{"id":725,"date":"2026-02-12T11:54:53","date_gmt":"2026-02-12T03:54:53","guid":{"rendered":"https:\/\/qubitledge.com\/?p=725"},"modified":"2026-05-22T16:46:11","modified_gmt":"2026-05-22T08:46:11","slug":"csdc-pdf","status":"publish","type":"post","link":"https:\/\/qubitledge.com\/index.php\/2026\/02\/12\/csdc-pdf\/","title":{"rendered":"\u4e2d\u56fd\u767b\u8bb0\u7ed3\u7b97\u516c\u53f8\u80a1\u4efd\u67e5\u8be2-PDF\u6279\u91cf\u91cd\u547d\u540d\u5de5\u5177-\u5f00\u53d1\u8bb0\u5f55"},"content":{"rendered":"\n
\n
\n

GitHub\u9879\u76ee\u5730\u5740\uff1a<\/p>\n\n\n\n\u70b9\u51fb\u8fdb\u5165<\/a>\n<\/div>\n\n\n\n

<\/div>\n<\/div>\n\n\n\n

\u4e00\u3001\u9879\u76ee\u80cc\u666f<\/h2>\n\n\n\n

\u5728\u5904\u7406\u4e2d\u767b\u7cfb\u7edf\u5bfc\u51fa\u7684\u8bc1\u5238\u6301\u6709\u53d8\u66f4\u4fe1\u606fPDF\u65f6\uff0c\u9700\u8981\uff1a<\/p>\n\n\n\n

    \n
  • \u6279\u91cf\u8bfb\u53d6 PDF<\/li>\n\n\n\n
  • \u63d0\u53d6\uff1a\n
      \n
    • \u8bc1\u5238\u5b50\u8d26\u6237\u53f7\u7801<\/li>\n\n\n\n
    • \u6301\u6709\u4eba\u540d\u79f0<\/li>\n<\/ul>\n<\/li>\n\n\n\n
    • \u81ea\u52a8\u751f\u6210\u89c4\u8303\u547d\u540d\u6587\u4ef6<\/li>\n\n\n\n
    • \u4fdd\u7559\u539f\u6587\u4ef6<\/li>\n\n\n\n
    • \u8f93\u51fa\u81f3\u72ec\u7acb\u5b50\u6587\u4ef6\u5939<\/li>\n\n\n\n
    • \u652f\u6301\u62d6\u62fd\u6279\u91cf\u5904\u7406<\/li>\n<\/ul>\n\n\n\n

      \u4e3a\u63d0\u5347\u6548\u7387\uff0c\u5f00\u53d1\u672c\u5730\u79bb\u7ebf\u53ef\u6267\u884c\u5de5\u5177\u3002<\/p>\n\n\n\n

      \n\n\n\n

      \u4e8c\u3001\u529f\u80fd\u9700\u6c42\u8bf4\u660e<\/h2>\n\n\n\n

      1.\u8f93\u5165\u65b9\u5f0f<\/h3>\n\n\n\n

      \u652f\u6301\uff1a<\/p>\n\n\n\n

        \n
      • \u62d6\u62fd\u5355\u4e2a PDF<\/li>\n\n\n\n
      • \u62d6\u62fd\u591a\u4e2a PDF<\/li>\n\n\n\n
      • \u62d6\u62fd\u6587\u4ef6\u5939<\/li>\n\n\n\n
      • \u62d6\u62fd\u591a\u4e2a\u6587\u4ef6\u5939<\/li>\n\n\n\n
      • \u6df7\u5408\u62d6\u62fd<\/li>\n\n\n\n
      • \u53cc\u51fb\u8fd0\u884c\u540e\u5f39\u7a97\u9009\u62e9\u6587\u4ef6\u5939<\/li>\n<\/ul>\n\n\n\n

