def testWordParse(self):
with gumboc.parse('Test') as output:
doctype_node = output.contents.document.contents
self.assertEquals(gumboc.NodeType.DOCUMENT, doctype_node.type)
document = doctype_node.v.document
self.assertEquals('', document.name)
self.assertEquals('', document.public_identifier)
self.assertEquals('', document.system_identifier)
root = output.contents.root.contents
self.assertEquals(gumboc.NodeType.ELEMENT, root.type)
self.assertEquals(gumboc.Tag.HTML, root.tag)
self.assertEquals(gumboc.Namespace.HTML, root.tag_namespace)
self.assertEquals(2, len(root.children))
head = root.children[0]
self.assertEquals(gumboc.NodeType.ELEMENT, head.type)
self.assertEquals(gumboc.Tag.HEAD, head.tag)
self.assertEquals('head', head.tag_name)
self.assertEquals(gumboc.Namespace.HTML, head.tag_namespace)
self.assertEquals(0, len(head.original_tag))
self.assertEquals('', str(head.original_end_tag))
self.assertEquals(0, head.children.length)
body = root.children[1]
self.assertNotEquals(body, doctype_node)
self.assertEquals(gumboc.NodeType.ELEMENT, body.type)
self.assertEquals(gumboc.Tag.BODY, body.tag)
self.assertEquals('body', body.tag_name)
self.assertEquals(1, len(body.children))
text_node = body.children[0]
self.assertEquals(gumboc.NodeType.TEXT, text_node.type)
self.assertEquals('Test', text_node.text)
def testWordParse(self):
with gumboc.parse('Test') as output:
doctype_node = output.contents.document.contents
self.assertEquals(gumboc.NodeType.DOCUMENT, doctype_node.type)
document = doctype_node.v.document
self.assertEquals('', document.name)
self.assertEquals('', document.public_identifier)
self.assertEquals('', document.system_identifier)
root = output.contents.root.contents
self.assertEquals(gumboc.NodeType.ELEMENT, root.type)
self.assertEquals(gumboc.Tag.HTML, root.tag)
self.assertEquals(gumboc.Namespace.HTML, root.tag_namespace)
self.assertEquals(2, len(root.children))
head = root.children[0]
self.assertEquals(gumboc.NodeType.ELEMENT, head.type)
self.assertEquals(gumboc.Tag.HEAD, head.tag)
self.assertEquals('head', head.tag_name)
self.assertEquals(gumboc.Namespace.HTML, head.tag_namespace)
self.assertEquals(0, len(head.original_tag))
self.assertEquals('', str(head.original_end_tag))
self.assertEquals(0, head.children.length)
body = root.children[1]
self.assertNotEquals(body, doctype_node)
self.assertEquals(gumboc.NodeType.ELEMENT, body.type)
self.assertEquals(gumboc.Tag.BODY, body.tag)
self.assertEquals('body', body.tag_name)
self.assertEquals(1, len(body.children))
text_node = body.children[0]
self.assertEquals(gumboc.NodeType.TEXT, text_node.type)
self.assertEquals('Test', text_node.text)
def parse(text, **kwargs):
with gumboc.parse(text, **kwargs) as output:
soup = bs4.BeautifulSoup('', "html.parser")
_add_document(soup, output.contents.document.contents)
for node in output.contents.document.contents.children:
soup.append(_add_node(soup, node))
_add_next_prev_pointers(soup.html)
return soup
def parse(text, **kwargs):
with gumboc.parse(text, **kwargs) as output:
soup = bs4.BeautifulSoup('', "html.parser")
_add_document(soup, output.contents.document.contents)
for node in output.contents.document.contents.children:
soup.append(_add_node(soup, node))
_add_next_prev_pointers(soup.html)
return soup
def testFragment(self):
with gumboc.parse('<div></div>',
fragment_context=gumboc.Tag.TITLE,
fragment_namespace=gumboc.Namespace.SVG) as output:
root = output.contents.root.contents
self.assertEquals(1, len(root.children))
div = root.children[0]
self.assertEquals(gumboc.NodeType.ELEMENT, div.type)
self.assertEquals(gumboc.Tag.DIV, div.tag)
self.assertEquals(gumboc.Namespace.HTML, div.tag_namespace)
def testFragment(self):
with gumboc.parse(
'<div></div>',
container=gumboc.Tag.TITLE,
