使用Pandoc读取Docx，捕获docx文本框的内容

from docx import Document

def extract_text_from_textboxes(docx_file):
    doc = Document(docx_file)
    text = []
    for rel in doc.part.rels.values():
        if "word/document.xml" in rel.reltype:
            for textbox in rel.element.body:
                for t in textbox.itertext():
                    text.append(t)
    return text

print(extract_text_from_textboxes('your_file.docx'))