{"id":978271,"date":"2024-12-27T06:36:23","date_gmt":"2024-12-26T22:36:23","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/978271.html"},"modified":"2024-12-27T06:36:25","modified_gmt":"2024-12-26T22:36:25","slug":"python%e5%a6%82%e4%bd%95%e8%8e%b7%e5%be%97pdf%e5%ad%97%e4%bd%93","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/978271.html","title":{"rendered":"Python\u5982\u4f55\u83b7\u5f97PDF\u5b57\u4f53"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/24203332\/b0cd0787-64fd-4c33-bfd7-71384b2194a1.webp\" alt=\"Python\u5982\u4f55\u83b7\u5f97PDF\u5b57\u4f53\" \/><\/p>\n<p><p> <strong>Python\u83b7\u53d6PDF\u5b57\u4f53\u7684\u65b9\u6cd5\u4e3b\u8981\u5305\u62ec\u4f7f\u7528PyPDF2\u5e93\u3001PDFMiner\u5e93\u3001pdfquery\u5e93\u3002\u8fd9\u4e9b\u5e93\u53ef\u4ee5\u5e2e\u52a9\u4f60\u89e3\u6790PDF\u6587\u4ef6\u3001\u63d0\u53d6\u5b57\u4f53\u4fe1\u606f\u3001\u5206\u6790\u6587\u672c\u5185\u5bb9\u3002<\/strong>\u5176\u4e2d\uff0cPDFMiner\u5e93\u5728\u83b7\u53d6PDF\u5b57\u4f53\u65b9\u9762\u8868\u73b0\u5c24\u4e3a\u7a81\u51fa\uff0c\u5b83\u80fd\u89e3\u6790PDF\u6587\u4ef6\u7ed3\u6784\u5e76\u63d0\u53d6\u5b57\u4f53\u548c\u6587\u672c\u4fe1\u606f\u3002\u4e0b\u9762\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528PDFMiner\u5e93\u6765\u83b7\u5f97PDF\u5b57\u4f53\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001PDFMINER\u5e93\u4ecb\u7ecd<\/h3>\n<\/p>\n<p><p>PDFMiner\u662f\u4e00\u4e2a\u7528Python\u7f16\u5199\u7684\u5de5\u5177\uff0c\u7528\u4e8e\u4ecePDF\u6587\u6863\u4e2d\u63d0\u53d6\u4fe1\u606f\u3002\u5b83\u652f\u6301\u89e3\u6790PDF\u6587\u6863\u7684\u6587\u672c\u3001\u5b57\u4f53\u3001\u5e03\u5c40\u7b49\u5185\u5bb9\uff0c\u56e0\u6b64\u6210\u4e3a\u63d0\u53d6PDF\u5b57\u4f53\u7684\u9996\u9009\u5de5\u5177\u4e4b\u4e00\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u5b89\u88c5\u4e0e\u57fa\u7840\u4f7f\u7528<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u4f60\u9700\u8981\u5b89\u88c5PDFMiner\u5e93\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install pdfminer.six<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u4f60\u53ef\u4ee5\u4f7f\u7528PDFMiner\u63d0\u4f9b\u7684\u5de5\u5177\u6765\u89e3\u6790PDF\u6587\u4ef6\u3002PDFMiner\u7684\u6838\u5fc3\u7ec4\u4ef6\u5305\u62ecPDFParser\u3001PDFDocument\u3001PDFPageInterpreter\u3001PDFDevice\u548cPDFResourceManager\u7b49\u3002\u5b83\u4eec\u534f\u540c\u5de5\u4f5c\uff0c\u89e3\u6790PDF\u6587\u4ef6\u5e76\u63d0\u53d6\u4fe1\u606f\u3002<\/p>\n<\/p>\n<p><h4>2\u3001\u63d0\u53d6PDF\u5b57\u4f53\u4fe1\u606f<\/h4>\n<\/p>\n<p><p>\u8981\u63d0\u53d6PDF\u4e2d\u7684\u5b57\u4f53\u4fe1\u606f\uff0c\u53ef\u4ee5\u4f7f\u7528PDFMiner\u4e2d\u7684PDFResourceManager\u548cLAParams\u7c7b\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u4f8b\u5b50\uff0c\u5c55\u793a\u5982\u4f55\u63d0\u53d6PDF\u4e2d\u7684\u5b57\u4f53\u4fe1\u606f\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter<\/p>\n<p>from