python实现pdf转word,利用python进行数据分析 第三版 pdf

文章目录 背景需求环境安装完整代码效果

背景需求

已经获取到了大量的pdf在download文件夹中但是我需要的是txt文件和word文件

环境安装

pip install pdf2docx pdfminer.six

完整代码

# pip install pdf2docx pdfminer.siximport osfrom pdf2docx import Converterfrom pdfminer.high_level import extract_text# 忽略警告import warningswarnings.filterwarnings(ignore, categoryUserWarning, modulepdf2docx)# pdf转txtdef pdf_to_txt(pdf_path, txt_path):    text  extract_text(pdf_path)    with open(txt_path, w, encodingutf-8) as f:        f.write(text)# pdf转worddef pdf_to_docx(pdf_path, docx_path):    cv  Converter(pdf_path)    cv.convert(docx_path, start0, endNone)    cv.close()# 分批转换文件格式检测def batch_convert(download_folder, data_folder, output_formattxt):    # 确保输出文件夹存在    if not os.path.exists(data_folder):        os.makedirs(data_folder)    # 遍历download文件夹中的所有PDF文件    for filename in os.listdir(download_folder):        if filename.endswith(.pdf):            pdf_path  os.path.join(download_folder, filename)            if output_format  txt:                txt_filename  os.path.splitext(filename)[0]  .txt                txt_path  os.path.join(data_folder, txt_filename)                pdf_to_txt(pdf_path, txt_path)            elif output_format  docx:                docx_filename  os.path.splitext(filename)[0]  .docx                docx_path  os.path.join(data_folder, docx_filename)                pdf_to_docx(pdf_path, docx_path)# 转换txtbatch_convert(download, data_txt, output_formattxt)# 转换word文件batch_convert(download, data_docx, output_formatdocx)

效果