{"id":1172983,"date":"2025-01-15T16:57:13","date_gmt":"2025-01-15T08:57:13","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1172983.html"},"modified":"2025-01-15T16:57:16","modified_gmt":"2025-01-15T08:57:16","slug":"python%e5%a6%82%e4%bd%95%e7%bb%99pdf%e6%89%b9%e9%87%8f%e5%91%bd%e5%90%8d","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1172983.html","title":{"rendered":"python\u5982\u4f55\u7ed9pdf\u6279\u91cf\u547d\u540d"},"content":{"rendered":"

\"python\u5982\u4f55\u7ed9pdf\u6279\u91cf\u547d\u540d\"<\/p>\n

\u5728Python\u4e2d\u7ed9PDF\u6279\u91cf\u547d\u540d\u53ef\u4ee5\u901a\u8fc7\u51e0\u4e2a\u5173\u952e\u6b65\u9aa4\u6765\u5b9e\u73b0\uff1a\u904d\u5386\u6307\u5b9a\u76ee\u5f55\u3001\u8bfb\u53d6PDF\u6587\u4ef6\u3001\u751f\u6210\u65b0\u7684\u6587\u4ef6\u540d\u3001\u91cd\u547d\u540d\u6587\u4ef6<\/strong>\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u5b9e\u73b0\u8fd9\u4e9b\u6b65\u9aa4\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u904d\u5386\u6307\u5b9a\u76ee\u5f55<\/h3>\n<\/p>\n

\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u904d\u5386\u6307\u5b9a\u7684\u76ee\u5f55\u6765\u83b7\u53d6\u6240\u6709\u7684PDF\u6587\u4ef6\u3002\u53ef\u4ee5\u4f7f\u7528os<\/code>\u6a21\u5757\u6765\u5b9e\u73b0\u8fd9\u4e00\u529f\u80fd\u3002<\/p>\n<\/p>\n

import os<\/p>\n
def get_pdf_files(directory):<\/p>\n
    pdf_files = []<\/p>\n
    for root, dirs, files in os.walk(directory):<\/p>\n
        for file in files:<\/p>\n
            if file.endswith(".pdf"):<\/p>\n
                pdf_files.append(os.path.join(root, file))<\/p>\n
    return pdf_files<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u8bfb\u53d6PDF\u6587\u4ef6<\/h3>\n<\/p>\n
\u4e3a\u4e86\u8bfb\u53d6PDF\u6587\u4ef6\u7684\u5185\u5bb9\u6216\u5143\u6570\u636e\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528PyPDF2<\/code>\u5e93\u3002\u8fd9\u4e2a\u5e93\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u63d0\u53d6PDF\u6587\u4ef6\u7684\u6807\u9898\u3001\u4f5c\u8005\u7b49\u4fe1\u606f\uff0c\u8fd9\u4e9b\u4fe1\u606f\u53ef\u4ee5\u7528\u6765\u751f\u6210\u65b0\u7684\u6587\u4ef6\u540d\u3002<\/p>\n<\/p>\n
import PyPDF2<\/p>\n
def get_pdf_info(pdf_path):<\/p>\n
    with open(pdf_path, "rb") as f:<\/p>\n
        reader = PyPDF2.PdfFileReader(f)<\/p>\n
        info = reader.getDocumentInfo()<\/p>\n
    return info<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u751f\u6210\u65b0\u7684\u6587\u4ef6\u540d<\/h3>\n<\/p>\n
\u751f\u6210\u65b0\u7684\u6587\u4ef6\u540d\u53ef\u4ee5\u6839\u636e\u9700\u6c42\u6765\u51b3\u5b9a\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u6839\u636ePDF\u7684\u6807\u9898\u548c\u4f5c\u8005\u6765\u751f\u6210\u6587\u4ef6\u540d\u3002<\/p>\n<\/p>\n
def generate_new_name(info):<\/p>\n
    title = info.title if info.title else "Untitled"<\/p>\n
    author = info.author if info.author else "Unknown"<\/p>\n
    new_name = f"{title}_{author}.pdf"<\/p>\n
    return new_name<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u91cd\u547d\u540d\u6587\u4ef6<\/h3>\n<\/p>\n