        2.\u547d\u540d\u89c4\u5219<\/h3>\n\n\n\n
        \u65b0\u6587\u4ef6\u540d = \u8bc1\u5238\u5b50\u8d26\u6237\u53f7\u7801-\u6301\u6709\u4eba\u540d\u79f0.pdf\n<\/pre>\n\n\n\n
        \u4f8b\u5982\uff1a<\/p>\n\n\n\n
        A290074561-\u674e\u5927\u5f3a.pdf\n<\/pre>\n\n\n\n
        3.\u8f93\u51fa\u89c4\u5219<\/h3>\n\n\n\n
          \n
        • \u4e0d\u4fee\u6539\u539f\u6587\u4ef6<\/li>\n\n\n\n
        • \u5728\u539f\u76ee\u5f55\u751f\u6210\u5b50\u6587\u4ef6\u5939\uff1a<\/li>\n<\/ul>\n\n\n\n
          \u5df2\u91cd\u547d\u540d\u8f93\u51fa\n<\/pre>\n\n\n\n
            \n
          • \u6240\u6709\u65b0\u6587\u4ef6\u590d\u5236\u5230\u8be5\u6587\u4ef6\u5939<\/li>\n\n\n\n
          • \u81ea\u52a8\u9632\u6b62\u91cd\u540d\uff1a<\/li>\n<\/ul>\n\n\n\n
            A290074561-\u674e\u5927\u5f3a(2).pdf\n<\/pre>\n\n\n\n
            4.\u65e5\u5fd7\u751f\u6210<\/h3>\n\n\n\n
            \u81ea\u52a8\u751f\u6210\uff1a<\/p>\n\n\n\n
            \u91cd\u547d\u540d\u65e5\u5fd7.csv\n<\/pre>\n\n\n\n
            \u5185\u5bb9\uff1a<\/p>\n\n\n\n
            | \u6e90\u6587\u4ef6\u540d | \u8f93\u51fa\u6587\u4ef6\u540d |<\/p>\n\n\n\n
            \n\n\n\n
            \u4e09\u3001\u6280\u672f\u5b9e\u73b0\u65b9\u6848<\/h2>\n\n\n\n
            \u6280\u672f\u6808<\/h3>\n\n\n\n
              \n
            • Python 3.13<\/li>\n\n\n\n
            • pdfplumber\uff08PDF\u6587\u672c\u89e3\u6790\uff09<\/li>\n\n\n\n
            • shutil\uff08\u6587\u4ef6\u590d\u5236\uff09<\/li>\n\n\n\n
            • PyInstaller\uff08\u6253\u5305EXE\uff09<\/li>\n<\/ul>\n\n\n\n
              \n\n\n\n
              \u56db\u3001\u6838\u5fc3\u4ee3\u7801\u5b9e\u73b0<\/h2>\n\n\n\n
              \u5b57\u6bb5\u63d0\u53d6\u903b\u8f91<\/h3>\n\n\n\n
              m1 = re.search(r\"\u8bc1\u5238\u5b50\u8d26\u6237\u53f7\u7801\\s*\uff1a\\s*([A-Za-z0-9]+)\", text)\nm2 = re.search(r\"\u6301\u6709\u4eba\u540d\u79f0\\s*\uff1a\\s*(\\S+)\", text)\n<\/pre>\n\n\n\n
              \u65b0\u6587\u4ef6\u540d\u751f\u6210<\/h3>\n\n\n\n
              new_filename = f\"{sub_account}-{holder}.pdf\"\n<\/pre>\n\n\n\n
              \u9632\u91cd\u540d\u673a\u5236<\/h3>\n\n\n\n
              A290074561-\u674e\u5927\u5f3a.pdf\nA290074561-\u674e\u5927\u5f3a(2).pdf\nA290074561-\u674e\u5927\u5f3a(3).pdf\n<\/pre>\n\n\n\n
              \u590d\u5236\u800c\u975e\u91cd\u547d\u540d<\/h3>\n\n\n\n
              shutil.copy2(src_path, dst_path)\n<\/pre>\n\n\n\n
              \u4fdd\u8bc1\uff1a<\/p>\n\n\n\n
                \n
              • \u539f\u6587\u4ef6\u4fdd\u7559<\/li>\n\n\n\n
              • \u65f6\u95f4\u6233\u4fdd\u7559<\/li>\n<\/ul>\n\n\n\n
                \n\n\n\n
                \u4e94\u3001\u5b8c\u6574\u6700\u7ec8\u811a\u672c<\/h2>\n\n\n\n