pdfminer.pdfpage import PDFPage<\/p>\n<p>from pdfminer.converter import PDFPageAggregator<\/p>\n<p>from pdfminer.layout import LAParams<\/p>\n<p>def extract_fonts(pdf_path):<\/p>\n<p>    # \u521b\u5efaPDF<a href=\"https:\/\/docs.pingcode.com\/blog\/project-management\/58557.html\" target=\"_blank\">\u8d44\u6e90\u7ba1\u7406<\/a>\u5668<\/p>\n<p>    rsrcmgr = PDFResourceManager()<\/p>\n<p>    # \u8bbe\u7f6e\u53c2\u6570<\/p>\n<p>    laparams = LAParams()<\/p>\n<p>    # \u521b\u5efa\u805a\u5408\u5668<\/p>\n<p>    device = PDFPageAggregator(rsrcmgr, laparams=laparams)<\/p>\n<p>    # \u521b\u5efa\u89e3\u91ca\u5668<\/p>\n<p>    interpreter = PDFPageInterpreter(rsrcmgr, device)<\/p>\n<p>    # \u6253\u5f00PDF\u6587\u4ef6<\/p>\n<p>    with open(pdf_path, &#39;rb&#39;) as fp:<\/p>\n<p>        # \u904d\u5386PDF\u4e2d\u7684\u6bcf\u4e00\u9875<\/p>\n<p>        for page in PDFPage.get_pages(fp):<\/p>\n<p>            # \u5904\u7406\u9875\u9762\u5185\u5bb9<\/p>\n<p>            interpreter.process_page(page)<\/p>\n<p>            # \u83b7\u53d6\u9875\u9762\u5e03\u5c40<\/p>\n<p>            layout = device.get_result()<\/p>\n<p>            # \u904d\u5386\u9875\u9762\u4e2d\u7684\u6bcf\u4e2a\u5bf9\u8c61<\/p>\n<p>            for element in layout:<\/p>\n<p>                if hasattr(element, &#39;get_text&#39;):<\/p>\n<p>                    # \u6253\u5370\u5b57\u4f53\u4fe1\u606f<\/p>\n<p>                    print(element.fontname, element.size)<\/p>\n<h2><strong>\u8c03\u7528\u51fd\u6570<\/strong><\/h2>\n<p>extract_fonts(&#39;example.pdf&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e8c\u3001PDFQUERY\u5e93\u4f7f\u7528<\/h3>\n<\/p>\n<p><p>PDFQuery\u662f\u53e6\u4e00\u4e2a\u5f3a\u5927\u7684PDF\u89e3\u6790\u5de5\u5177\uff0c\u5b83\u7ed3\u5408\u4e86lxml\u548cpdfminer\u7684\u529f\u80fd\uff0c\u5141\u8bb8\u4f60\u4f7f\u7528CSS\u9009\u62e9\u5668\u6765\u67e5\u8be2PDF\u6587\u6863\u4e2d\u7684\u5143\u7d20\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u5b89\u88c5\u4e0e\u57fa\u7840\u4f7f\u7528<\/h4>\n<\/p>\n<p><p>\u8981\u4f7f\u7528PDFQuery\uff0c\u4f60\u9700\u8981\u5148\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install