container_namespace=gumboc.Namespace.SVG) as output:
root = output.contents.root.contents
self.assertEqual(1, len(root.children))
div = root.children[0]
self.assertEqual(gumboc.NodeType.ELEMENT, div.type)
self.assertEqual(gumboc.Tag.DIV, div.tag)
self.assertEqual(gumboc.Namespace.HTML, div.tag_namespace)
def testSarcasm(self):
with gumboc.parse('<div><sarcasm><div></div></sarcasm></div>') as output:
root = output.contents.root.contents
body = root.children[1]
div = body.children[0]
sarcasm = div.children[0]
self.assertEquals(gumboc.NodeType.ELEMENT, sarcasm.type)
self.assertEquals(gumboc.Tag.UNKNOWN, sarcasm.tag)
self.assertEquals('<sarcasm>', str(sarcasm.original_tag))
self.assertEquals('</sarcasm>', str(sarcasm.original_end_tag))
self.assertEquals('sarcasm', sarcasm.tag_name.decode('utf-8'))
def testSarcasm(self):
with gumboc.parse('<div><sarcasm><div></div></sarcasm></div>') as output:
root = output.contents.root.contents
body = root.children[1]
div = body.children[0]
sarcasm = div.children[0]
self.assertEquals(gumboc.NodeType.ELEMENT, sarcasm.type)
self.assertEquals(gumboc.Tag.UNKNOWN, sarcasm.tag)
self.assertEquals('<sarcasm>', str(sarcasm.original_tag))
self.assertEquals('</sarcasm>', str(sarcasm.original_end_tag))
self.assertEquals('sarcasm', sarcasm.tag_name.decode('utf-8'))
def testUnknownTag(self):
with gumboc.parse('<foo bar=quux>1<p>2</foo>') as output:
root = output.contents.root.contents
body = root.children[1]
foo = body.children[0]
self.assertEquals(gumboc.NodeType.ELEMENT, foo.type)
self.assertEquals(gumboc.Tag.UNKNOWN, foo.tag)
self.assertEquals('<foo bar=quux>', str(foo.original_tag))
self.assertEquals('', str(foo.original_end_tag))
self.assertEquals('foo', foo.tag_name.decode('utf-8'))
self.assertEquals('bar', foo.attributes[0].name)
self.assertEquals('quux', foo.attributes[0].value)
def testUnknownTag(self):
with gumboc.parse('<foo bar=quux>1<p>2</foo>') as output:
root = output.contents.root.contents
body = root.children[1]
foo = body.children[0]
self.assertEquals(gumboc.NodeType.ELEMENT, foo.type)
self.assertEquals(gumboc.Tag.UNKNOWN, foo.tag)
self.assertEquals('<foo bar=quux>', str(foo.original_tag))
self.assertEquals('', str(foo.original_end_tag))
self.assertEquals('foo', foo.tag_name.decode('utf-8'))
self.assertEquals('bar', foo.attributes[0].name)
self.assertEquals('quux', foo.attributes[0].value)
def testBufferThatGoesAway(self):
for i in range(10):
source = StringIO.StringIO('<foo bar=quux>1<p>2</foo>')
parse_tree = gumboc.parse(source.read())
source.close()
with parse_tree as output:
root = output.contents.root.contents
body = root.children[1]
foo = body.children[0]
self.assertEquals(gumboc.NodeType.ELEMENT, foo.type)
self.assertEquals(gumboc.Tag.UNKNOWN, foo.tag)
self.assertEquals('<foo bar=quux>', str(foo.original_tag))
self.assertEquals('', str(foo.original_end_tag))
self.assertEquals('foo', foo.tag_name.decode('utf-8'))
self.assertEquals('bar', foo.attributes[0].name)
self.assertEquals('quux', foo.attributes[0].value)
def testBufferThatGoesAway(self):
for i in range(10):
source = StringIO.StringIO('<foo bar=quux>1<p>2</foo>')
parse_tree = gumboc.parse(source.read())
source.close()
with parse_tree as output:
root = output.contents.root.contents
body = root.children[1]
foo = body.children[0]
self.assertEquals(gumboc.NodeType.ELEMENT, foo.type)
self.assertEquals(gumboc.Tag.UNKNOWN, foo.tag)
self.assertEquals('<foo bar=quux>', str(foo.original_tag))
self.assertEquals('', str(foo.original_end_tag))
self.assertEquals('foo', foo.tag_name.decode('utf-8'))
self.assertEquals('bar', foo.attributes[0].name)
self.assertEquals('quux', foo.attributes[0].value)
def parse(self, text_or_file, **kwargs):
try:
text = text_or_file.read()
except AttributeError:
# Assume a string.
text = text_or_file
with gumboc.parse(text, **kwargs) as output:
_convert_doctype(self.tree, output.contents.document.contents)
for node in output.contents.document.contents.children:
if node.type == gumboc.NodeType.COMMENT:
self.tree.insertComment({'data': node.v.text.text.decode('utf-8')},
self.tree.document)
elif node.type in (gumboc.NodeType.ELEMENT, gumboc.NodeType.TEMPLATE):
_insert_root(self.tree, output.contents.root.contents)
else:
assert 'Only comments and <html> nodes allowed at the root'
return self.tree.getDocument()
def __init__(self, text, **kwargs):
# We need to record the addresses of GumboNodes as we add them and correlate
# them with the BeautifulSoup objects that they become. This lets us
# correctly wire up the next/previous pointers so that they point to
# BeautifulSoup objects instead of ctypes ones.
self._node_map = {}
self._HANDLERS = [
_add_document,
self._add_element,
_add_text(BeautifulSoup.NavigableString),
_add_text(BeautifulSoup.CData),
_add_text(BeautifulSoup.Comment),
_add_text(BeautifulSoup.NavigableString),
]
self.soup = BeautifulSoup.BeautifulSoup()
with gumboc.parse(text, **kwargs) as output:
self.soup.append(self._add_node(output.contents.root.contents))
self._fix_next_prev_pointers(self.soup)
def __init__(self, text, **kwargs):
# We need to record the addresses of GumboNodes as we add them and correlate
# them with the BeautifulSoup objects that they become. This lets us
# correctly wire up the next/previous pointers so that they point to
# BeautifulSoup objects instead of ctypes ones.
self._node_map = {}
self._HANDLERS = [
_add_document,
self._add_element,
_add_text(BeautifulSoup.NavigableString),
_add_text(BeautifulSoup.CData),
_add_text(BeautifulSoup.Comment),
_add_text(BeautifulSoup.NavigableString),
]
self.soup = BeautifulSoup.BeautifulSoup()
with gumboc.parse(text, **kwargs) as output:
self.soup.append(self._add_node(output.contents.root.contents))
self._fix_next_prev_pointers(self.soup)
def parse(self, text_or_file, **kwargs):
try:
text = text_or_file.read()
except AttributeError:
# Assume a string.
text = text_or_file
with gumboc.parse(text, **kwargs) as output:
_convert_doctype(self.tree, output.contents.document.contents)
for node in output.contents.document.contents.children:
if node.type == gumboc.NodeType.COMMENT:
self.tree.insertComment(
{'data': node.v.text.text.decode('utf-8')},
self.tree.document)
elif node.type == gumboc.NodeType.ELEMENT:
_insert_root(self.tree, output.contents.root.contents)
else:
assert 'Only comments and <html> nodes allowed at the root'
return self.tree.getDocument()
def parseFragment(self, text_or_file, container, **kwargs):
try:
text = text_or_file.read()
except AttributeError:
# Assume a string.
text = text_or_file
if ' ' in container:
container_ns, container = container.split(' ')
else:
container_ns = "html"
with gumboc.parse(
text,
container=gumboc.Tag.from_str(container),
container_namespace=getattr(gumboc.Namespace, container_ns.upper()),
**kwargs) as output:
for node in output.contents.document.contents.children:
if node.type in (gumboc.NodeType.ELEMENT, gumboc.NodeType.TEMPLATE):
_insert_root(self.tree, output.contents.root.contents, False)
else:
assert 'Malformed fragment parse (??)'
return self.tree.getFragment()
def parseFragment(self, text_or_file, container, **kwargs):
try:
text = text_or_file.read()
except AttributeError:
# Assume a string.
text = text_or_file
if ' ' in container:
container_ns, container = container.split(' ')
else:
container_ns = "html"
with gumboc.parse(text,
container=gumboc.Tag.from_str(container),
container_namespace=getattr(gumboc.Namespace,
container_ns.upper()),
**kwargs) as output:
for node in output.contents.document.contents.children:
if node.type in (gumboc.NodeType.ELEMENT,
gumboc.NodeType.TEMPLATE):
_insert_root(self.tree, output.contents.root.contents,
False)
else:
assert 'Malformed fragment parse (??)'
return self.tree.getFragment()
def parse(text, **kwargs):
with gumboc.parse(text, **kwargs) as output:
soup = BeautifulSoup.BeautifulSoup()
soup.append(_add_node(soup, output.contents.root.contents))
return soup
def parse(text, **kwargs):
with gumboc.parse(text, **kwargs) as output:
soup = BeautifulSoup.BeautifulSoup()
soup.append(_add_node(soup, output.contents.root.contents))
_add_next_prev_pointers(soup)
return soup