Python html5lib.constants.namespaces() Examples
The following are 30
code examples of html5lib.constants.namespaces().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
html5lib.constants
, or try the search function
.
.
Example #1
| Source File: chunk.py From budou with Apache License 2.0 | 5 votes |
|
def wbr_serialize(self):
"""Returns concatenated HTML code with WBR tag. This is still experimental.
Returns:
The organized HTML code. (str)
"""
doc = ET.Element('span')
doc.attrib['style'] = 'word-break: keep-all'
for chunk in self:
if (chunk.has_cjk() and doc.text):
ele = ET.Element('wbr')
doc.append(ele)
doc.getchildren()[-1].tail = chunk.word
else:
# add word without span tag for non-CJK text (e.g. English)
# by appending it after the last element
if doc.getchildren():
if doc.getchildren()[-1].tail is None:
doc.getchildren()[-1].tail = chunk.word
else:
doc.getchildren()[-1].tail += chunk.word
else:
if doc.text is None:
doc.text = chunk.word
else:
doc.text += chunk.word
content = ET.tostring(doc, encoding='utf-8').decode('utf-8')
dom = html5lib.parseFragment(content)
treewalker = getTreeWalker('etree')
stream = treewalker(dom)
serializer = html5lib.serializer.HTMLSerializer(
quote_attr_values='always')
allowed_elements = set(sanitizer.allowed_elements)
allowed_elements.add((namespaces['html'], 'wbr'))
allowed_css_properties = set(sanitizer.allowed_css_properties)
allowed_css_properties.add('word-break')
result = serializer.render(sanitizer.Filter(
stream, allowed_elements=allowed_elements,
allowed_css_properties=allowed_css_properties,
))
return result
Example #2
| Source File: _html5lib.py From moviegrabber with GNU General Public License v3.0 | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #3
| Source File: test_parser2.py From bazarr with GNU General Public License v3.0 | 5 votes |
|
def test_namespace_html_elements_0_etree():
doc = parse("<html></html>",
treebuilder="etree",
namespaceHTMLElements=True)
assert doc.tag == "{%s}html" % (namespaces["html"],)
Example #4
| Source File: test_parser2.py From bazarr with GNU General Public License v3.0 | 5 votes |
|
def test_namespace_html_elements_0_dom():
doc = parse("<html></html>",
treebuilder="dom",
namespaceHTMLElements=True)
assert doc.childNodes[0].namespaceURI == namespaces["html"]
Example #5
| Source File: _html5lib.py From Crunchyroll-XML-Decoder with GNU General Public License v2.0 | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #6
| Source File: _html5lib.py From Crunchyroll-XML-Decoder with GNU General Public License v2.0 | 5 votes |
|
def reparentChildren(self, newParent):
while self.element.contents:
child = self.element.contents[0]
child.extract()
if isinstance(child, Tag):
newParent.appendChild(
Element(child, self.soup, namespaces["html"]))
else:
newParent.appendChild(
TextNode(child, self.soup))
Example #7
| Source File: _html5lib.py From POC-EXP with GNU General Public License v3.0 | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #8
| Source File: _html5lib.py From python-for-android with Apache License 2.0 | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #9
| Source File: _html5lib.py From python-for-android with Apache License 2.0 | 5 votes |
|
def reparentChildren(self, newParent):
while self.element.contents:
child = self.element.contents[0]
child.extract()
if isinstance(child, Tag):
newParent.appendChild(
Element(child, self.soup, namespaces["html"]))
else:
newParent.appendChild(
TextNode(child, self.soup))
Example #10
| Source File: _html5lib.py From ru with GNU General Public License v2.0 | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #11
| Source File: test_parser2.py From MARA_Framework with GNU Lesser General Public License v3.0 | 5 votes |
|
def test_namespace_html_elements_0_etree(self):
parser = html5parser.HTMLParser(namespaceHTMLElements=True)
doc = parser.parse("<html></html>")
self.assertTrue(list(doc)[0].tag == "{%s}html" % (namespaces["html"],))
Example #12
| Source File: test_parser2.py From MARA_Framework with GNU Lesser General Public License v3.0 | 5 votes |
|
def test_namespace_html_elements_0_dom(self):
parser = html5parser.HTMLParser(tree=self.dom_tree, namespaceHTMLElements=True)
doc = parser.parse("<html></html>")
self.assertTrue(doc.childNodes[0].namespaceURI == namespaces["html"])
Example #13
| Source File: _html5lib.py From MARA_Framework with GNU Lesser General Public License v3.0 | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #14
| Source File: _html5lib.py From CrisisMappingToolkit with Apache License 2.0 | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #15
| Source File: _html5lib.py From nbaplus-server with Apache License 2.0 | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #16
| Source File: _html5lib.py From pledgeservice with Apache License 2.0 | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #17
