger.close()\n<\/code><\/pre>\n<p>\u8fd9\u4e2a\u4ee3\u7801\u6bb5\u4f1a\u5c06<code>file1.pdf<\/code>\u548c<code>file2.pdf<\/code>\u5408\u5e76\u6210\u4e00\u4e2a\u540d\u4e3a<code>merged.pdf<\/code>\u7684\u65b0\u6587\u4ef6\u3002<\/p>\n<p><strong>\u5408\u5e76PDF\u6587\u4ef6\u65f6\u5982\u4f55\u5904\u7406\u6587\u4ef6\u5927\u5c0f\u95ee\u9898\uff1f<\/strong><br \/>\u5408\u5e76PDF\u6587\u4ef6\u540e\uff0c\u751f\u6210\u7684\u6587\u4ef6\u5927\u5c0f\u53ef\u80fd\u4f1a\u6bd4\u539f\u6587\u4ef6\u5927\u3002\u8fd9\u901a\u5e38\u662f\u56e0\u4e3a\u5408\u5e76\u8fc7\u7a0b\u4e2d\u5305\u542b\u4e86\u91cd\u590d\u7684\u8d44\u6e90\uff08\u5982\u56fe\u7247\uff09\u3002\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u538b\u7f29\u5de5\u5177\uff0c\u5982<code>pdf2image<\/code>\u6216<code>PyPDF2<\/code>\u81ea\u5e26\u7684\u538b\u7f29\u529f\u80fd\uff0c\u6765\u4f18\u5316\u6587\u4ef6\u5927\u5c0f\u3002\u538b\u7f29\u540e\uff0c\u6587\u4ef6\u7684\u8d28\u91cf\u53ef\u80fd\u4f1a\u6709\u6240\u4e0b\u964d\uff0c\u56e0\u6b64\u5728\u4fdd\u5b58\u4e4b\u524d\u6700\u597d\u5148\u9884\u89c8\u6548\u679c\u3002<\/p>\n<p><strong>\u662f\u5426\u53ef\u4ee5\u5728\u5408\u5e76PDF\u65f6\u9009\u62e9\u7279\u5b9a\u7684\u9875\u9762\uff1f<\/strong><br \/>\u5f53\u7136\u53ef\u4ee5\u3002\u4f7f\u7528<code>PdfFileReader<\/code>\u7c7b\u53ef\u4ee5\u9009\u62e9\u7279\u5b9a\u7684\u9875\u9762\u8fdb\u884c\u5408\u5e76\u3002\u4f8b\u5982\uff0c\u5982\u679c\u53ea\u60f3\u5408\u5e76\u7b2c1\u9875\u548c\u7b2c3\u9875\uff0c\u53ef\u4ee5\u8fd9\u6837\u505a\uff1a<\/p>\n<pre><code class=\"language-python\">from PyPDF2 import PdfFileReader, PdfFileWriter\n\npdf_writer = PdfFileWriter()\npdf_reader = PdfFileReader(&#39;file1.pdf&#39;)\n\npdf_writer.addPage(pdf_reader.getPage(0))  # \u6dfb\u52a0\u7b2c1\u9875\npdf_writer.addPage(pdf_reader.getPage(2))  # \u6dfb\u52a0\u7b2c3\u9875\n\nwith open(&#39;selected_pages.pdf&#39;, &#39;wb&#39;) as output_pdf:\n    pdf_writer.write(output_pdf)\n<\/code><\/pre>\n<p>\u8fd9\u79cd\u65b9\u6cd5\u53ef\u4ee5\u8ba9\u7528\u6237\u66f4\u52a0\u7075\u6d3b\u5730\u9009\u62e9\u5408\u5e76\u7684\u5185\u5bb9\uff0c\u6ee1\u8db3\u4e0d\u540c\u7684\u9700\u6c42\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python \u8fde\u63a5\u4e24\u4e2aPDF\u6587\u4ef6\u5927\u5c0f\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528PyPDF2\u3001\u4f7f\u7528pdfrw\u3001\u521b\u5efa\u4e00\u4e2a\u65b0PDF\u5e76\u5408\u5e76\u8fd9\u4e24\u4e2a [&hellip;]","protected":false},"author":3,"featured_media":1128829,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1128822"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1128822"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1128822\/revisions"}],"predecessor-version":[{"id":1128830,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1128822\/revisions\/1128830"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1128829"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1128822"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1128822"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1128822"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}