Created
May 22, 2012 17:41
-
-
Save obeattie/2770517 to your computer and use it in GitHub Desktop.
A BeautifulSoup that can handle HTML fragments with lxml
This file contains 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 bs4 import BeautifulSoup | |
| from bs4.builder._lxml import LXML as BS_LXML_FEATURE | |
| class FragmentSoup(BeautifulSoup): | |
| """A custom BeautifulSoup implementation that properly represents fragments when using lxml, without wrapping them | |
| in a document on output (internally, they are still wrapped).""" | |
| def _feed(self, *args, **kwargs): | |
| if not hasattr(self, '__markup_enclosure'): | |
| self.__markup_enclosure = None | |
| if BS_LXML_FEATURE in self.builder.features and (not self.builder.is_xml) and not ( | |
| self.markup.startswith('<html') or self.markup.startswith('<!doctype')): | |
| # Wrap in an enclosure -- if this is a <body> then don't include another | |
| if self.markup.startswith('<body'): | |
| self.markup = '<html>%s</html>' % self.markup | |
| self.__markup_enclosure = 'html' | |
| else: | |
| self.markup = '<html><body>%s</body></html>' % self.markup | |
| self.__markup_enclosure = 'body' | |
| return super(FragmentSoup, self)._feed(*args, **kwargs) | |
| def decode(self, *args, **kwargs): | |
| if self.__markup_enclosure is not None: | |
| targets = self.find(self.__markup_enclosure).children | |
| return ''.join(t.decode(*args, **kwargs) for t in targets) | |
| else: | |
| return super(FragmentSoup, self).decode(*args, **kwargs) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
You can use undocumented (in v.4) soup.body.decode_contents()