import xml.parsers.expat
import httplib2
import lxml
from lxml.etree import Element, ElementTree, HTML
from io import StringIO
# Just to get some example data
#con = httplib2.Http()
#con.add_credentials('wibble', 'fish')
#a, b = con.request("http://localhost/myWebDAV/", method="PROPFIND", headers={'Depth':'1'})
class Response(object):
"""
Response objects are for storing information about resources
"""
def __init__(self):
"""
Response objects are for storing information about resources
"""
self.href = None
self.resourcetype = None
self.creationdate = None
self.getcontentlength = None
self.getlastmodified = None
self.getetag = None
self.executable = None
self.locks = []
self.getcontenttype = None
class Lock(object):
""" This is an object for storing resource lock information
"""
def __init__(self):
self.locktype = None
self.lockscope = None
class Parser(object):
def __init__(self):
"""
Warning, this has been depreciated. Use LxxmlParser instead
"""
self.element_list = []
self.closed_elements = []
self.response_objects = []
self.current_element = None
self.p = xml.parsers.expat.ParserCreate()
self.p.StartElementHandler = self.start_element
self.p.EndElementHandler = self.end_element
self.p.CharacterDataHandler = self.char_data
self.is_lock = False
#self.p.StartNamespaceDeclHandler = self.ns_data
def start_element(self, name, attrs):
#print 'Start element:', name, attrs
namespace, element_name = name.split(':')
if element_name == 'response':
# Make a new response object
new_response = Response()
# Put it into the list
self.response_objects.append(new_response)
elif self.is_lock:
# If we are currently dealing with a supportedlock element make
# sure we can deal with the scope and type
if element_name == 'lockentry':
self.response_objects[-1].locks.append(Lock())
elif element_name == 'lockscope' or element_name == 'locktype':
self.current_element = element_name
elif element_name == 'supportedlock':
self.is_lock = True
else:
self.current_element = element_name
def end_element(self, name):
namespace, element_name = name.split(':')
if self.is_lock:
if element_name == 'supportedlock':
# Closing the supportedlock element
self.is_lock = False
elif self.current_element == 'lockscope':
# If a lockscope element was found, set the value here
self.response_objects[-1].locks[-1].lockscope = element_name
self.current_element = element_name
elif self.current_element == 'locktype':
# If a locktype element was found, set the value here
self.response_objects[-1].locks[-1].locktype = element_name
self.current_element = element_name
elif self.current_element == 'resourcetype':
self.response_objects[-1].resourcetype = 'resource'
elif self.current_element == 'collection':
self.response_objects[-1].resourcetype = 'collection'
def char_data(self, data):
if data.strip():
#self.element_list[-1].text = data
setattr(self.response_objects[-1], self.current_element, data)
#def ns_data(self, prefix, uri):
#print "Namespace data:", prefix, uri
def parse(self, data):
try:
self.p.Parse(data, 1)
except Exception, err:
err
class LxmlParser(object):
def __init__(self):
self.element_list = []
self.closed_elements = []
self.response_objects = []
self.current_element = None
#self.p = lxml.etree.
#self.p.StartElementHandler = self.start_element
#self.p.EndElementHandler = self.end_element
#self.p.CharacterDataHandler = self.char_data
self.is_lock = False
def parse(self, data):
try:
data_elements = HTML(data)
xml_etree = ElementTree(data_elements)
all_response_elements = xml_etree.findall("//response")
for response in all_response_elements:
new_response = Response()
resp_tree = ElementTree(response)
new_response.href = resp_tree.find('//href').text
if resp_tree.find('//collection') is not None:
new_response.resourcetype = 'collection'
else:
new_response.resourcetype = 'resource'
new_response.executable = getattr(resp_tree.find('//executable'), 'text', None)
new_response.creationdate = getattr(resp_tree.find('//creationdate'), 'text', None)
new_response.getcontentlength = getattr(resp_tree.find('//getcontentlength'), 'text', None)
new_response.getlastmodified = getattr(resp_tree.find('//getlastmodified'), 'text', None)
new_response.getetag = getattr(resp_tree.find('//getetag'), 'text', None)
new_response.getcontenttype = getattr(resp_tree.find('//getcontenttype'), 'text', None)
# Now we have the properties that are easy to get, lets get the lock information
lock_tree = resp_tree.findall('//lockentry')
for lock in lock_tree:
lock_tree = ElementTree(lock)
lock_obj = Lock()
lock_obj.locktype = lock_tree.find('//locktype').getchildren()[-1].tag
lock_obj.lockscope = lock_tree.find('//lockscope').getchildren()[-1].tag
new_response.locks.append(lock_obj)
self.response_objects.append(new_response)
except Exception, err:
err
