2014-07-21 19:01:46 -04:00
|
|
|
"""
|
2014-03-10 01:18:05 -04:00
|
|
|
HTML parsing library based on the WHATWG "HTML5"
|
|
|
|
specification. The parser is designed to be compatible with existing
|
|
|
|
HTML found in the wild and implements well-defined error recovery that
|
|
|
|
is largely compatible with modern desktop web browsers.
|
|
|
|
|
|
|
|
Example usage:
|
|
|
|
|
|
|
|
import html5lib
|
|
|
|
f = open("my_document.html")
|
2014-07-21 19:01:46 -04:00
|
|
|
tree = html5lib.parse(f)
|
2014-03-10 01:18:05 -04:00
|
|
|
"""
|
2014-07-21 19:01:46 -04:00
|
|
|
|
|
|
|
from __future__ import absolute_import, division, unicode_literals
|
|
|
|
|
|
|
|
from .html5parser import HTMLParser, parse, parseFragment
|
|
|
|
from .treebuilders import getTreeBuilder
|
|
|
|
from .treewalkers import getTreeWalker
|
|
|
|
from .serializer import serialize
|
|
|
|
|
|
|
|
__all__ = ["HTMLParser", "parse", "parseFragment", "getTreeBuilder",
|
|
|
|
"getTreeWalker", "serialize"]
|
|
|
|
__version__ = "0.999"
|