pdfquery<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u63d0\u53d6PDF\u5b57\u4f53\u4fe1\u606f<\/h4>\n<\/p>\n<p><p>PDFQuery\u80fd\u591f\u901a\u8fc7\u7b80\u5355\u7684CSS\u9009\u62e9\u5668\u6765\u8bbf\u95eePDF\u4e2d\u7684\u5143\u7d20\u3002\u4ee5\u4e0b\u662f\u4f7f\u7528PDFQuery\u63d0\u53d6\u5b57\u4f53\u4fe1\u606f\u7684\u4f8b\u5b50\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from pdfquery import PDFQuery<\/p>\n<p>def extract_fonts_with_pdfquery(pdf_path):<\/p>\n<p>    # \u52a0\u8f7dPDF<\/p>\n<p>    pdf = PDFQuery(pdf_path)<\/p>\n<p>    pdf.load()<\/p>\n<p>    # \u904d\u5386PDF\u4e2d\u7684\u6587\u672c\u5143\u7d20<\/p>\n<p>    for element in pdf.pq(&#39;LTTextLineHorizontal&#39;):<\/p>\n<p>        # \u6253\u5370\u5b57\u4f53\u4fe1\u606f<\/p>\n<p>        print(element.attrib[&#39;fontname&#39;], element.attrib[&#39;size&#39;])<\/p>\n<h2><strong>\u8c03\u7528\u51fd\u6570<\/strong><\/h2>\n<p>extract_fonts_with_pdfquery(&#39;example.pdf&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u5176\u4ed6\u76f8\u5173\u5e93\u4e0e\u5de5\u5177<\/h3>\n<\/p>\n<p><h4>1\u3001PyPDF2\u5e93<\/h4>\n<\/p>\n<p><p>PyPDF2\u662f\u4e00\u4e2a\u7eafPython\u7f16\u5199\u7684PDF\u5de5\u5177\u5305\uff0c\u652f\u6301PDF\u6587\u4ef6\u7684\u62c6\u5206\u3001\u5408\u5e76\u3001\u88c1\u526a\u3001\u52a0\u5bc6\u548c\u89e3\u5bc6\u7b49\u529f\u80fd\u3002\u867d\u7136\u5b83\u4e0d\u76f4\u63a5\u652f\u6301\u63d0\u53d6\u5b57\u4f53\u4fe1\u606f\uff0c\u4f46\u53ef\u4ee5\u7ed3\u5408\u5176\u4ed6\u5e93\u4f7f\u7528\u3002<\/p>\n<\/p>\n<p><h4>2\u3001\u5176\u4ed6\u5de5\u5177<\/h4>\n<\/p>\n<p><p>\u9664\u4e86\u4e0a\u8ff0Python\u5e93\uff0c\u8fd8\u6709\u4e00\u4e9b\u5176\u4ed6\u5de5\u5177\u548c\u5e93\u53ef\u4ee5\u5e2e\u52a9\u4f60\u89e3\u6790PDF\u6587\u4ef6\u5e76\u63d0\u53d6\u5b57\u4f53\u4fe1\u606f\u3002\u4f8b\u5982\uff0cAdobe Acrobat\u63d0\u4f9b\u4e86\u5f3a\u5927\u7684PDF\u7f16\u8f91\u548c\u89e3\u6790\u529f\u80fd\uff0c\u53ef\u4ee5\u901a\u8fc7\u5176API\u63a5\u53e3\u8fdb\u884c\u5b57\u4f53\u4fe1\u606f\u7684\u63d0\u53d6\u3002<\/p>\n<\/p>\n<p><h3>\u56db\u3001\u5e94\u7528\u573a\u666f\u4e0e\u6ce8\u610f\u4e8b\u9879<\/h3>\n<\/p>\n<p><h4>1\u3001\u5e94\u7528\u573a\u666f<\/h4>\n<\/p>\n<p><p>\u63d0\u53d6PDF\u5b57\u4f53\u4fe1\u606f\u5728\u8bb8\u591a\u573a\u666f\u4e0b\u90fd\u975e\u5e38\u6709\u7528\uff0c\u4f8b\u5982\uff1a<\/p>\n<\/p>\n<ul>\n<li><strong>\u6587\u6863\u5206\u6790<\/strong>\uff1a\u5206\u6790\u6587\u6863\u4e2d\u7684\u5b57\u4f53\u4f7f\u7528\u60c5\u51b5\uff0c\u4f18\u5316\u6392\u7248\u8bbe\u8ba1\u3002<\/li>\n<li><strong>\u6587\u672c\u8f6c\u6362<\/strong>\uff1a\u5728\u8fdb\u884cPDF\u8f6cWord\u6216\u5176\u4ed6\u683c\u5f0f\u65f6\uff0c\u4fdd\u6301\u5b57\u4f53\u4e00\u81f4\u6027\u3002<\/li>\n<li><strong>\u6570\u636e\u6316\u6398<\/strong>\uff1a\u4ecePDF\u62a5\u544a\u6216\u4e66\u7c4d\u4e2d\u63d0\u