NLP용 Python: PDF 파일에서 각주와 미주를 추출하고 분석하는 방법은 무엇입니까?

pip install PyPDF2
pip install pdfminer.six
pip install nltk

import PyPDF2
from pdfminer.high_level import extract_text
import nltk
nltk.download('punkt')

# 使用PyPDF2库提取文本
def extract_text_pypdf2(file_path):
    pdf_file = open(file_path, 'rb')
    pdf_reader = PyPDF2.PdfFileReader(pdf_file)
    num_pages = pdf_reader.numPages
    text = ""
    for page in range(num_pages):
        page_obj = pdf_reader.getPage(page)
        text += page_obj.extractText()
    return text

# 使用pdfminer.six库提取文本
def extract_text_pdfminer(file_path):
    return extract_text(file_path)

def extract_footnotes(text):
    paragraphs = text.split('

')
    footnotes = ""
    for paragraph in paragraphs:
        tokens = nltk.sent_tokenize(paragraph)
        for token in tokens:
            if token.endswith(('1', '2', '3', '4', '5', '6', '7', '8', '9')):
                footnotes += token + "
"
    return footnotes

def extract_endnotes(text):
    paragraphs = text.split('

')
    endnotes = ""
    for paragraph in paragraphs:
        tokens = nltk.sent_tokenize(paragraph)
        for token in tokens:
            if token.endswith(('i', 'ii', 'iii', 'iv', 'v', 'vi', 'vii', 'viii', 'ix')):
                endnotes += token + "
"
    return endnotes

def main(file_path):
    text = extract_text_pdfminer(file_path)
    footnotes = extract_footnotes(text)
    endnotes = extract_endnotes(text)
    print("脚注：")
    print(footnotes)
    print("尾注：")
    print(endnotes)

if __name__ == "__main__":
    file_path = "example.pdf"
    main(file_path)