If you come across a list in the data then you just need to call myprint on every element of the list:
def myprint(d):
if isinstance(d,dict): #check if it's a dict before using .iteritems()
for k, v in d.iteritems():
if isinstance(v, (list,dict)): #check for either list or dict
myprint(v)
else:
print "Key :{0}, Value: {1}".format(k, v)
elif isinstance(d,list): #allow for list input too
for item in d:
myprint(item)
then you will get an output something like:
...
Key :@name, Value: Employee
Key :@isMandotory, Value: True
Key :#text, Value: Jake Roberts
Key :@name, Value: Section
Key :@isOpen, Value: True
Key :@isMandotory, Value: False
Key :#text, Value: 5
...
Although I'm not sure how useful this is since you have a lot of duplicate keys like @name, I'd like to offer a function I created a while ago to traverse nested json data of nested dicts and lists:
def traverse(obj, prev_path = "obj", path_repr = "{}[{!r}]".format, yield_empty_lists_and_dicts=True):
it = None
if isinstance(obj,dict):
it = obj.items()
elif isinstance(obj,list):
it = enumerate(obj)
if it is None or (yield_empty_lists_and_dicts and len(obj)==0):
yield prev_path,obj
return
for k,v in it:
for data in traverse(v, path_repr(prev_path,k), path_repr):
yield data
Then you can traverse the data with:
for path,value in traverse(doc):
print("{} = {}".format(path,value))
with the default values for prev_path and path_repr it gives output like this:
obj[u'session'][u'@id'] = 2934
obj[u'session'][u'@name'] = Valves
obj[u'session'][u'@docVersion'] = 5.0.1
obj[u'session'][u'docInfo'][u'field'][0][u'@name'] = Employee
obj[u'session'][u'docInfo'][u'field'][0][u'@isMandotory'] = True
obj[u'session'][u'docInfo'][u'field'][0]['#text'] = Jake Roberts
obj[u'session'][u'docInfo'][u'field'][1][u'@name'] = Section
obj[u'session'][u'docInfo'][u'field'][1][u'@isOpen'] = True
obj[u'session'][u'docInfo'][u'field'][1][u'@isMandotory'] = False
obj[u'session'][u'docInfo'][u'field'][1]['#text'] = 5
obj[u'session'][u'docInfo'][u'field'][2][u'@name'] = Location
obj[u'session'][u'docInfo'][u'field'][2][u'@isOpen'] = True
obj[u'session'][u'docInfo'][u'field'][2][u'@isMandotory'] = False
obj[u'session'][u'docInfo'][u'field'][2]['#text'] = Munchen
although you can write a function for path_repr to take the value of prev_path (determined by recursively calling path_repr) and the new key, for example a function to take a tuple and add another element on the end means we can get a (tuple of indices : elem) format which is perfect to pass to the dict constructor
def _tuple_concat(tup, idx):
return (*tup, idx)
def flatten_data(obj):
"""converts nested dict and list structure into a flat dictionary with tuple keys
corresponding to the sequence of indices to reach particular element"""
return dict(traverse(obj, (), _tuple_concat))
new_data = flatten_data(obj)
import pprint
pprint.pprint(new_data)
which gives you the data in this dictionary format:
{('session', '@docVersion'): '5.0.1',
('session', '@id'): 2934,
('session', '@name'): 'Valves',
('session', 'docInfo', 'field', 0, '#text'): 'Jake Roberts',
('session', 'docInfo', 'field', 0, '@isMandotory'): True,
('session', 'docInfo', 'field', 0, '@name'): 'Employee',
('session', 'docInfo', 'field', 1, '#text'): 5,
('session', 'docInfo', 'field', 1, '@isMandotory'): False,
('session', 'docInfo', 'field', 1, '@isOpen'): True,
('session', 'docInfo', 'field', 1, '@name'): 'Section',
('session', 'docInfo', 'field', 2, '#text'): 'Munchen',
('session', 'docInfo', 'field', 2, '@isMandotory'): False,
('session', 'docInfo', 'field', 2, '@isOpen'): True,
('session', 'docInfo', 'field', 2, '@name'): 'Location'}
I found this particularly useful when dealing with my json data but I'm not really sure what you want to do with your xml.
