只将背景颜色为word-file的文本提取到python

pip install python-docx

from docx import Document

def extract_text_with_background_color(docx_file):
    doc = Document(docx_file)
    extracted_text = []

    for paragraph in doc.paragraphs:
        for run in paragraph.runs:
            if run.font.highlight_color.rgb == 'FFFF00':
                extracted_text.append(run.text)

    return extracted_text

# 使用示例
docx_file = 'path/to/your/docx/file.docx'
extracted_text = extract_text_with_background_color(docx_file)
print(extracted_text)