将每个pdf从目录传递到函数，并获取每个pdf的输出作为新的txt文件

Question

我写了一个函数，可以将目录中的每个pdf转换为文本，我想从pdf的txt文件中获取转换后的文本。我正在

"TypeError: expected str, bytes or os.PathLike object, not tuple".

有人可以帮我吗？在此处附加代码：

import io
import os
import os.path
from pdfminer.converter import TextConverter
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfpage import PDFPage

def extract_text_from_pdf(pdf_path):
    resource_manager = PDFResourceManager()
    fake_file_handle = io.BytesIO()
    converter = TextConverter(resource_manager, fake_file_handle)
    page_interpreter = PDFPageInterpreter(resource_manager, converter)

    with open(pdf_path, 'rb') as fh:
        for page in PDFPage.get_pages(fh, 
                                      caching=True,
                                      check_extractable=True):
            page_interpreter.process_page(page)

        text = fake_file_handle.getvalue()

    # close open handles
    converter.close()
    fake_file_handle.close()

    if text:
        return text

def parse_pdf(filename):
    "Parse a pdf into text"
    content = io.getPDFContent(filename)
    encoded = content.encode("utf-8")
    ## split of the pdf extension to add .txt instead.
    (root, _) = os.path.splitext(filename)
    text_file = open(root + ".txt", "w")
    text_file.write(encoded)
    text_file.close()    

if __name__ == '__main__':
    pdf_path = 'C:\\trainingdata_eng'    
    for file in os.walk(pdf_path):
        extract_text_from_pdf(file)

    for f in file:
        parse_pdf(f)