python富文本转word

#coding=utf-8
from docx import Document
from docx.shared import Pt, RGBColor
from docx.oxml.ns import qn
from lxml import etree
# from docx.enum.text import WD_ALIGN_PARAGRAPH

data = [{
    'document_title': u'<h1>写一个题目阿斯蒂芬按时</h1>',
    'document_content': u"""<p>你好</p>

<p>你好中国</p>

<p><strong>hello </strong>world</p>
""" 
},{
    'document_title': u'写一个题目阿斯蒂芬按时',
    'document_content': u"""<p>你好</p>

<p>你好中国</p>

<p><strong>hello </strong>world</p>
""" 
}]
<!-- more -->

# 格式化富文本
def clean_richtext(richtext):
    response = etree.HTML(text=richtext)
    return response.xpath('string(.)')

def render_data(data):
    document = Document()
    font_name = u'宋体'

    for item in data:
        title_text = clean_richtext(item['document_title'])
        content_text = clean_richtext(item['document_content'])
        title = document.add_heading()
        paragraph = document.add_paragraph()
        # 居中
        # title.alignment = WD_ALIGN_PARAGRAPH.CENTER
        title_run = title.add_run(title_text)
        title_run.font.size = Pt(22)
        title_run.font.color.rgb = RGBColor(0, 0, 0)
        title_run.font.name = font_name
        title_run._element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
        para_run = paragraph.add_run(content_text)
        para_run.font.size = Pt(10.5)
        para_run.font.name = font_name
        para_run._element.rPr.rFonts.set(qn('w:eastAsia'), font_name)

    document.save('test.docx')

render_data(data)