1 import copy
 2 import re
 3 import os
 4 
 5 try:
 6     from lxml import etree as lxml_etree
 7 except ImportError:
 8     lxml_etree = None
 9 
10 from robot.api import logger
11 from robot.libraries.BuiltIn import BuiltIn
12 from robot.utils import (asserts, ET, ETSource, is_string, is_truthy,
13                          plural_or_not as s)
14 from robot.version import get_version
15 
16 
17 should_be_equal = asserts.assert_equal
18 should_match = BuiltIn().should_match
19 
20 
21 class XML(object):
22  ROBOT_LIBRARY_SCOPE = ‘GLOBAL‘
23     ROBOT_LIBRARY_VERSION = get_version()
24     _xml_declaration = re.compile(‘^<\?xml .*\?>‘)
25   def __init__(self, use_lxml=False):
26   　　use_lxml = is_truthy(use_lxml)
27         if use_lxml and lxml_etree:
28             self.etree = lxml_etree
29             self.modern_etree = True
30             self.lxml_etree = True
31         else:
32             self.etree = ET
33             self.modern_etree = ET.VERSION >= ‘1.3‘
34             self.lxml_etree = False
35         if use_lxml and not lxml_etree:
36             logger.warn(‘XML library reverted to use standard ElementTree ‘
37                         ‘because lxml module is not installed.‘)
38 
39 
40   def parse_xml(self, source, keep_clark_notation=False):
41  　　with ETSource(source) as source:
42             tree = self.etree.parse(source)
43         if self.lxml_etree:
44             strip = (lxml_etree.Comment, lxml_etree.ProcessingInstruction)
45             lxml_etree.strip_elements(tree, *strip, **dict(with_tail=False))
46         root = tree.getroot()
47         if not is_truthy(keep_clark_notation):
48             NameSpaceStripper().strip(root)
49         return root

 　　python提供了几个标准库都可以对xml进行解析，之前我使用的是DOM，基于RF使用的是ETree，便开始学习了下ETree的开发文档。学习对XML文件的操作,那肯定也得对XML本身有最基本的了解，比如XML的用途，树结构，节点类型（DOM），带命名空间的xml。下面是部分的知识点的总结：

    xml是一种可扩展的标记语言。要求标记需要成对的出现（有时候会进行简写<b/>）。一个典型的xml文档如下所示：

 1 <example>
 2   <first id="1">text</first>
 3   <second id="2">
 4     <child/>
 5   </second>
 6   <third>
 7     <child>more text</child>
 8     <second id="child"/>
 9     <child><grandchild/></child>
10   </third>
11 </example>

 1 XML
 2 
 3 Library version:    3.0.2
 4 Library scope:    global
 5 Named arguments:    supported
 6 Introduction
 7 
 8 Robot Framework test library for verifying and modifying XML documents.
 9 As the name implies, XML is a test library for verifying contents of XML files. In practice it is a pretty thin wrapper on top of Python‘s ElementTree XML API.
10 The library has the following main usages:
11 Parsing an XML file, or a string containing XML, into an XML element structure and finding certain elements from it for for further analysis (e.g. Parse XML and Get Element keywords).
12 Getting text or attributes of elements (e.g. Get Element Text and Get Element Attribute).
13 Directly verifying text, attributes, or whole elements (e.g Element Text Should Be and Elements Should Be Equal).
14 Modifying XML and saving it (e.g. Set Element Text, Add Element and Save XML).
15 Table of contents
16 Parsing XML
17 Using lxml
18 Example
19 Finding elements with xpath
20 Element attributes
21 Handling XML namespaces
22 Boolean arguments
23 Shortcuts
24 Keywords