input.xml

<?xml version="1.0"?>
<actors xmlns:fictional="http://characters.example.com"
        xmlns="http://people.example.com">
    <actor>
        <name>John Cleese</name>
        <fictional:character>Lancelot</fictional:character>
        <fictional:character>Archie Leach</fictional:character>
    </actor>
    <actor>
        <name>Eric Idle</name>
        <fictional:character>Sir Robin</fictional:character>
        <fictional:character>Gunther</fictional:character>
        <fictional:character>Commander Clement</fictional:character>
    </actor>
</actors>

1 xml.dom.minidom(推荐*)

from xml.dom import minidom
tree = minidom.parse('input.xml')
actors = tree.getElementsByTagName('actor')
for actor in actors:
    name = actor.getElementsByTagName('name')[0].firstChild.nodeValue
    print name
    for character in actor.getElementsByTagName('fictional:character'):
        print '  |-->', character.firstChild.nodeValue

2 bs4(不推荐)

需要全部读入，适用于文件不太大

import bs4
with open('input.xml') as f:
  try:
      soup = bs4.BeautifulSoup(f.read(), 'lxml')        # use lxml parser, faster then default
  except:
    soup = bs4.BeautifulSoup(f.read(), 'html.parser') # default parser
  # 不能用soup.select('fictional:character')
  for actor in soup.find_all('actor'):
      print actor.find_all('name')[0].text
      for character in  actor.find_all('fictional:character'):
          print '  |-->', character.text

3 xml.etree.ElementTree/cElementTree(推荐**)

try:
    import xml.etree.cElementTree as ET   # cElementTree is faster
except ImportError:
    import xml.etree.ElementTree as ET
infile = 'ns.xml'
tree = ET.parse(infile)
root = tree.getroot()
# 该文件中含有两个命名空间：
#   特定的fictional   xmlns:fictional="http://characters.example.com"
#   默认的            xmlns="http://people.example.com" 
# 寻找元素时，不带fictional的元素即为默认的
# 下面自己设置了命名空间的映射，其中foo, bar可随意起名
ns = {
    'foo': 'http://people.example.com',
    'bar': 'http://characters.example.com'
}
for actor in root.findall('foo:actor', ns):
    print actor.find('foo:name', ns).text
    for character in actor.findall('bar:character', ns):
        print '  |-->', character.text

4 lxml.etree(推荐*)

import lxml.etree as ET
tree = ET.parse('input.xml')
root = tree.getroot()
ns = root.nsmap   # 自动获取namespace映射
# print ns
# {'fictional': 'http://characters.example.com', None: 'http://people.example.com'}
for actor in root.findall('actor', ns):
    print actor.find('name', ns).text
    for character in actor.findall('fictional:character', ns):
        print '  |-->', character.text

5 xml.parsers.expat(不确定)

据说速度较快，不过用起来比较麻烦，还未测试

PS: 测试比较