适用于Python的XML编写工具
时间：2020-03-05 18:51:21 来源:igfitidea点击:
我目前正在尝试ElementTree，它看起来还不错，它可以转义HTML实体，依此类推。我是否错过了我从未听说过的真正奇妙的东西？
这类似于我的实际操作：
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 á 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 &aacute;
letters'</script></head><body><h1>And I like the fact that 3 > 1</h1>
</body></html>
解决方案
回答
我们实际上不是想要这样的东西吗：
html(head(script(type='text/javascript', content='var a = ...')),
body(h1('And I like the fact that 3 < 1'), p('just some paragraph'))
我想我在某处看到了类似的东西。太好了
编辑：实际上，我今天去写了一个库来做到这一点：magictree
我们可以像这样使用它：
from magictree import html, head, script, body, h1, p
root = html(
head(
script('''var a = 'I love &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"中的魔力在于导入的工作方式：在需要时创建" Element"工厂。看一下源代码，它基于另一个StackOverflow问题的答案。
回答
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: <spam&egg>.</p>
<p>And finally an embedded XHTML fragment.</p>
</body>
</html>
回答
我假设我们实际上是在创建XML DOM树，因为我们要验证此文件中包含的内容是有效的XML，否则我们将只向文件中写入静态字符串。如果验证输出确实是目标，那么我建议
from xml.dom.minidom import parseString
doc = parseString("""<html>
<head>
<script type="text/javascript">
var a = 'I love &aacute; letters'
</script>
</head>
<body>
<h1>And I like the fact that 3 > 1</h1>
</body>
</html>""")
with open("foo.xhtml", "w") as f:
f.write( doc.toxml() )
这使我们可以只编写要输出的XML，验证其正确性(因为parseString如果无效则将引发异常)，并使代码看起来更好。
大概我们不只是每次都编写相同的静态XML并且想要进行替换。在这种情况下，我会有像
var a = '%(message)s'
然后使用％运算符进行替换，例如
</html>""" % {"message": "I love &aacute; letters"})
回答
尝试http://uche.ogbuji.net/tech/4suite/amara。它非常完整，并且具有一组直接的访问工具。普通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')
回答
我最终使用saxutils.escape(str)生成了有效的XML字符串，然后使用Eli的方法对其进行了验证，以确保我不会错过任何标签
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"
回答
总有SimpleXMLWriter，它是ElementTree工具包的一部分。该接口非常简单。
这是一个例子：
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)
