Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import bs4
- html_string = """
- <html>
- <head>
- <title></title>
- </head>
- <body>
- <p align="center">
- This is before.
- <div style="page-break-after:always">
- </div>
- This is after.
- </p>
- </body>
- </html>
- """
- html_element = bs4.BeautifulSoup(html_string, features="xml")
- style = {'style': 'page-break-after:always'}
- page_break_elements = html_element.findAll('div', style)
- for page_break_element in page_break_elements:
- current = page_break_element
- while True:
- parent = current.parent
- if parent is None:
- break
- if parent.name == 'body':
- current.insert_before(page_break_element)
- break
- current = parent
Add Comment
Please, Sign In to add comment