| Source File: _html5lib.py From stopstalk-deployment with MIT License | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #18
| Source File: soup.py From nzb-subliminal with GNU General Public License v3.0 | 5 votes |
|
def reparentChildren(self, newParent):
while self.element.contents:
child = self.element.contents[0]
child.extract()
if isinstance(child, Tag):
newParent.appendChild(Element(child, self.soup, namespaces["html"]))
else:
newParent.appendChild(TextNode(child, self.soup))
Example #19
| Source File: simpletree.py From nzb-subliminal with GNU General Public License v3.0 | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #20
| Source File: _base.py From nzb-subliminal with GNU General Public License v3.0 | 5 votes |
|
def elementInScope(self, target, variant=None):
#If we pass a node in we match that. if we pass a string
#match any node with that name
exactNode = hasattr(target, "nameTuple")
listElementsMap = {
None:(scopingElements, False),
"button":(scopingElements | set([(namespaces["html"], "button")]), False),
"list":(scopingElements | set([(namespaces["html"], "ol"),
(namespaces["html"], "ul")]), False),
"table":(set([(namespaces["html"], "html"),
(namespaces["html"], "table")]), False),
"select":(set([(namespaces["html"], "optgroup"),
(namespaces["html"], "option")]), True)
}
listElements, invert = listElementsMap[variant]
for node in reversed(self.openElements):
if (node.name == target and not exactNode or
node == target and exactNode):
return True
elif (invert ^ (node.nameTuple in listElements)):
return False
assert False # We should never reach this point
Example #21
| Source File: soup.py From nzb-subliminal with GNU General Public License v3.0 | 5 votes |
|
def getNodeDetails(self, node):
if isinstance(node, BeautifulSoup): # Document or DocumentFragment
return (_base.DOCUMENT,)
elif isinstance(node, Declaration): # DocumentType
string = unicode(node.string)
#Slice needed to remove markup added during unicode conversion,
#but only in some versions of BeautifulSoup/Python
if string.startswith('<!') and string.endswith('>'):
string = string[2:-1]
m = self.doctype_regexp.match(string)
#This regexp approach seems wrong and fragile
#but beautiful soup stores the doctype as a single thing and we want the seperate bits
#It should work as long as the tree is created by html5lib itself but may be wrong if it's
#been modified at all
#We could just feed to it a html5lib tokenizer, I guess...
assert m is not None, "DOCTYPE did not match expected format"
name = m.group('name')
publicId = m.group('publicId')
if publicId is not None:
systemId = m.group('systemId1')
else:
systemId = m.group('systemId2')
return _base.DOCTYPE, name, publicId or "", systemId or ""
elif isinstance(node, Comment):
string = unicode(node.string)
if string.startswith('<!--') and string.endswith('-->'):
string = string[4:-3]
return _base.COMMENT, string
elif isinstance(node, unicode): # TextNode
return _base.TEXT, node
elif isinstance(node, Tag): # Element
return (_base.ELEMENT, namespaces["html"], node.name,
dict(node.attrs).items(), node.contents)
else:
return _base.UNKNOWN, node.__class__.__name__
Example #22
| Source File: _html5lib.py From nzb-subliminal with GNU General Public License v3.0 | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #23
| Source File: _html5lib.py From Gank-Alfred-Workflow with MIT License | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #24
| Source File: _html5lib.py From Gank-Alfred-Workflow with MIT License | 5 votes |
|
def reparentChildren(self, newParent):
while self.element.contents:
child = self.element.contents[0]
child.extract()
if isinstance(child, Tag):
newParent.appendChild(
Element(child, self.soup, namespaces["html"]))
else:
newParent.appendChild(
TextNode(child, self.soup))
Example #25
| Source File: _html5lib.py From svg-animation-tools with MIT License | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #26
| Source File: _html5lib.py From svg-animation-tools with MIT License | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #27
| Source File: _html5lib.py From crunchy-xml-decoder with GNU General Public License v2.0 | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #28
| Source File: _html5lib.py From crunchy-xml-decoder with GNU General Public License v2.0 | 5 votes |
|
def reparentChildren(self, newParent):
while self.element.contents:
child = self.element.contents[0]
child.extract()
if isinstance(child, Tag):
newParent.appendChild(
Element(child, self.soup, namespaces["html"]))
else:
newParent.appendChild(
TextNode(child, self.soup))
Example #29
| Source File: _html5lib.py From weeman with GNU General Public License v3.0 | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
Example #30
| Source File: _html5lib.py From fuzzdb-collect with GNU General Public License v3.0 | 5 votes |
|
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
