用于Python的XML编写工具
我目前正在尝试ElementTree，它看起来很好，它转义HTML实体等等。 我是否错过了一些我从来没有听说过的奇妙的东西？
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 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> 我假设你实际上正在创build一个XML DOM树，因为你要validation这个文件是什么是有效的XML，否则你只需要向文件写一个静态string。 如果validation你的输出确实是你的目标，那么我会build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() )
这让你只需要编写你想要输出的XML，validation它是正确的（因为parseString会在exception无效的情况下产生exception）并让你的代码更好看。
据推测，你不是每次都写同样的静态XML，并想要一些替代。 在这种情况下，我会有类似的行
var a = '%(message)s'
然后使用％运算符来进行replace，就像
</html>""" % {"message": "I love &aacute; letters"})
另一种方法是使用lxml的E Factory Builder（也可以在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")), ... Ep("This is a paragraph with ", Eb("bold"), " text in it!"), ... Ep("This is another paragraph, with a", "\n ", ... Ea("link", href="http://www.python.org"), "."), ... Ep("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>
总是有SimpleXMLWriter ，它是ElementTree工具箱的一部分。 界面非常简单。
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)
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)
你不是真的想要像这样的东西：
html(head(script(type='text/javascript', content='var a = ...')), body(h1('And I like the fact that 3 < 1'), p('just some paragraph'))
我想我在某处看到了类似的东西。 这将是美好的。
编辑：其实，我今天去写了一个图书馆来做这个 ： 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 &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的魔力在于如何导入工程： Element工厂在需要的时候被创build。 看看源代码 ，它是基于另一个StackOverflow问题的答案 。
我结束了使用saxutils.escape（str）生成有效的XMLstring，然后用Eli的方法validation它，以确保我没有错过任何标签
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"
对于现在遇到这种情况的人来说，实际上有一种方法可以在xml.sax.utils.XMLGenerator中隐藏在Python标准库中。 下面是它的一个例子：
>>> 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>
尝试http://uche.ogbuji.net/tech/4suite/amara 。 这是相当完整的，有一个简单的访问工具。 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')
