Should I use PyXML or what\'s in the standard library?
ElementTree is provided as part of the standard Python libs. ElementTree is pure python, and cElementTree is the faster C implementation:
# Try to use the C implementation first, falling back to python
try:
from xml.etree import cElementTree as ElementTree
except ImportError, e:
from xml.etree import ElementTree
Here's an example usage, where I'm consuming xml from a RESTful web service:
def find(*args, **kwargs):
"""Find a book in the collection specified"""
search_args = [('access_key', api_key),]
if not is_valid_collection(kwargs['collection']):
return None
kwargs.pop('collection')
for key in kwargs:
# Only the first keword is honored
if kwargs[key]:
search_args.append(('index1', key))
search_args.append(('value1', kwargs[key]))
break
url = urllib.basejoin(api_url, '%s.xml' % 'books')
data = urllib.urlencode(search_args)
req = urllib2.urlopen(url, data)
rdata = []
chunk = 'xx'
while chunk:
chunk = req.read()
if chunk:
rdata.append(chunk)
tree = ElementTree.fromstring(''.join(rdata))
results = []
for i, elem in enumerate(tree.getiterator('BookData')):
results.append(
{'isbn': elem.get('isbn'),
'isbn13': elem.get('isbn13'),
'title': elem.find('Title').text,
'author': elem.find('AuthorsText').text,
'publisher': elem.find('PublisherText').text,}
)
return results