/usr/lib64/python2.6/site-packages/lxml/html
Edit: /usr/lib64/python2.6/site-packages/lxml/html/_html5builder.py (3124B)
"""
This module implements a tree builder for html5lib that generates lxml
html element trees. This module uses camelCase as it follows the
html5lib style guide.
"""
from html5lib.treebuilders import _base, etree as etree_builders
from lxml import html, etree
class DocumentType(object):
def __init__(self, name, publicId, systemId):
self.name = name
self.publicId = publicId
self.systemId = systemId
class Document(object):
def __init__(self):
self._elementTree = None
self.childNodes = []
def appendChild(self, element):
self._elementTree.getroot().addnext(element._element)
class TreeBuilder(_base.TreeBuilder):
documentClass = Document
doctypeClass = DocumentType
elementClass = None
commentClass = None
fragmentClass = Document
def __init__(self):
html_builder = etree_builders.getETreeModule(html, fullTree=False)
etree_builder = etree_builders.getETreeModule(etree, fullTree=False)
self.elementClass = html_builder.Element
self.commentClass = etree_builder.Comment
_base.TreeBuilder.__init__(self)
def reset(self):
_base.TreeBuilder.reset(self)
self.rootInserted = False
self.initialComments = []
self.doctype = None
def getDocument(self):
return self.document._elementTree
def getFragment(self):
fragment = []
element = self.openElements[0]._element
if element.text:
fragment.append(element.text)
fragment.extend(element.getchildren())
if element.tail:
fragment.append(element.tail)
return fragment
def insertDoctype(self, name, publicId, systemId):
doctype = self.doctypeClass(name, publicId, systemId)
self.doctype = doctype
def insertComment(self, data, parent=None):
if not self.rootInserted:
self.initialComments.append(data)
else:
_base.TreeBuilder.insertComment(self, data, parent)
def insertRoot(self, name):
buf = []
if self.doctype and self.doctype.name:
buf.append('')
buf.append('')
root = html.fromstring(u''.join(buf))
# Append the initial comments:
for comment in self.initialComments:
root.addprevious(etree.Comment(comment))
# Create the root document and add the ElementTree to it
self.document = self.documentClass()
self.document._elementTree = root.getroottree()
# Add the root element to the internal child/open data structures
root_element = self.elementClass(name)
root_element._element = root
self.document.childNodes.append(root_element)
self.openElements.append(root_element)
self.rootInserted = True