如何修复Python中的“ TypeError：无法在类似字节的对象上使用字符串模式”错误

Question

我正在尝试使用正则表达式抓取一些PDF。我在下面有以下代码：

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

def pdf_to_text(path):
    manager = PDFResourceManager()
    retstr = BytesIO()
    layout = LAParams(all_texts=True)
    device = TextConverter(manager, retstr, laparams=layout)
    filepath = open(path, 'rb')
    interpreter = PDFPageInterpreter(manager, device)

    for page in PDFPage.get_pages(filepath, check_extractable=False):
        interpreter.process_page(page)

    text = retstr.getvalue()

    filepath.close()
    device.close()
    retstr.close()
    return text

if __name__ == "__main__":
    text = pdf_to_text("C:\\Users\\User1\\Documents\\Python Scripts\\PDF Scraping\\123.pdf")
    regex = r"(?<=3\. Induction Training\n).*(?=4\. Corporate Training\/Departmental Training)"
    matches = re.finditer(regex, text, re.MULTILINE | re.DOTALL)
    print(text)

我遇到以下错误：

File "C:\Users\User1\AppData\Local\Continuum\anaconda3\lib\re.py", line 230, in finditer
    return _compile(pattern, flags).finditer(string)

TypeError: cannot use a string pattern on a bytes-like object

我不确定我的代码底部是否正确，有人可以指出我要去哪里了吗？

这是一个示例PDF：https://www.scribd.com/document/396797318/123