使用Python 3从PDF解析中提取标题和子标题

import PyPDF2

def extract_titles_from_pdf(pdf_path):
    with open(pdf_path, 'rb') as file:
        pdf_reader = PyPDF2.PdfFileReader(file)
        num_pages = pdf_reader.numPages

        titles = []

        for page_number in range(num_pages):
            page = pdf_reader.getPage(page_number)
            text = page.extractText()

            # 提取标题和子标题
            lines = text.split('\n')
            for line in lines:
                line = line.strip()
                if line:
                    if line.isupper():
                        # 大写字母一般表示标题
                        titles.append(line)
                    else:
                        # 非大写字母一般表示子标题
                        titles.append(line)

    return titles

pdf_path = 'example.pdf'
titles = extract_titles_from_pdf(pdf_path)
print(titles)