def parse_xml(self, readsize=16384):
if not self.path:
return
elements = []
builder = SnippetsTreeBuilder( \
lambda node: elements.append((node, True)), \
lambda node: elements.append((node, False)))
parser = et.XMLTreeBuilder(target=builder)
self.insnippet = False
try:
f = open(self.path, "r")
while True:
data = f.read(readsize)
if not data:
break
parser.feed(data)
for element in elements:
yield element
del elements[:]
f.close()
except IOError:
self.ok = False
def parse_xml(xml):
document = ET.ElementTree()
if isinstance(xml, unicode):
xml = xml.encode('utf-8')
if isinstance(xml, (basestring, buffer)):
from io import BytesIO
xml = BytesIO(bytes(xml))
document.parse(xml, ET.XMLTreeBuilder())
return document.getroot()
def parseFile(file):
treeBuilder = ElementTree.TreeBuilder(element_factory=SimpleElementTreeVar)
xmlTreeBuilder = ElementTree.XMLTreeBuilder(target=treeBuilder)
if (not hasattr(file, 'read')):
ourFile = open(file)
xmlTreeBuilder.feed(ourFile.read())
ourFile.close()
else:
xmlTreeBuilder.feed(file.read())
return xmlTreeBuilder.close()
def __init__(self, file=None, tag='global', **extra):
if isinstance(file, basestring):
file = os.path.expanduser(file)
if file is None:
top_level_elt = XmlList(tag=tag, **extra)
top_level_elt.text = top_level_elt.tail = '\n'
ElementTree.ElementTree.__init__(self, element=top_level_elt)
else:
ElementTree.ElementTree.__init__(self)
self.parse(source=file,
parser=ElementTree.XMLTreeBuilder(
target=ElementTree.TreeBuilder(XmlList)))
return
def __init__(self, xmlin, out, param={}):
self.counter = 0
self.constants = {}
self.lines = []
h = open(xmlin, 'r')
xml = h.read()
h.close()
builder = ET.XMLTreeBuilder()
builder.feed(xml)
tree = builder.close()
self.out = out
self.__walk(tree, None)
self.__write()
def __init__(self, client):
self.client = client
self.parser = etree.XMLTreeBuilder(
target=self) #XMLParser(target=self)
self.parser.feed(b'')
self.__nsmap__ = __nsmap__
def parseComment(text):
parser = ElementTree.XMLTreeBuilder()
parser.feed(text.encode('utf8'))
root = parser.close()
return root
#!/usr/bin/env python2.7
# -*- coding: utf8 -*-
"""Filter out OACI areas depending on geographic position"""
from math import isnan
from optparse import OptionParser
from xml.etree import ElementTree as ET
from pprint import pprint
import sys
import time
parser = ET.XMLTreeBuilder()
prefix = 'http://earth.google.com/kml/2.2'
def PF(s):
return '{%s}%s' % (prefix, s)
def m2f(m):
return float(m) / 0.3048
def f2m(m):
return float(m) * 0.3048
def parse(filename):
print >> sys.stderr, "Parsing..."
with filename and open(filename, 'rt') or sys.stdin as f:
et = ET.parse(f)
def BuildTree(xmlstring):
parser = ElementTree.XMLTreeBuilder()
parser.feed(xmlstring)
return parser.close()
def main():
parser = ET.XMLTreeBuilder(target=OutlinerParser())
parser.feed(sys.stdin.read())
parser.close()
def __init__(self):
self.tree_builder = _TerminationDetectingTreeBuilder()
self.xml_tree_builder = et.XMLTreeBuilder(target=self.tree_builder)
except ImportError:
raise ImportError("You need ElementTree")
if __name__ == "__main__":
mk = file('MochiKit/MochiKit.js').read()
modules = map(
str.strip,
re.search(r"""(?mxs)MochiKit.MochiKit.SUBMODULES\s*=\s*\[([^\]]+)""",
mk).group(1).replace(' ', '').replace('"', '').split(','))
root = ET.Element("pages")
for modulename in modules:
tb = ET.XMLTreeBuilder()
tb.entity['nbsp'] = " "
doc = ET.parse("doc/html/MochiKit/%s.html" % modulename, parser=tb)
mod = ET.SubElement(root, "page")
mod.attrib.update(
dict(title="MochiKit.%s" % modulename,
type="package",
url="http://mochikit.com/doc/html/MochiKit/%s.html" %
modulename))
for a in doc.findall("//{http://www.w3.org/1999/xhtml}a"):
if a.attrib.get("class", None) == "mochidef reference":
fun = ET.SubElement(mod, "page")
fun.attrib.update(
dict(title=a.text),
def end(self, tag):
# Ignore closing tags
pass
def data(self, data):
# Ignore data inside nodes
pass
def close(self):
# Nothing special to do here
return
print "Using a custom tree-building class:"
target = PodcastListToCSV(sys.stdout)
with closing(ElementTree.XMLTreeBuilder(target=target)) as parser:
with closing(open('data/7.6-xml.etree.ElementTree_podcasts.opml',
'r')) as f:
for line in f:
parser.feed(line)
print
## 7.6.7 Parsing Strings
# To work ith smaller bits of XML text, use XML() with the string containing the XML as the only argument
xml_string_to_parse = """
<root>
<group>
<child id="a">This is child "a".</child>
<child id="b">This is child "b".</child>
</group>
<group>
