def parse(source,
prefixes=None,
model=None,
encoding=None,
use_xhtml_ns=False):
'''
Parse an input source with HTML text into an Amara Bindery tree
Warning: if you pass a string, you must make sure it's a byte string, not a Unicode object. You might also want to wrap it with amara.lib.inputsource.text if it's not obviously XML or HTML (for example it could be confused with a file name)
'''
from amara.lib.util import set_namespaces
#from amara.bindery import html; doc = html.parse("http://www.hitimewine.net/istar.asp?a=6&id=161153!1247")
#parser = html5lib.HTMLParser()
if PRE_0_90:
def get_tree_instance():
entity_factory = model.clone if model else entity
return treebuilder(entity_factory)
else:
def get_tree_instance(namespaceHTMLElements,
use_xhtml_ns=use_xhtml_ns):
#use_xhtml_ns is a boolean, whether or not to use http://www.w3.org/1999/xhtml
entity_factory = model.clone if model else entity
return treebuilder(entity_factory, use_xhtml_ns)
parser = html5lib.HTMLParser(tree=get_tree_instance)
doc = parser.parse(inputsource(source, None).stream, encoding=encoding)
if prefixes: set_namespaces(doc, prefixes)
return doc
def parse(source,
prefixes=None,
model=None,
encoding=None,
use_xhtml_ns=False):
'''
'''
from amara.lib.util import set_namespaces
#from amara.bindery import html; doc = html.parse("http://www.hitimewine.net/istar.asp?a=6&id=161153!1247")
#parser = html5lib.HTMLParser()
if PRE_0_90:
def get_tree_instance():
entity_factory = model.clone if model else entity
return treebuilder(entity_factory)
else:
def get_tree_instance(namespaceHTMLElements,
use_xhtml_ns=use_xhtml_ns):
#use_xhtml_ns is a boolean, whether or not to use http://www.w3.org/1999/xhtml
entity_factory = model.clone if model else entity
return treebuilder(entity_factory, use_xhtml_ns)
parser = html5lib.HTMLParser(tree=get_tree_instance)
doc = parser.parse(inputsource(source, None).stream, encoding=encoding)
if prefixes: set_namespaces(doc, prefixes)
return doc
def parse(obj, uri=None, entity_factory=None, standalone=False, validate=False, prefixes=None, model=None):
if model:
entity_factory = model.clone
if not entity_factory:
entity_factory = nodes.entity_base
doc = tree.parse(obj, uri, entity_factory=entity_factory, standalone=standalone, validate=validate)
if prefixes:
set_namespaces(doc, prefixes)
return doc
def parse(obj,
uri=None,
entity_factory=None,
standalone=False,
validate=False,
prefixes=None,
model=None):
if model:
entity_factory = model.clone
if not entity_factory:
entity_factory = nodes.entity_base
doc = tree.parse(obj,
uri,
entity_factory=entity_factory,
standalone=standalone,
validate=validate)
if prefixes: set_namespaces(doc, prefixes)
return doc
def parse(source, prefixes=None, model=None, encoding=None, use_xhtml_ns=False):
'''
'''
from amara.lib.util import set_namespaces
#from amara.bindery import html; doc = html.parse("http://www.hitimewine.net/istar.asp?a=6&id=161153!1247")
#parser = html5lib.HTMLParser()
if PRE_0_90:
def get_tree_instance():
entity_factory = model.clone if model else entity
return treebuilder(entity_factory)
else:
def get_tree_instance(namespaceHTMLElements, use_xhtml_ns=use_xhtml_ns):
#use_xhtml_ns is a boolean, whether or not to use http://www.w3.org/1999/xhtml
entity_factory = model.clone if model else entity
return treebuilder(entity_factory, use_xhtml_ns)
parser = html5lib.HTMLParser(tree=get_tree_instance)
doc = parser.parse(inputsource(source, None).stream, encoding=encoding)
if prefixes: set_namespaces(doc, prefixes)
return doc
def parse(source, prefixes=None, model=None, encoding=None, use_xhtml_ns=False):
'''
Parse an input source with HTML text into an Amara Bindery tree
Warning: if you pass a string, you must make sure it's a byte string, not a Unicode object. You might also want to wrap it with amara.lib.inputsource.text if it's not obviously XML or HTML (for example it could be confused with a file name)
'''
from amara.lib.util import set_namespaces
#from amara.bindery import html; doc = html.parse("http://www.hitimewine.net/istar.asp?a=6&id=161153!1247")
#parser = html5lib.HTMLParser()
if PRE_0_90:
def get_tree_instance():
entity_factory = model.clone if model else entity
return treebuilder(entity_factory)
else:
def get_tree_instance(namespaceHTMLElements, use_xhtml_ns=use_xhtml_ns):
#use_xhtml_ns is a boolean, whether or not to use http://www.w3.org/1999/xhtml
entity_factory = model.clone if model else entity
return treebuilder(entity_factory, use_xhtml_ns)
parser = html5lib.HTMLParser(tree=get_tree_instance)
doc = parser.parse(inputsource(source, None).stream, encoding=encoding)
if prefixes: set_namespaces(doc, prefixes)
return doc
