import os, pymupdf

def read_files(path, output, filetypes=None):
    if filetypes is None:
        filetypes = ["pdf", "txt", "png", "jpg", "mp3"]

    for root, dirs, files in os.walk(path):
        for file in files:
            if (file_type := file.split(".")[-1]) in filetypes:
                output.append((file_type, os.path.join(path, file)))

        for folder in dirs:
            read_files(os.path.join(path, folder), output)

        break

def extract_pdf_content(pdf_datei):
    doc = pymupdf.open(pdf_datei)
    a = ""
    for page in doc:
        a += page.get_text()
    return a