53d6\u6709\u4ef7\u503c\u7684\u4fe1\u606f\u3002<\/li>\n<\/ul>\n<p><h4>2\u3001\u6ce8\u610f\u4e8b\u9879<\/h4>\n<\/p>\n<p><p>\u5728\u63d0\u53d6PDF\u5b57\u4f53\u4fe1\u606f\u65f6\uff0c\u9700\u8981\u6ce8\u610f\u4ee5\u4e0b\u51e0\u70b9\uff1a<\/p>\n<\/p>\n<ul>\n<li><strong>PDF\u6587\u4ef6\u7684\u590d\u6742\u6027<\/strong>\uff1a\u4e0d\u540c\u7684PDF\u6587\u4ef6\u7ed3\u6784\u53ef\u80fd\u5bfc\u81f4\u63d0\u53d6\u7ed3\u679c\u4e0d\u540c\uff0c\u56e0\u6b64\u9700\u8981\u9488\u5bf9\u6027\u5730\u9009\u62e9\u5de5\u5177\u548c\u65b9\u6cd5\u3002<\/li>\n<li><strong>\u7248\u6743\u4e0e\u5408\u6cd5\u6027<\/strong>\uff1a\u5728\u5904\u7406\u53d7\u7248\u6743\u4fdd\u62a4\u7684PDF\u6587\u4ef6\u65f6\uff0c\u786e\u4fdd\u9075\u5faa\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\u3002<\/li>\n<li><strong>\u5b57\u4f53\u7f16\u7801<\/strong>\uff1a\u67d0\u4e9bPDF\u6587\u4ef6\u53ef\u80fd\u4f7f\u7528\u81ea\u5b9a\u4e49\u5b57\u4f53\u7f16\u7801\uff0c\u9700\u8981\u989d\u5916\u7684\u89e3\u6790\u6b65\u9aa4\u3002<\/li>\n<\/ul>\n<p><h3>\u4e94\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u5229\u7528Python\u63d0\u53d6PDF\u4e2d\u7684\u5b57\u4f53\u4fe1\u606f\u662f\u4e00\u4e2a\u975e\u5e38\u5b9e\u7528\u7684\u6280\u80fd\uff0c\u7279\u522b\u662f\u5728\u6570\u636e\u5206\u6790\u3001\u6587\u672c\u5904\u7406\u548c\u6587\u6863\u7ba1\u7406\u7b49\u9886\u57df\u3002\u901a\u8fc7\u4f7f\u7528PDFMiner\u3001PDFQuery\u7b49\u5e93\uff0c\u53ef\u4ee5\u9ad8\u6548\u5730\u83b7\u53d6PDF\u4e2d\u7684\u5b57\u4f53\u4fe1\u606f\uff0c\u4e3a\u540e\u7eed\u7684\u6587\u672c\u5904\u7406\u548c\u6570\u636e\u5206\u6790\u6253\u4e0b\u826f\u597d\u7684\u57fa\u7840\u3002\u5728\u5177\u4f53\u5b9e\u73b0\u8fc7\u7a0b\u4e2d\uff0c\u53ef\u4ee5\u6839\u636e\u5b9e\u9645\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\u548c\u65b9\u6cd5\uff0c\u786e\u4fdd\u63d0\u53d6\u7ed3\u679c\u7684\u51c6\u786e\u6027\u548c\u5b8c\u6574\u6027\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u5728Python\u4e2d\u63d0\u53d6PDF\u6587\u4ef6\u7684\u5b57\u4f53\u4fe1\u606f\uff1f<\/strong><br \/>\u5728Python\u4e2d\u63d0\u53d6PDF\u6587\u4ef6\u7684\u5b57\u4f53\u4fe1\u606f\uff0c\u53ef\u4ee5\u4f7f\u7528\u4e00\u4e9b\u6d41\u884c\u7684\u5e93\uff0c\u5982PyPDF2\u3001pdfminer.six\u6216PyMuPDF\uff08fitz\uff09\u3002\u8fd9\u4e9b\u5e93\u5141\u8bb8\u4f60\u8bfb\u53d6PDF\u6587\u4ef6\u7684\u7ed3\u6784\uff0c\u5e76\u63d0\u53d6\u76f8\u5173\u7684\u5b57\u4f53\u4fe1\u606f\u3002\u4f7f\u7528pdfminer.six\uff0c\u4f60\u53ef\u4ee5\u89e3\u6790PDF\u5e76\u83b7\u53d6\u6bcf\u4e2a\u6587\u672c\u5143\u7d20\u7684\u5b57\u4f53\u7c7b\u578b\u3001\u5927\u5c0f\u548c\u5176\u4ed6\u5c5e\u6027\u3002\u786e\u4fdd\u5b89\u88c5\u76f8\u5e94\u7684\u5e93\uff0c\u5e76\u53c2\u8003\u5176\u6587\u6863\u4ee5\u4e86\u89e3\u8be6\u7ec6\u7684\u4f7f\u7528\u65b9\u6cd5\u3002<\/p>\n<p><strong>Python\u4e2d\u5e38\u7528\u7684PDF\u5904\u7406\u5e93\u6709\u54ea\u4e9b\uff1f<\/strong><br \/>\u5904\u7406PDF\u6587\u4ef6\u7684\u5e38\u7528Python\u5e93\u5305\u62ecPyPDF2\u3001pdfminer.six\u3001PyMuPDF\uff08fitz\uff09\u3001reportlab\u548cpdfrw\u7b49\u3002\u6bcf\u4e2a\u5e93\u90fd\u6709\u5176\u72ec\u7279\u7684\u529f\u80fd\uff0c\u4f8b\u5982PyPDF2\u9002\u5408\u4e8e\u5408\u5e76\u548c\u62c6\u5206PDF\uff0c\u800cpdfminer.six\u66f4\u9002\u5408\u4e8e\u6587\u672c\u63d0\u53d6\u548c\u5206\u6790\u3002\u9009\u62e9\u5408\u9002\u7684\u5e93\u53d6\u51b3\u4e8e\u4f60\u7684\u5177\u4f53\u9700\u6c42\uff0c\u6bd4\u5982\u662f\u5426\u9700\u8981\u5904\u7406\u56fe\u5f62\u3001\u8868\u683c\u6216\u590d\u6742\u7684\u5e03\u5c40\u3002<\/p>\n<p><strong>\u5982\u4f55\u786e\u4fdd\u63d0\u53d6\u7684\u5b57\u4f53\u4fe1\u606f\u51c6\u786e\u65e0\u8bef\uff1f<\/strong><br \/>\u4e3a\u4e86\u786e\u4fdd\u63d0\u53d6\u7684\u5b57\u4f53\u4fe1\u606f\u51c6\u786e\uff0c\u5efa\u8bae\u4f7f\u7528\u5177\u6709\u826f\u597d\u6587\u6863\u548c\u793e\u533a\u652f\u6301\u7684\u5e93\u3002\u4f7f\u7528pdfminer.six\u65f6\uff0c\u53ef\u4ee5\u901a\u8fc7\u5bf9\u6bd4PDF\u5185\u5d4c\u7684\u5b57\u4f53\u4fe1\u606f\u4e0e\u5b9e\u9645\u5448\u73b0\u7684\u6587\u672c\u8fdb\u884c\u9a8c\u8bc1\u3002\u6b64\u5916\uff0c\u5904\u7406\u4e0d\u540c\u7248\u672c\u7684PDF\u6587\u4ef6\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u517c\u5bb9\u6027\u95ee\u9898\uff0c\u5efa\u8bae\u6d4b\u8bd5\u4e0d\u540c\u7684PDF\u6587\u4ef6\u4ee5\u786e\u4fdd\u63d0\u53d6\u7ed3\u679c\u7684\u4e00\u81f4\u6027\u548c\u53ef\u9760\u6027\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u83b7\u53d6PDF\u5b57\u4f53\u7684\u65b9\u6cd5\u4e3b\u8981\u5305\u62ec\u4f7f\u7528PyPDF2\u5e93\u3001PDFMiner\u5e93\u3001pdfquery\u5e93\u3002\u8fd9\u4e9b\u5e93\u53ef\u4ee5 [&hellip;]","protected":false},"author":3,"featured_media":978280,"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\/978271"}],"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=978271"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/978271\/revisions"}],"predecessor-version":[{"id":978282,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/978271\/revisions\/978282"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/978280"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=978271"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=978271"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=978271"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}