在一个函数中从doc和docx文件中抓取文本

from docx import Document

def extract_text_from_docx(file_path):
    doc = Document(file_path)
    text = ""
    for paragraph in doc.paragraphs:
        text += paragraph.text + "\n"
    return text

def extract_text_from_doc(file_path):
    with open(file_path, "rb") as file:
        data = file.read()
    text = data.decode("utf-8")
    return text

def extract_text_from_file(file_path):
    if file_path.endswith(".docx"):
        return extract_text_from_docx(file_path)
    elif file_path.endswith(".doc"):
        return extract_text_from_doc(file_path)
    else:
        return "Unsupported file format."

# 示例用法
file_path = "example.docx"
text = extract_text_from_file(file_path)
print(text)