Skip to content

Instantly share code, notes, and snippets.

@beannguyen
Forked from ergoithz/xpath_soup.py
Created September 14, 2018 13:29
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save beannguyen/bf896dff7e6d3f75334ab40124006f48 to your computer and use it in GitHub Desktop.
Save beannguyen/bf896dff7e6d3f75334ab40124006f48 to your computer and use it in GitHub Desktop.
Generate unique XPATH for BeautifulSoup element
#!/usr/bin/python
# -*- coding: utf-8 -*-
def xpath_soup(element):
"""
Generate xpath from BeautifulSoup4 element
:param element: BeautifulSoup4 element.
:type element: bs4.element.Tag or bs4.element.NavigableString
:return: xpath as string
:rtype: str
Usage:
>>> import bs4
>>> html = (
... '<html><head><title>title</title></head>'
... '<body><p>p <i>1</i></p><p>p <i>2</i></p></body></html>'
... )
>>> soup = bs4.BeautifulSoup(html, 'html.parser')
>>> xpath_soup(soup.html.body.p.i)
'/html/body/p[1]/i'
"""
components = []
child = element if element.name else element.parent
for parent in child.parents:
"""
@type parent: bs4.element.Tag
"""
siblings = parent.find_all(child.name, recursive=False)
components.append(
child.name
if siblings == [child] else
'%s[%d]' % (child.name, 1 + siblings.index(child))
)
child = parent
components.reverse()
return '/%s' % '/'.join(components)
if __name__ == '__main__':
import doctest
doctest.testmod(verbose=True)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment