从xml标签中检索数据Python

Question

我试图使用以下代码检索'a：t'标签之间的类型=“slidenum”之间的幻灯片编号，但某些内容不起作用。我应该得到1

这里的XML：

<a:p><a:fld id="{55FBEE69-CA5C-45C8-BA74-481781281731}" type="slidenum"> 
<a:rPr lang="en-US" sz="1300" i="0"><a:solidFill><a:srgbClr val="000000"/> 
</a:solidFill></a:rPr><a:pPr/><a:t>1</a:t></a:fld><a:endParaRPr lang="en-US" 
sz="1300" i="0"><a:solidFill><a:srgbClr val="000000"/></a:solidFill> 
</a:endParaRPr></a:p></p:txBody></p:sp> 

这里是我的代码

z = zipfile.ZipFile(pptx_filename) 
    for name in z.namelist(): 
     m = re.match(r'ppt/notesSlides/notesSlide\d+\.xml', name) 
    if m is not None: 
     f = z.open(name) 
     tree = ET.parse(f) 
     f.close() 
     root = tree.getroot() 
     # Find the slide number. 
     slide_num = None 
     for fld in root.findall('/'.join(['.', '', p.txBody, a.p, a.fld])): 
      if fld.get('type', '') == 'slidenum': 
       slide_num = int(fld.find(a.t).text) 
       print slide_num 

Answer 1

：

# cElementTree is the faster, C language based big brother of ElementTree 
from xml.etree import cElementTree as etree 

# Our test XML 
xml = ''' 
<a:p xmlns:a="http://example.com"><a:fld id="{55FBEE69-CA5C-45C8-BA74-481781281731}" type="slidenum"> 
<a:rPr lang="en-US" sz="1300" i="0"><a:solidFill><a:srgbClr val="000000"/> 
</a:solidFill></a:rPr><a:pPr/><a:t>1</a:t></a:fld><a:endParaRPr lang="en-US" 
sz="1300" i="0"><a:solidFill><a:srgbClr val="000000"/></a:solidFill> 
</a:endParaRPr></a:p> 
''' 

# Manually specify the namespace. The prefix letter ("a") is arbitrary. 
namespaces = {"a":"http://example.com"} 

# Parse the XML string 
tree = etree.fromstring(xml) 

""" 
Breaking down the search expression below 
    a:fld - Find the fld element prefixed with namespace identifier a: 
    [@type='slidenum'] - Match on an attribute type with a value of 'slidenum' 
    /a:t - Find the child element t prefixed with namespace identifier a: 
""" 
slidenums = tree.findall("a:fld[@type='slidenum']/a:t", namespaces) 
for slidenum in slidenums: 
    print(slidenum.text) 

下面是使用使用提供的命名空间的外部文件相同的例子下面的OP：

from xml.etree import cElementTree as etree 

tree = etree.parse("my_xml_file.xml") 
namespaces = {"a":"http://schemas.openxmlformats.org/presentationml/2006/main"} 
slidenums = tree.findall("a:fld[@type='slidenum']/a:t", namespaces) 
for slidenum in slidenums: 
    print(slidenum.text) 

Answer 2

分析之前，我会删除您的XML命名空间的标签。然后使用XPATH fld[@type='slidenum']/t找到类型为fld的所有节点，其中fld[@type='slidenum']/t和子节点t。这里有一个例子来说明这是如何工作的：从Moxymoo的回答以下使用的命名空间，而不是删除它们的改性

from lxml import etree 

xml = """ 
<a:p><a:fld id="{55FBEE69-CA5C-45C8-BA74-481781281731}" type="slidenum"> 
<a:rPr lang="en-US" sz="1300" i="0"><a:solidFill><a:srgbClr val="000000"/> 
</a:solidFill></a:rPr><a:pPr/><a:t>1</a:t></a:fld><a:endParaRPr lang="en-US" 
sz="1300" i="0"><a:solidFill><a:srgbClr val="000000"/></a:solidFill> 
</a:endParaRPr></a:p> 
""" 

tree = etree.fromstring(xml.replace('a:','')) 
slidenum = tree.find("fld[@type='slidenum']/t").text 
print(slidenum) 
1