富文本转word

  1. #coding=utf-8
  2. from docx import Document
  3. from docx.shared import Pt, RGBColor
  4. from docx.oxml.ns import qn
  5. from lxml import etree
  6. # from docx.enum.text import WD_ALIGN_PARAGRAPH
  8. data = [{
  9.     'document_title': u'<h1>写一个题目阿斯蒂芬按时</h1>',
  10.     'document_content': u"""<p>你好</p>
  12. <p>你好中国</p>
  14. <p><strong>hello </strong>world</p>
  15. """ 
  16. },{
  17.     'document_title': u'写一个题目阿斯蒂芬按时',
  18.     'document_content': u"""<p>你好</p>
  20. <p>你好中国</p>
  22. <p><strong>hello </strong>world</p>
  23. """ 
  24. }]
  25. <!-- more -->
  27. # 格式化富文本
  28. def clean_richtext(richtext):
  29.     response = etree.HTML(text=richtext)
  30.     return response.xpath('string(.)')
  32. def render_data(data):
  33.     document = Document()
  34.     font_name = u'宋体'
  36.     for item in data:
  37.         title_text = clean_richtext(item['document_title'])
  38.         content_text = clean_richtext(item['document_content'])
  39.         title = document.add_heading()
  40.         paragraph = document.add_paragraph()
  41.         # 居中
  42.         # title.alignment = WD_ALIGN_PARAGRAPH.CENTER
  43.         title_run = title.add_run(title_text)
  44.         title_run.font.size = Pt(22)
  45.         title_run.font.color.rgb = RGBColor(0, 0, 0)
  46.         title_run.font.name = font_name
  47.         title_run._element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
  48.         para_run = paragraph.add_run(content_text)
  49.         para_run.font.size = Pt(10.5)
  50.         para_run.font.name = font_name
  51.         para_run._element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
  53.     document.save('test.docx')
  55. render_data(data)