{"id":1014990,"date":"2024-12-27T12:01:15","date_gmt":"2024-12-27T04:01:15","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1014990.html"},"modified":"2024-12-27T12:01:17","modified_gmt":"2024-12-27T04:01:17","slug":"python%e5%a6%82%e4%bd%95pdf%e8%bd%acpng","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1014990.html","title":{"rendered":"python\u5982\u4f55pdf\u8f6cpng"},"content":{"rendered":"

\"python\u5982\u4f55pdf\u8f6cpng\"<\/p>\n

\u5f00\u5934\u6bb5\u843d\uff1a
Python\u901a\u8fc7\u4f7f\u7528PyMuPDF\u3001pdf2image\u5e93<\/strong>\u7b49\u591a\u79cd\u65b9\u6cd5\u53ef\u4ee5\u5c06PDF\u6587\u4ef6\u8f6c\u6362\u4e3aPNG\u683c\u5f0f\u3002PyMuPDF\u5e93<\/strong>\u63d0\u4f9b\u4e86\u4e00\u4e2a\u9ad8\u6548\u7684\u65b9\u6cd5\u6765\u5904\u7406PDF\u6587\u4ef6\uff0c\u5b83\u53ef\u4ee5\u5feb\u901f\u5730\u5c06PDF\u9875\u9762\u6e32\u67d3\u4e3a\u56fe\u50cf\u683c\u5f0f\uff1bpdf2image\u5e93<\/strong>\u5219\u662f\u4e00\u4e2a\u4e13\u95e8\u7528\u4e8e\u5c06PDF\u6587\u4ef6\u8f6c\u6362\u4e3a\u56fe\u50cf\u7684\u5e93\uff0c\u80fd\u591f\u8f7b\u677e\u5730\u5904\u7406\u591a\u9875PDF\u6587\u4ef6\u3002\u4f7f\u7528PyMuPDF\u5e93\u65f6\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u52a0\u8f7dPDF\u6587\u4ef6\u5e76\u9010\u9875\u6e32\u67d3\u4e3a\u56fe\u50cf\uff0c\u4ece\u800c\u5b9e\u73b0\u8f6c\u6362\u3002\u5bf9\u4e8epdf2image\u5e93\uff0c\u5219\u53ef\u4ee5\u5229\u7528\u5176\u5185\u7f6e\u7684\u8f6c\u6362\u51fd\u6570\uff0c\u76f4\u63a5\u6307\u5b9a\u8f93\u51fa\u683c\u5f0f\u4e3aPNG\u3002\u4ee5\u4e0b\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u8fd9\u4e24\u79cd\u65b9\u6cd5\u7684\u5177\u4f53\u5b9e\u73b0\u6b65\u9aa4\u548c\u4f7f\u7528\u6280\u5de7\u3002<\/p>\n<\/p>\n

\u4e00\u3001PYMUPDF\u5e93\u7684\u4f7f\u7528<\/p>\n<\/p>\n

PyMuPDF\u662f\u4e00\u4e2a\u8f7b\u91cf\u7ea7\u4e14\u529f\u80fd\u5f3a\u5927\u7684\u5e93\uff0c\u53ef\u4ee5\u7528\u4e8e\u5904\u7406PDF\u6587\u4ef6\u3002\u5b83\u5141\u8bb8\u7528\u6237\u76f4\u63a5\u4ecePDF\u6587\u4ef6\u4e2d\u63d0\u53d6\u9875\u9762\uff0c\u5e76\u5c06\u5176\u8f6c\u6362\u4e3a\u56fe\u50cf\u683c\u5f0f\u3002<\/p>\n<\/p>\n

    \n
  1. \u5b89\u88c5\u548c\u57fa\u672c\u7528\u6cd5<\/li>\n<\/ol>\n

    \u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5PyMuPDF\u5e93\u3002\u53ef\u4ee5\u4f7f\u7528pip\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n