\u6700\u540e\u4e00\u6b65\u662f\u91cd\u547d\u540d\u6587\u4ef6\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528os.rename<\/code>\u51fd\u6570\u6765\u5b9e\u73b0\u8fd9\u4e00\u529f\u80fd\u3002<\/p>\n<\/p>\n
def rename_pdf_files(directory):<\/p>\n
    pdf_files = get_pdf_files(directory)<\/p>\n
    for pdf_path in pdf_files:<\/p>\n
        info = get_pdf_info(pdf_path)<\/p>\n
        new_name = generate_new_name(info)<\/p>\n
        new_path = os.path.join(os.path.dirname(pdf_path), new_name)<\/p>\n
        os.rename(pdf_path, new_path)<\/p>\n
        print(f"Renamed {pdf_path} to {new_path}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u5b8c\u6574\u4ee3\u7801\u793a\u4f8b<\/h3>\n<\/p>\n
\u7efc\u5408\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u4e0b\u9762\u662f\u4e00\u4e2a\u5b8c\u6574\u7684\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
import os<\/p>\n
import PyPDF2<\/p>\n
def get_pdf_files(directory):<\/p>\n
    pdf_files = []<\/p>\n
    for root, dirs, files in os.walk(directory):<\/p>\n
        for file in files:<\/p>\n
            if file.endswith(".pdf"):<\/p>\n
                pdf_files.append(os.path.join(root, file))<\/p>\n
    return pdf_files<\/p>\n
def get_pdf_info(pdf_path):<\/p>\n
    with open(pdf_path, "rb") as f:<\/p>\n
        reader = PyPDF2.PdfFileReader(f)<\/p>\n
        info = reader.getDocumentInfo()<\/p>\n
    return info<\/p>\n
def generate_new_name(info):<\/p>\n
    title = info.title if info.title else "Untitled"<\/p>\n
    author = info.author if info.author else "Unknown"<\/p>\n
    new_name = f"{title}_{author}.pdf"<\/p>\n
    return new_name<\/p>\n
def rename_pdf_files(directory):<\/p>\n
    pdf_files = get_pdf_files(directory)<\/p>\n
    for pdf_path in pdf_files:<\/p>\n
        info = get_pdf_info(pdf_path)<\/p>\n
        new_name = generate_new_name(info)<\/p>\n
        new_path = os.path.join(os.path.dirname(pdf_path), new_name)<\/p>\n
        os.rename(pdf_path, new_path)<\/p>\n
        print(f"Renamed {pdf_path} to {new_path}")<\/p>\n
if __name__ == "__mAI<\/a>n__":<\/p>\n
    directory = "path\/to\/your\/pdf\/folder"<\/p>\n
    rename_pdf_files(directory)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u8fdb\u4e00\u6b65\u4f18\u5316<\/h3>\n<\/p>\n
\u4e0a\u8ff0\u4ee3\u7801\u53ea\u662f\u4e00\u4e2a\u57fa\u7840\u5b9e\u73b0\uff0c\u5b9e\u9645\u5e94\u7528\u4e2d\u53ef\u80fd\u9700\u8981\u8fdb\u4e00\u6b65\u4f18\u5316\uff0c\u4f8b\u5982\uff1a<\/p>\n<\/p>\n
    \n
  1. \u5904\u7406\u6587\u4ef6\u540d\u51b2\u7a81<\/strong>\uff1a\u5982\u679c\u65b0\u751f\u6210\u7684\u6587\u4ef6\u540d\u5df2\u7ecf\u5b58\u5728\uff0c\u9700\u8981\u5904\u7406\u6587\u4ef6\u540d\u51b2\u7a81\uff0c\u53ef\u4ee5\u5728\u6587\u4ef6\u540d\u540e\u6dfb\u52a0\u5e8f\u53f7\u3002<\/li>\n
  2. \u5f02\u5e38\u5904\u7406<\/strong>\uff1a\u6dfb\u52a0\u5f02\u5e38\u5904\u7406\u4ee3\u7801\u6765\u5904\u7406\u53ef\u80fd\u51fa\u73b0\u7684\u9519\u8bef\uff0c\u5982\u6587\u4ef6\u8bfb\u53d6\u5931\u8d25\u3001\u6743\u9650\u95ee\u9898\u7b49\u3002<\/li>\n
  3. \u65e5\u5fd7\u8bb0\u5f55<\/strong>\uff1a\u6dfb\u52a0\u65e5\u5fd7\u8bb0\u5f55\u529f\u80fd\uff0c\u8bb0\u5f55\u6bcf\u4e2a\u6587\u4ef6\u7684\u91cd\u547d\u540d\u64cd\u4f5c\uff0c\u4fbf\u4e8e\u540e\u7eed\u67e5\u627e\u548c\u7ef4\u62a4\u3002<\/li>\n<\/ol>\n
