XML writing tools for Python

I'm currently trying ElementTree and it looks fine, it escapes HTML entities and so on and so forth. Am I missing something truly wonderful I haven't heard of?

This is similar to what I'm actually doing:

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>

标签： python xml xhtml

8条回答

冷血范

2楼-- · 2019-01-30 11:49

For anyone encountering this now, there's actually a way to do this hidden away in Python's standard library in xml.sax.utils.XMLGenerator. Here's an example of it in action:

>>> 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>

0人赞添加讨论(0) 举报

一夜七次

3楼-- · 2019-01-30 11:51

I assume that you're actually creating an XML DOM tree, because you want to validate that what goes into this file is valid XML, since otherwise you'd just write a static string to a file. If validating your output is indeed your goal, then I'd suggest

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() )

This lets you just write the XML you want to output, validate that it's correct (since parseString will raise an exception if it's invalid) and have your code look much nicer.

Presumably you're not just writing the same static XML every time and want some substitution. In this case I'd have lines like

var a = '%(message)s'

and then use the % operator to do the substitution, like

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

0人赞添加讨论(0) 举报

别忘想泡老子

4楼-- · 2019-01-30 11:55

Try http://uche.ogbuji.net/tech/4suite/amara. It is quite complete and has a straight forward set of access tools. Normal Unicode support, etc.

#
#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')

0人赞添加讨论(0) 举报

闹够了就滚

5楼-- · 2019-01-30 11:57

Another way is using the E Factory builder from lxml (available in Elementtree too)

>>> 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>

0人赞添加讨论(0) 举报

欢心

6楼-- · 2019-01-30 12:01

There's always SimpleXMLWriter, part of the ElementTree toolkit. The interface is dead simple.

Here's an example:

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)

0人赞添加讨论(0) 举报

小情绪 Triste *

7楼-- · 2019-01-30 12:01

I ended up using saxutils.escape(str) to generate valid XML strings and then validating it with Eli's approach to be sure I didn't miss any tag

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"

0人赞添加讨论(0) 举报

1 2 下一页

XML writing tools for Python

采纳回答

编辑标签

举报内容

检举类型

检举原因

检举说明(必填)

打开微信“扫一扫”，打开网页后点击屏幕右上角分享按钮

付费偷看金额在0.1-10元之间