                import os\nimport sys\nimport re\nimport time\nimport csv\nimport shutil\nimport pdfplumber\n\nOUTPUT_DIR_NAME = \"\u5df2\u91cd\u547d\u540d\u8f93\u51fa\"\n\ndef pick_folder_dialog():\n    try:\n        import tkinter as tk\n        from tkinter import filedialog\n        root = tk.Tk()\n        root.withdraw()\n        root.attributes(\"-topmost\", True)\n        folder = filedialog.askdirectory(title=\"\u8bf7\u9009\u62e9\u8981\u5904\u7406\u7684PDF\u6587\u4ef6\u5939\")\n        root.destroy()\n        return folder\n    except Exception:\n        return \"\"\n\ndef extract_fields(pdf_path: str):\n    with pdfplumber.open(pdf_path) as pdf:\n        text = (pdf.pages[0].extract_text() or \"\")\n\n    # \u63d0\u53d6\u8bc1\u5238\u5b50\u8d26\u6237\u53f7\u7801\n    m1 = re.search(r\"\u8bc1\u5238\u5b50\u8d26\u6237\u53f7\u7801\\s*\uff1a\\s*([A-Za-z0-9]+)\", text)\n    sub_account = m1.group(1) if m1 else \"\"\n\n    # \u63d0\u53d6\u6301\u6709\u4eba\u540d\u79f0\n    m2 = re.search(r\"\u6301\u6709\u4eba\u540d\u79f0\\s*\uff1a\\s*(\\S+)\", text)\n    holder_name = m2.group(1) if m2 else \"\"\n\n    return sub_account, holder_name\n\ndef safe_target_path(folder: str, filename: str) -> str:\n    target = os.path.join(folder, filename)\n    if not os.path.exists(target):\n        return target\n\n    base, ext = os.path.splitext(filename)\n    k = 2\n    while True:\n        new_name = f\"{base}({k}){ext}\"\n        new_path = os.path.join(folder, new_name)\n        if not os.path.exists(new_path):\n            return new_path\n        k += 1\n\ndef collect_pdfs_from_folder(folder: str):\n    return [\n        os.path.join(folder, n)\n        for n in os.listdir(folder)\n        if n.lower().endswith(\".pdf\")\n    ]\n\ndef process_pdf_files(pdf_files):\n    by_folder = {}\n    for p in pdf_files:\n        by_folder.setdefault(os.path.dirname(p), []).append(p)\n\n    for src_folder, files in by_folder.items():\n        out_folder = os.path.join(src_folder, OUTPUT_DIR_NAME)\n        os.makedirs(out_folder, exist_ok=True)\n\n        print(f\"\\n\u6765\u6e90\u76ee\u5f55: {src_folder}\")\n        print(f\"\u8f93\u51fa\u76ee\u5f55: {out_folder}\")\n        print(\"-\" * 60)\n\n        records = []\n        ok = 0\n\n        for src_path in files:\n            src_name = os.path.basename(src_path)\n\n            try:\n                sub_account, holder = extract_fields(src_path)\n\n                if not sub_account:\n                    print(f\"\u672a\u627e\u5230\u8bc1\u5238\u5b50\u8d26\u6237\u53f7\u7801: {src_name}\")\n                    continue\n                if not holder:\n                    print(f\"\u672a\u627e\u5230\u6301\u6709\u4eba\u540d\u79f0: {src_name}\")\n                    continue\n\n                new_filename = f\"{sub_account}-{holder}.pdf\"\n                dst_path = safe_target_path(out_folder, new_filename)\n\n                shutil.copy2(src_path, dst_path)\n\n                records.append([src_name, os.path.basename(dst_path)])\n                print(f\"\u5df2\u751f\u6210: {os.path.basename(dst_path)}\")\n                ok += 1\n\n            except Exception as e:\n                print(f\"\u5904\u7406\u5931\u8d25: {src_name} | {e}\")\n\n        log_path = os.path.join(out_folder, \"\u91cd\u547d\u540d\u65e5\u5fd7.csv\")\n        try:\n            with open(log_path, \"w\", newline=\"\", encoding=\"utf-8-sig\") as f:\n                w = csv.writer(f)\n                