    \u5904\u7406\u6587\u4ef6\u540d\u51b2\u7a81<\/h3>\n<\/p>\n
    def generate_unique_name(directory, name):<\/p>\n
        base, ext = os.path.splitext(name)<\/p>\n
        counter = 1<\/p>\n
        unique_name = name<\/p>\n
        while os.path.exists(os.path.join(directory, unique_name)):<\/p>\n
            unique_name = f"{base}_{counter}{ext}"<\/p>\n
            counter += 1<\/p>\n
        return unique_name<\/p>\n
    <\/code><\/pre>\n<\/p>\n
    \u6dfb\u52a0\u5f02\u5e38\u5904\u7406<\/h3>\n<\/p>\n
    def rename_pdf_files(directory):<\/p>\n
        pdf_files = get_pdf_files(directory)<\/p>\n
        for pdf_path in pdf_files:<\/p>\n
            try:<\/p>\n
                info = get_pdf_info(pdf_path)<\/p>\n
                new_name = generate_new_name(info)<\/p>\n
                new_name = generate_unique_name(os.path.dirname(pdf_path), new_name)<\/p>\n
                new_path = os.path.join(os.path.dirname(pdf_path), new_name)<\/p>\n
                os.rename(pdf_path, new_path)<\/p>\n
                print(f"Renamed {pdf_path} to {new_path}")<\/p>\n
            except Exception as e:<\/p>\n
                print(f"Failed to rename {pdf_path}: {e}")<\/p>\n
    <\/code><\/pre>\n<\/p>\n
    \u6dfb\u52a0\u65e5\u5fd7\u8bb0\u5f55<\/h3>\n<\/p>\n
    import logging<\/p>\n
    logging.basicConfig(filename='rename_log.log', level=logging.INFO)<\/p>\n
    def rename_pdf_files(directory):<\/p>\n
        pdf_files = get_pdf_files(directory)<\/p>\n
        for pdf_path in pdf_files:<\/p>\n
            try:<\/p>\n
                info = get_pdf_info(pdf_path)<\/p>\n
                new_name = generate_new_name(info)<\/p>\n
                new_name = generate_unique_name(os.path.dirname(pdf_path), new_name)<\/p>\n
                new_path = os.path.join(os.path.dirname(pdf_path), new_name)<\/p>\n
                os.rename(pdf_path, new_path)<\/p>\n
                logging.info(f"Renamed {pdf_path} to {new_path}")<\/p>\n
            except Exception as e:<\/p>\n
                logging.error(f"Failed to rename {pdf_path}: {e}")<\/p>\n
    <\/code><\/pre>\n<\/p>\n
    \u901a\u8fc7\u8fd9\u4e9b\u6b65\u9aa4\u548c\u4f18\u5316\uff0c\u4f60\u53ef\u4ee5\u66f4\u7a33\u5065\u5730\u5b9e\u73b0PDF\u6587\u4ef6\u7684\u6279\u91cf\u91cd\u547d\u540d\u529f\u80fd\u3002\u5e0c\u671b\u8fd9\u4e9b\u5185\u5bb9\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\u3002<\/p>\n<\/p>\n
    \u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
     \u5982\u4f55\u4f7f\u7528Python\u5bf9\u591a\u4e2aPDF\u6587\u4ef6\u8fdb\u884c\u6279\u91cf\u91cd\u547d\u540d\uff1f<\/strong>
    \u5728Python\u4e2d\uff0c\u60a8\u53ef\u4ee5\u4f7f\u7528os<\/code>\u6a21\u5757\u548cPyPDF2<\/code>\u5e93\u6765\u6279\u91cf\u91cd\u547d\u540dPDF\u6587\u4ef6\u3002\u9996\u5148\uff0c\u786e\u4fdd\u60a8\u5df2\u5b89\u88c5\u4e86PyPDF2<\/code>\u5e93\u3002\u63a5\u4e0b\u6765\uff0c\u60a8\u53ef\u4ee5\u4f7f\u7528os.listdir()<\/code>\u5217\u51fa\u76ee\u6807\u6587\u4ef6\u5939\u4e2d\u7684\u6240\u6709PDF\u6587\u4ef6\uff0c\u5e76\u6839\u636e\u9700\u8981\u4f7f\u7528os.rename()<\/code>\u6765\u91cd\u547d\u540d\u5b83\u4eec\u3002\u4ee3\u7801\u793a\u4f8b\u5982\u4e0b\uff1a<\/p>\n