    pip install PyMuPDF<\/p>\n
    <\/code><\/pre>\n<\/p>\n
    \u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u4ee3\u7801\u5c06PDF\u6587\u4ef6\u8f6c\u6362\u4e3aPNG\u683c\u5f0f\uff1a<\/p>\n<\/p>\n
    import fitz  # PyMuPDF<\/p>\n
    def pdf_to_png(pdf_path, output_path):<\/p>\n
        # \u6253\u5f00PDF\u6587\u4ef6<\/p>\n
        document = fitz.open(pdf_path)<\/p>\n
        for page_number in range(document.page_count):<\/p>\n
            # \u83b7\u53d6\u9875\u9762<\/p>\n
            page = document.load_page(page_number)<\/p>\n
            # \u6e32\u67d3\u9875\u9762\u4e3a\u56fe\u50cf<\/p>\n
            pix = page.get_pixmap()<\/p>\n
            # \u4fdd\u5b58\u56fe\u50cf<\/p>\n
            pix.save(f"{output_path}\/page_{page_number + 1}.png")<\/p>\n
    pdf_to_png("example.pdf", "output_directory")<\/p>\n
    <\/code><\/pre>\n<\/p>\n
      \n
    1. \u4f18\u5316\u548c\u8c03\u6574\u8f93\u51fa<\/li>\n<\/ol>\n
      \u5728\u4f7f\u7528PyMuPDF\u65f6\uff0c\u6211\u4eec\u53ef\u4ee5\u6839\u636e\u9700\u6c42\u8c03\u6574\u8f93\u51fa\u56fe\u50cf\u7684\u5206\u8fa8\u7387\u548c\u8d28\u91cf\u3002\u53ef\u4ee5\u901a\u8fc7\u8bbe\u7f6epixmap<\/code>\u5bf9\u8c61\u7684\u53c2\u6570\u6765\u63a7\u5236\u8f93\u51fa\u56fe\u50cf\u7684\u5206\u8fa8\u7387\uff1a<\/p>\n<\/p>\n
      pix = page.get_pixmap(matrix=fitz.Matrix(2, 2))  # \u589e\u52a0\u5206\u8fa8\u7387<\/p>\n
      <\/code><\/pre>\n<\/p>\n
      \u901a\u8fc7\u8c03\u6574Matrix<\/code>\u7684\u53c2\u6570\uff0c\u53ef\u4ee5\u63d0\u9ad8\u56fe\u50cf\u6e05\u6670\u5ea6\uff0c\u4f46\u540c\u65f6\u4e5f\u4f1a\u589e\u52a0\u8f6c\u6362\u65f6\u95f4\u548c\u8f93\u51fa\u6587\u4ef6\u7684\u5927\u5c0f\u3002<\/p>\n<\/p>\n
      \u4e8c\u3001PDF2IMAGE\u5e93\u7684\u4f7f\u7528<\/p>\n<\/p>\n
      pdf2image\u662f\u4e00\u4e2a\u4e13\u95e8\u7528\u4e8e\u5c06PDF\u6587\u4ef6\u8f6c\u6362\u4e3a\u56fe\u50cf\u7684Python\u5e93\uff0c\u5b83\u53ef\u4ee5\u65b9\u4fbf\u5730\u5904\u7406\u591a\u9875PDF\u6587\u4ef6\u5e76\u5c06\u5176\u8f6c\u6362\u4e3a\u5404\u79cd\u56fe\u50cf\u683c\u5f0f\u3002<\/p>\n<\/p>\n
        \n
      1. \u5b89\u88c5\u548c\u57fa\u672c\u7528\u6cd5<\/li>\n<\/ol>\n
        \u9996\u5148\uff0c\u5b89\u88c5pdf2image\u5e93\uff1a<\/p>\n<\/p>\n
        pip install pdf2image<\/p>\n
        <\/code><\/pre>\n<\/p>\n
        \u6b64\u5916\uff0c\u8be5\u5e93\u4f9d\u8d56\u4e8ePoppler\u5de5\u5177\u5305\uff0c\u7528\u6237\u9700\u8981\u6839\u636e\u64cd\u4f5c\u7cfb\u7edf\u5b89\u88c5Poppler\u3002<\/p>\n<\/p>\n
        \u5728Linux\u4e0a\uff0c\u53ef\u4ee5\u4f7f\u7528\u5305\u7ba1\u7406\u5668\u5b89\u88c5\uff1a<\/p>\n<\/p>\n
        sudo apt-get install poppler-utils<\/p>\n
        <\/code><\/pre>\n<\/p>\n
        \u5728Windows\u4e0a\uff0c\u53ef\u4ee5\u4ecePoppler\u7684\u5b98\u65b9\u9875\u9762\u4e0b\u8f7d\u5e76\u914d\u7f6e\u73af\u5883\u53d8\u91cf\u3002<\/p>\n<\/p>\n
        \u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u4ee3\u7801\u8fdb\u884c\u8f6c\u6362\uff1a<\/p>\n<\/p>\n
        from pdf2image import convert_from_path<\/p>\n
        def pdf_to_png(pdf_path, output_path):<\/p>\n
            # \u5c06PDF\u8f6c\u6362\u4e3a\u56fe\u50cf<\/p>\n
            images = convert_from_path(pdf_path)<\/p>\n
            for i, image in enumerate(images):<\/p>\n
                # \u4fdd\u5b58\u56fe\u50cf<\/p>\n
                image.save(f"{output_path}\/page_{i + 1}.png", 'PNG')<\/p>\n
        pdf_to_png("example.pdf", "output_directory")<\/p>\n
        <\/code><\/pre>\n<\/p>\n
          \n
        1. \u53c2\u6570\u8c03\u6574\u548c\u6027\u80fd\u4f18\u5316<\/li>\n<\/ol>\n
          \u5728\u4f7f\u7528pdf2image\u65f6\uff0c\u53ef\u4ee5\u901a\u8fc7\u53c2\u6570\u6765\u63a7\u5236\u8f93\u51fa\u56fe\u50cf\u7684\u8d28\u91cf\u548c\u6027\u80fd\u3002\u5e38\u7528\u7684\u53c2\u6570\u5305\u62ec\uff1a<\/p>\n<\/p>\n