input_folder = D南巢第六学期大数据与会计分析贵州茅台财务分析年报output_folder = D南巢第六学期大数据与会计分析贵州茅台财务分析年报for pdf_file in globglobospathjoininput_folder pdf with openpdf_file rb as f pdf_reader = PyPDF2PdfReaderf

input_folder = "D:\南巢\第六学期\大数据与会计分析\贵州茅台财务分析\年报" output_folder = "D:\南巢\第六学期\大数据与会计分析\贵州茅台财务分析\年报"

for pdf_file in glob.glob(os.path.join(input_folder, "*.pdf")): with open(pdf_file, "rb") as f: pdf_reader = PyPDF2.PdfReader(f) for i in range(len(pdf_reader.pages)): page = pdf_reader.pages[i] text = '\n'.join(page.extract_text()) output_file = os.path.splitext(os.path.basename(pdf_file))[0] + ".txt" output_file = output_file.replace("年报", "第{}页".format(i+1)) with open(os.path.join(output_folder, output_file), "w", encoding="utf-8") as f: f.write(text