Question

我正在尝试使用ElementTree，它看起来很好，它可以逃脱HTML实体等等。我错过了一些我从未听说过的精彩内容吗？

这与我实际做的相似：

import xml.etree.ElementTree as ET
root = ET.Element('html')
head = ET.SubElement(root,'head')
script = ET.SubElement(head,'script')
script.set('type','text/javascript')
script.text = "var a = 'I love &aacute; letters'"
body = ET.SubElement(root,'body')
h1 = ET.SubElement(body,'h1')
h1.text = "And I like the fact that 3 > 1"
tree = ET.ElementTree(root)
tree.write('foo.xhtml')

# more foo.xhtml
<html><head><script type="text/javascript">var a = 'I love &amp;aacute;
letters'</script></head><body><h1>And I like the fact that 3 &gt; 1</h1>
</body></html>

Answer 1

另一种方法是使用lxml中的E Factory构建器（也可在Elementtree中使用）

>>> from lxml import etree

>>> from lxml.builder import E

>>> def CLASS(*args): # class is a reserved word in Python
...     return {"class":' '.join(args)}

>>> html = page = (
...   E.html(       # create an Element called "html"
...     E.head(
...       E.title("This is a sample document")
...     ),
...     E.body(
...       E.h1("Hello!", CLASS("title")),
...       E.p("This is a paragraph with ", E.b("bold"), " text in it!"),
...       E.p("This is another paragraph, with a", "\n      ",
...         E.a("link", href="http://www.python.org"), "."),
...       E.p("Here are some reserved characters: <spam&egg>."),
...       etree.XML("<p>And finally an embedded XHTML fragment.</p>"),
...     )
...   )
... )

>>> print(etree.tostring(page, pretty_print=True))
<html>
  <head>
    <title>This is a sample document</title>
  </head>
  <body>
    <h1 class="title">Hello!</h1>
    <p>This is a paragraph with <b>bold</b> text in it!</p>
    <p>This is another paragraph, with a
      <a href="http://www.python.org">link</a>.</p>
    <p>Here are some reservered characters: &lt;spam&amp;egg&gt;.</p>
    <p>And finally an embedded XHTML fragment.</p>
  </body>
</html>

Answer 2

总是SimpleXMLWriter，是ElementTree工具包的一部分。界面很简单。

以下是一个例子：

from elementtree.SimpleXMLWriter import XMLWriter
import sys

w = XMLWriter(sys.stdout)
html = w.start("html")

w.start("head")
w.element("title", "my document")
w.element("meta", name="generator", value="my application 1.0")
w.end()

w.start("body")
w.element("h1", "this is a heading")
w.element("p", "this is a paragraph")

w.start("p")
w.data("this is ")
w.element("b", "bold")
w.data(" and ")
w.element("i", "italic")
w.data(".")
w.end("p")

w.close(html)

Answer 3

我假设您实际上正在创建XML DOM树，因为您要验证进入此文件的内容是否为有效XML，否则您只需将静态字符串写入文件。如果确认您的输出确实是您的目标，那么我建议

from xml.dom.minidom import parseString

doc = parseString("""<html>
    <head>
        <script type="text/javascript">
            var a = 'I love &amp;aacute; letters'
        </script>
    </head>
    <body>
        <h1>And I like the fact that 3 &gt; 1</h1>
    </body>
    </html>""")

with open("foo.xhtml", "w") as f:
    f.write( doc.toxml() )

这使您可以只编写要输出的XML，验证它是否正确（因为如果它无效，parseString将引发异常）并使代码看起来更好。

据推测，您不仅每次都编写相同的静态XML，而且还需要替换。在这种情况下，我会有像

这样的行

var a = '%(message)s'

然后使用％运算符进行替换，如

</html>""" % {"message": "I love &amp;aacute; letters"})

Answer 4

https://github.com/galvez/xmlwitch：

import xmlwitch
xml = xmlwitch.Builder(version='1.0', encoding='utf-8')
with xml.feed(xmlns='http://www.w3.org/2005/Atom'):
    xml.title('Example Feed')
    xml.updated('2003-12-13T18:30:02Z')
    with xml.author:
        xml.name('John Doe')
    xml.id('urn:uuid:60a76c80-d399-11d9-b93C-0003939e0af6')
    with xml.entry:
        xml.title('Atom-Powered Robots Run Amok')
        xml.id('urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a')
        xml.updated('2003-12-13T18:30:02Z')
        xml.summary('Some text.')
print(xml)

Answer 5

你真的不想要这样的东西：

html(head(script(type='text/javascript', content='var a = ...')),
body(h1('And I like the fact that 3 < 1'), p('just some paragraph'))

我想我在某个地方看到了类似的东西。这太棒了。

编辑：实际上，我今天去写了一个图书馆：magictree

你可以像这样使用它：

from magictree import html, head, script, body, h1, p
root = html(
         head(
           script('''var a = 'I love &amp;aacute; letters''', 
                  type='text/javascript')),
         body(
           h1('And I like the fact that 3 > 1')))

# root is a plain Element object, like those created with ET.Element...
# so you can write it out using ElementTree :)
tree = ET.ElementTree(root)
tree.write('foo.xhtml')

magictree中的神奇之处在于导入的工作原理：Element工厂在需要时创建。有一个look at the source，它是based on an answer to another StackOverflow question。

Answer 6

我最终使用saxutils.escape（str）生成有效的XML字符串，然后使用Eli的方法验证它，以确保我没有遗漏任何标记

from xml.sax import saxutils
from xml.dom.minidom import parseString
from xml.parsers.expat import ExpatError

xml = '''<?xml version="1.0" encoding="%s"?>\n
<contents title="%s" crawl_date="%s" in_text_date="%s" 
url="%s">\n<main_post>%s</main_post>\n</contents>''' %
(self.encoding, saxutils.escape(title), saxutils.escape(time), 
saxutils.escape(date), saxutils.escape(url), saxutils.escape(contents))
try:
    minidoc = parseString(xml)
catch ExpatError:
    print "Invalid xml"

Answer 7

对于现在遇到这种情况的人来说，实际上有一种方法可以隐藏在xml.sax.utils.XMLGenerator中Python的标准库中。以下是它的实例：

>>> from xml.sax.saxutils import XMLGenerator
>>> import StringIO
>>> w = XMLGenerator(out, 'utf-8')
>>> w.startDocument()
>>> w.startElement("test", {'bar': 'baz'})
>>> w.characters("Foo")
>>> w.endElement("test")
>>> w.endDocument()
>>> print out.getvalue()
<?xml version="1.0" encoding="utf-8"?>
<test bar="baz">Foo</test>

Answer 8

试试http://uche.ogbuji.net/tech/4suite/amara。它非常完整，并有一套直接的访问工具。正常的Unicode支持等。

#
#Output the XML entry
#
def genFileOLD(out,label,term,idval):
    filename=entryTime() + ".html"
    writer=MarkupWriter(out, indent=u"yes")
    writer.startDocument()
    #Test element and attribute writing
    ans=namespace=u'http://www.w3.org/2005/Atom'
    xns=namespace=u'http://www.w3.org/1999/xhtml'
    writer.startElement(u'entry',
       ans,
       extraNss={u'x':u'http://www.w3.org/1999/xhtml' ,
                 u'dc':u'http://purl.org/dc/elements/1.1'})
    #u'a':u'http://www.w3.org/2005/Atom',
    #writer.attribute(u'xml:lang',unicode("en-UK"))

    writer.simpleElement(u'title',ans,content=unicode(label))
    #writer.simpleElement(u'a:subtitle',ans,content=u' ')
    id=unicode("http://www.dpawson.co.uk/nodesets/"+afn.split(".")[0])
    writer.simpleElement(u'id',ans,content=id)
    writer.simpleElement(u'updated',ans,content=unicode(dtime()))
    writer.startElement(u'author',ans)
    writer.simpleElement(u'name',ans,content=u'Dave ')
    writer.simpleElement(u'uri',ans,
      content=u'http://www.dpawson.co.uk/nodesets/'+afn+".xml")
    writer.endElement(u'author')
    writer.startElement(u'category', ans)
    if (prompt):
        label=unicode(raw_input("Enter label "))
    writer.attribute(u'label',unicode(label))
    if (prompt):
        term = unicode(raw_input("Enter term to use "))
    writer.attribute(u'term', unicode(term))
    writer.endElement(u'category')
    writer.simpleElement(u'rights',ans,content=u'\u00A9 Dave 2005-2008')
    writer.startElement(u'link',ans)
    writer.attribute(u'href',
         unicode("http://www.dpawson.co.uk/nodesets/entries/"+afn+".html"))
    writer.attribute(u'rel',unicode("alternate"))
    writer.endElement(u'link')
    writer.startElement(u'published', ans)
    dt=dtime()
    dtu=unicode(dt)
    writer.text(dtu)
    writer.endElement(u'published')
    writer.simpleElement(u'summary',ans,content=unicode(label))
    writer.startElement(u'content',ans)
    writer.attribute(u'type',unicode("xhtml"))
    writer.startElement(u'div',xns)
    writer.simpleElement(u'h3',xns,content=unicode(label))
    writer.endElement(u'div')
    writer.endElement(u'content')
    writer.endElement(u'entry')

用于Python的XML编写工具

8 个答案: