python读取pdf文字

import PyPDF2

def read_pdf_text(file_path):
    with open(file_path, 'rb') as file:
        pdf_reader = PyPDF2.PdfFileReader(file)
        num_pages = pdf_reader.numPages
        text = ''
        for page_num in range(num_pages):
            page = pdf_reader.getPage(page_num)
            text += page.extractText()
    return text

# 调用函数读取PDF文字
pdf_text = read_pdf_text('example.pdf')
print(pdf_text)

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

def read_pdf_text(file_path):
    resource_manager = PDFResourceManager()
    return_string = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(resource_manager, return_string, codec=codec, laparams=laparams)
    with open(file_path, 'rb') as file:
        interpreter = PDFPageInterpreter(resource_manager, device)
        for page in PDFPage.get_pages(file):
            interpreter.process_page(page)
    text = return_string.getvalue()
    device.close()
    return_string.close()
    return text

# 调用函数读取PDF文字
pdf_text = read_pdf_text('example.pdf')
print(pdf_text)