w.writerow([\"\u6e90\u6587\u4ef6\u540d\", \"\u8f93\u51fa\u6587\u4ef6\u540d\"])\n                w.writerows(records)\n        except Exception as e:\n            print(f\"\u5199\u65e5\u5fd7\u5931\u8d25: {e}\")\n\n        print(\"\\n\u5b8c\u6210\uff1a\u6210\u529f\u8f93\u51fa\", ok, \"\u4e2a\u6587\u4ef6\")\n        print(\"\u65e5\u5fd7\u4f4d\u7f6e:\", log_path)\n\ndef main():\n    args = sys.argv[1:]\n\n    if not args:\n        folder = pick_folder_dialog()\n        if folder:\n            process_pdf_files(collect_pdfs_from_folder(folder))\n        else:\n            print(\"\u672a\u9009\u62e9\u6587\u4ef6\u5939\u3002\")\n        input(\"\\n\u6309\u56de\u8f66\u9000\u51fa...\")\n        return\n\n    all_pdfs = []\n    for raw in args:\n        p = raw.strip('\"')\n        if os.path.isdir(p):\n            all_pdfs.extend(collect_pdfs_from_folder(p))\n        elif os.path.isfile(p) and p.lower().endswith(\".pdf\"):\n            all_pdfs.append(os.path.abspath(p))\n        else:\n            print(f\"\u8df3\u8fc7: {p}\")\n\n    if not all_pdfs:\n        print(\"\u672a\u627e\u5230\u53ef\u5904\u7406\u7684PDF\u6587\u4ef6\u3002\")\n        input(\"\\n\u6309\u56de\u8f66\u9000\u51fa...\")\n        return\n\n    process_pdf_files(all_pdfs)\n    input(\"\\n\u5168\u90e8\u5904\u7406\u5b8c\u6210\uff0c\u6309\u56de\u8f66\u9000\u51fa...\")\n\nif __name__ == \"__main__\":\n    main()\n<\/pre>\n\n\n\n
                \n\n\n\n
                \u516d\u3001\u6253\u5305EXE\u6d41\u7a0b<\/h2>\n\n\n\n
                1.\u521b\u5efa\u5e72\u51c0\u865a\u62df\u73af\u5883<\/h3>\n\n\n\n
                python -m venv packenv\n.\\packenv\\Scripts\\activate\npip install -U pip\npip install pyinstaller pdfplumber\n<\/pre>\n\n\n\n
                2.\u6253\u5305\u547d\u4ee4<\/h3>\n\n\n\n
                pyinstaller --onefile --console --clean --noconfirm rename_pdf_drag.py -n PDF\u91cd\u547d\u540d\u5de5\u5177\n<\/pre>\n\n\n\n
                3.\u8f93\u51fa\u7ed3\u679c<\/h3>\n\n\n\n
                \u751f\u6210\uff1a<\/p>\n\n\n\n
                dist\\PDF\u91cd\u547d\u540d\u5de5\u5177.exe\n<\/pre>\n\n\n\n
                \n\n\n\n
                \u4e03\u3001\u5e38\u89c1\u95ee\u9898\u53ca\u89e3\u51b3\u65b9\u6848<\/h2>\n\n\n\n
                1.\u62d6\u62fd\u65e0\u53cd\u5e94<\/h3>\n\n\n\n
                \u539f\u56e0\uff1a<\/p>\n\n\n\n
                  \n
                • \u4f7f\u7528\u7ba1\u7406\u5458\u8fd0\u884c<\/li>\n\n\n\n
                • \u62d6\u62fd\u65b9\u5f0f\u9519\u8bef<\/li>\n<\/ul>\n\n\n\n
                  \u89e3\u51b3\uff1a<\/p>\n\n\n\n
                    \n
                  • \u4e0d\u8981\u4ee5\u7ba1\u7406\u5458\u8eab\u4efd\u8fd0\u884c<\/li>\n\n\n\n
                  • \u76f4\u63a5\u62d6\u6587\u4ef6\/\u6587\u4ef6\u5939\u5230exe\u56fe\u6807<\/li>\n<\/ul>\n\n\n\n
                    2.\u6253\u5305\u5361\u5728 PKG \u9636\u6bb5<\/h3>\n\n\n\n
                    \u539f\u56e0\uff1a<\/p>\n\n\n\n
                      \n
                    • \u5168\u5c40\u73af\u5883\u5305\u542b torch \/ pandas \/ scipy \u7b49\u5927\u578b\u5e93<\/li>\n<\/ul>\n\n\n\n
                      \u89e3\u51b3\uff1a<\/p>\n\n\n\n
