-
-
Save Ricky-Wilson/9980817 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from BeautifulSoup import BeautifulSoup | |
| def _remove_attrs(soup): | |
| for tag in soup.findAll(True): | |
| tag.attrs = None | |
| return soup | |
| def example(): | |
| doc = '<html><head><title>test</title></head><body id="foo" onload="whatever"><p class="whatever">junk</p><div style="background: yellow;" id="foo" class="blah">blah</div></body></html>' | |
| print 'Before:\n%s' % doc | |
| soup = BeautifulSoup(doc) | |
| clean_soup = _remove_attrs(soup) | |
| print '\nAfter:\n%s' % clean_soup |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment