如何用Python for NLP处理含有小字体文本的PDF文件？

pip install PyPDF2
pip install pdfminer.six

import PyPDF2
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from io import StringIO

def extract_text_from_pdf(file_path):
    text = ''
    with open(file_path, 'rb') as file:
        pdf_reader = PyPDF2.PdfReader(file)
        for page_num in range(len(pdf_reader.pages)):
            page_obj = pdf_reader.pages[page_num]
            page_text = page_obj.extract_text()
            text += page_text
    return text

def extract_text_from_pdf_with_pdfminer(file_path):
    text = ''
    rsrcmgr = PDFResourceManager()
    sio = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    laparams.all_texts = True
    converter = TextConverter(rsrcmgr, sio, codec=codec, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, converter)

    with open(file_path, 'rb') as file:
        for page in PDFPage.get_pages(file):
            interpreter.process_page(page)

        text = sio.getvalue()

    converter.close()
    sio.close()

    return text

# 测试代码
pdf_file = '小字体文本.pdf'
extracted_text = extract_text_from_pdf(pdf_file)
print(extracted_text)

extracted_text_with_pdfminer = extract_text_from_pdf_with_pdfminer(pdf_file)
print(extracted_text_with_pdfminer)