                        \n
                      • \u4f7f\u7528\u5e72\u51c0 venv \u6253\u5305<\/li>\n<\/ul>\n\n\n\n
                        3. dist \u6587\u4ef6\u5939\u4e3a\u7a7a<\/h3>\n\n\n\n
                        \u53ef\u80fd\uff1a<\/p>\n\n\n\n
                          \n
                        • \u6740\u6bd2\u8f6f\u4ef6\u62e6\u622a<\/li>\n\n\n\n
                        • \u6253\u5305\u672a\u5b8c\u6210<\/li>\n<\/ul>\n\n\n\n
                          \n\n\n\n
                          \u516b\u3001\u6700\u7ec8\u76ee\u5f55\u7ed3\u6784\u793a\u4f8b<\/h2>\n\n\n\n
                          \u67d0\u76ee\u5f55\n\u251c\u2500\u2500 \u539fPDF\u6587\u4ef6\n\u251c\u2500\u2500 \u5df2\u91cd\u547d\u540d\u8f93\u51fa\n\u2502   \u251c\u2500\u2500 A290074561-\u674e\u5927\u5f3a.pdf\n\u2502   \u251c\u2500\u2500 \u91cd\u547d\u540d\u65e5\u5fd7.csv\n<\/pre>\n\n\n\n
                          \n\n\n\n
                          \u4e5d\u3001\u5b89\u5168\u4e0e\u5408\u89c4\u8bf4\u660e<\/h2>\n\n\n\n
                            \n
                          • \u672c\u5de5\u5177\u5b8c\u5168\u672c\u5730\u8fd0\u884c<\/li>\n\n\n\n
                          • \u4e0d\u8054\u7f51<\/li>\n\n\n\n
                          • \u4e0d\u4e0a\u4f20\u6570\u636e<\/li>\n\n\n\n
                          • \u9002\u7528\u4e8e\u8bc1\u5238\u767b\u8bb0\u7c7b\u654f\u611f\u6587\u4ef6\u7684\u5185\u7f51\u5904\u7406<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"
                            \u4e3a\u63d0\u5347\u6548\u7387\uff0c\u5f00\u53d1\u7684\u672c\u5730\u79bb\u7ebf\u53ef\u6267\u884c\u5de5\u5177\uff0c\u53ef\u6279\u91cf\u5904\u7406\u4e2d\u767b\u7cfb\u7edf\u5bfc\u51fa\u7684\u8bc1\u5238\u6301\u6709\u53d8\u66f4\u4fe1\u606fPDF<\/p>\n","protected":false},"author":1,"featured_media":726,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[22],"tags":[16],"class_list":["post-725","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-22","tag-16"],"_links":{"self":[{"href":"https:\/\/qubitledge.com\/index.php\/wp-json\/wp\/v2\/posts\/725","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/qubitledge.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/qubitledge.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/qubitledge.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/qubitledge.com\/index.php\/wp-json\/wp\/v2\/comments?post=725"}],"version-history":[{"count":29,"href":"https:\/\/qubitledge.com\/index.php\/wp-json\/wp\/v2\/posts\/725\/revisions"}],"predecessor-version":[{"id":774,"href":"https:\/\/qubitledge.com\/index.php\/wp-json\/wp\/v2\/posts\/725\/revisions\/774"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/qubitledge.com\/index.php\/wp-json\/wp\/v2\/media\/726"}],"wp:attachment":[{"href":"https:\/\/qubitledge.com\/index.php\/wp-json\/wp\/v2\/media?parent=725"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/qubitledge.com\/index.php\/wp-json\/wp\/v2\/categories?post=725"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/qubitledge.com\/index.php\/wp-json\/wp\/v2\/tags?post=725"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}