    import os\n\nfolder_path = 'path\/to\/your\/pdf\/folder'\nfor index, filename in enumerate(os.listdir(folder_path)):\n    if filename.endswith('.pdf'):\n        new_name = f"document_{index + 1}.pdf"\n        os.rename(os.path.join(folder_path, filename), os.path.join(folder_path, new_name))\n<\/code><\/pre>\n
    \u6b64\u4ee3\u7801\u5c06PDF\u6587\u4ef6\u91cd\u547d\u540d\u4e3adocument_1.pdf<\/code>\u3001document_2.pdf<\/code>\u7b49\u3002<\/p>\n
    \u5728\u6279\u91cf\u91cd\u547d\u540d\u65f6\uff0c\u5982\u4f55\u786e\u4fdd\u6587\u4ef6\u540d\u7684\u552f\u4e00\u6027\uff1f<\/strong>
    \u5728\u6279\u91cf\u91cd\u547d\u540dPDF\u6587\u4ef6\u65f6\uff0c\u4e3a\u4e86\u907f\u514d\u6587\u4ef6\u540d\u91cd\u590d\uff0c\u53ef\u4ee5\u5728\u65b0\u6587\u4ef6\u540d\u4e2d\u52a0\u5165\u65f6\u95f4\u6233\u6216\u968f\u673a\u6570\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528datetime<\/code>\u6a21\u5757\u83b7\u53d6\u5f53\u524d\u65f6\u95f4\uff0c\u6216\u4f7f\u7528random<\/code>\u6a21\u5757\u751f\u6210\u968f\u673a\u6570\u3002\u8fd9\u6837\u5373\u4f7f\u5728\u540c\u4e00\u6587\u4ef6\u5939\u5185\uff0c\u751f\u6210\u7684\u6587\u4ef6\u540d\u4e5f\u4e0d\u4f1a\u91cd\u590d\u3002<\/p>\n
    \u6709\u6ca1\u6709\u63a8\u8350\u7684Python\u5e93\u53ef\u4ee5\u5e2e\u52a9\u6211\u5904\u7406PDF\u6587\u4ef6\uff1f<\/strong>
    \u9664\u4e86PyPDF2<\/code>\uff0c\u8fd8\u6709\u5176\u4ed6\u4e00\u4e9b\u4f18\u79c0\u7684Python\u5e93\u53ef\u4ee5\u7528\u4e8e\u5904\u7406PDF\u6587\u4ef6\uff0c\u5982pdfplumber<\/code>\u3001reportlab<\/code>\u3001\u548cpdfrw<\/code>\u3002\u8fd9\u4e9b\u5e93\u63d0\u4f9b\u4e86\u4e0d\u540c\u7684\u529f\u80fd\uff0c\u4f8b\u5982\u4ecePDF\u4e2d\u63d0\u53d6\u6587\u672c\u3001\u5408\u5e76\u591a\u4e2aPDF\u6587\u4ef6\u6216\u521b\u5efa\u65b0\u7684PDF\u6587\u4ef6\u3002\u6839\u636e\u60a8\u7684\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u5e93\uff0c\u53ef\u4ee5\u5e2e\u52a9\u60a8\u66f4\u52a0\u9ad8\u6548\u5730\u7ba1\u7406PDF\u6587\u4ef6\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\u7ed9PDF\u6279\u91cf\u547d\u540d\u53ef\u4ee5\u901a\u8fc7\u51e0\u4e2a\u5173\u952e\u6b65\u9aa4\u6765\u5b9e\u73b0\uff1a\u904d\u5386\u6307\u5b9a\u76ee\u5f55\u3001\u8bfb\u53d6PDF\u6587\u4ef6\u3001\u751f\u6210\u65b0\u7684\u6587\u4ef6\u540d\u3001\u91cd\u547d […]","protected":false},"author":3,"featured_media":1172987,"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\/1172983"}],"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=1172983"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1172983\/revisions"}],"predecessor-version":[{"id":1172988,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1172983\/revisions\/1172988"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1172987"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1172983"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1172983"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1172983"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}