Python用Etree替换XML内容

我想用Python Etree解析器解析和比较2个XML文件，如下所示：

我有2个包含大量数据的XML文件。一个是英文（源文件），另一个是相应的法文翻译（目标文件）。 例如：

源文件：

<AB>
  <CD/>
  <EF>

    <GH>
      <id>123</id>
      <IJ>xyz</IJ>
      <KL>DOG</KL>
      <MN>dogs/dog</MN>
      some more tags and info on same level
      <metadata>
        <entry>
           <cl>Translation</cl>
           <cl>English:dog/dogs</cl>
        </entry>
        <entry>
           <string>blabla</string>
           <string>blabla</string>
        </entry>
            some more strings and entries
      </metadata>
    </GH>

  </EF>
  <stuff/>
  <morestuff/>
  <otherstuff/>
  <stuffstuff/>
  <blubb/>
  <bla/>
  <blubbbla>8</blubbla>
</AB>

---

我不仅仅是个傻瓜，阅读其他关于这个的帖子更让我困惑。如果有人能启发我，我将不胜感激：-）

可能还有更多细节需要澄清。下面是一些调试打印的示例，展示了这个想法。它假定两个文件具有完全相同的结构，并且您只希望位于根目录下一个级别：

import xml.etree.ElementTree as etree

english_tree = etree.parse('en.xml')
french_tree = etree.parse('fr.xml')

# Get the root elements, as they support iteration
# through their children (direct descendants)
english_root = english_tree.getroot()
french_root = french_tree.getroot()

# Iterate through the direct descendants of the root
# elements in both trees in parallel.
for en, fr in zip(english_root, french_root):
   assert en.tag == fr.tag # check for the same structure
   if en.tag == 'id':
       assert en.text == fr.text # check for the same id

   elif en.tag == 'string':
       if fr.text is None:
           fr.text = en.text
           print en.text      # displaying what was replaced

etree.dump(french_tree)

对于更复杂的文件结构，通过节点的直接子级的循环可以被通过树的所有元素的迭代所代替。如果文件的结构完全相同，则以下代码将起作用：

import xml.etree.ElementTree as etree

english_tree = etree.parse('en.xml')
french_tree = etree.parse('fr.xml')

for en, fr in zip(english_tree.iter(), french_tree.iter()):
   assert en.tag == fr.tag        # check if the structure is the same
   if en.tag == 'id':
       assert en.text == fr.text  # identification must be the same
   elif en.tag == 'string':
       if fr.text is None:
           fr.text = en.text
           print en.text          # display the inserted text

# Write the result to the output file.
with open('fr2.xml', 'w') as fout:
    fout.write(etree.tostring(french_tree.getroot()))

但是，它仅在两个文件的结构完全相同的情况下才起作用。让我们按照手动完成任务时使用的算法进行操作。首先，我们需要找到空的法语翻译。然后，应将其替换为具有相同标识的GH元素的英文翻译。在搜索元素时使用XPath表达式的子集：

import xml.etree.ElementTree as etree

def find_translation(tree, id_):
    # Search fot the GH element with the given identification, and return
    # its translation if found. Otherwise None is returned implicitly.
    for gh in tree.iter('GH'):
       id_elem = gh.find('./id')
       if id_ == id_elem.text:
           # The related GH element found.
           # Find metadata entry, extract the translation.
           # Warning! This is simplification for the fixed position 
           # of the Translation entry.
           me = gh.find('./metadata/entry')
           assert len(me) == 2     # metadata/entry has two elements
           cl1 = me[0]
           assert cl1.text == 'Translation'
           cl2 = me[1]

           return cl2.text


# Body of the program. --------------------------------------------------

english_tree = etree.parse('en.xml')
french_tree = etree.parse('fr.xml')

for gh in french_tree.iter('GH'): # iterate through the GH elements only 
   # Get the identification of the GH section
   id_elem = gh.find('./id')      
   id_ = id_elem.text

   # Find and check the metadata entry, extract the French translation.
   # Warning! This is simplification for the fixed position of the Translation 
   # entry.
   me = gh.find('./metadata/entry')
   assert len(me) == 2     # metadata/entry has two elements
   cl1 = me[0]
   assert cl1.text == 'Translation'
   cl2 = me[1]
   fr_translation = cl2.text

   # If the French translation is empty, put there the English translation
   # from the related element.
   if cl2.text is None:
       cl2.text = find_translation(english_tree, id_)


with open('fr2.xml', 'w') as fout:
   fout.write(etree.tostring(french_tree.getroot()).decode('utf-8'))

---

最好附加一个更复杂的示例来帮助解决方案的正确性。现在是使用XPath的时候了（标准的

xml.etree.ElementTree

只支持它的一些特性，但它们的功能足够强大）。尝试修改后的答案（最后一部分）。修复输入/输出文件的名称。然后我建议清理这里的评论，使其更具可读性，对其他人更有用。对……如果翻译条目不固定，我可以将翻译周围的“条目”标记重命名为独特的名称，并以这种方式找到它，还是不建议这样做（因为我试过了，但没有成功，但我想知道这是否是正确的方向？）标记重命名一般不应该进行。如果标记/元素有自己的特殊名称，则更好。这种方式

不是一个很好的示例。但我理解用户可能决定以交互方式插入该列，并且底层软件无法猜出用户想要什么。

import xml.etree.ElementTree as etree

english_tree = etree.parse('en.xml')
french_tree = etree.parse('fr.xml')

for en, fr in zip(english_tree.iter(), french_tree.iter()):
   assert en.tag == fr.tag        # check if the structure is the same
   if en.tag == 'id':
       assert en.text == fr.text  # identification must be the same
   elif en.tag == 'string':
       if fr.text is None:
           fr.text = en.text
           print en.text          # display the inserted text

# Write the result to the output file.
with open('fr2.xml', 'w') as fout:
    fout.write(etree.tostring(french_tree.getroot()))

import xml.etree.ElementTree as etree

def find_translation(tree, id_):
    # Search fot the GH element with the given identification, and return
    # its translation if found. Otherwise None is returned implicitly.
    for gh in tree.iter('GH'):
       id_elem = gh.find('./id')
       if id_ == id_elem.text:
           # The related GH element found.
           # Find metadata entry, extract the translation.
           # Warning! This is simplification for the fixed position 
           # of the Translation entry.
           me = gh.find('./metadata/entry')
           assert len(me) == 2     # metadata/entry has two elements
           cl1 = me[0]
           assert cl1.text == 'Translation'
           cl2 = me[1]

           return cl2.text


# Body of the program. --------------------------------------------------

english_tree = etree.parse('en.xml')
french_tree = etree.parse('fr.xml')

for gh in french_tree.iter('GH'): # iterate through the GH elements only 
   # Get the identification of the GH section
   id_elem = gh.find('./id')      
   id_ = id_elem.text

   # Find and check the metadata entry, extract the French translation.
   # Warning! This is simplification for the fixed position of the Translation 
   # entry.
   me = gh.find('./metadata/entry')
   assert len(me) == 2     # metadata/entry has two elements
   cl1 = me[0]
   assert cl1.text == 'Translation'
   cl2 = me[1]
   fr_translation = cl2.text

   # If the French translation is empty, put there the English translation
   # from the related element.
   if cl2.text is None:
       cl2.text = find_translation(english_tree, id_)


with open('fr2.xml', 'w') as fout:
   fout.write(etree.tostring(french_tree.getroot()).decode('utf-8'))