如何在dexml的标签中添加属性？

在使用dexml进行Python XML序列化时，需要在生成的XML中为某些标记添加属性，但是文档中没有找到如何实现这一目标的清晰说明。

以下是涉及的代码。

import dexml
import urllib2
from dexml import fields
from bs4 import BeautifulSoup

class Section(dexml.Model):
    section = fields.String()
    entries = fields.List(fields.String(tagname="Entry"))
    # Add something for href here, maybe?

class AtoZ(dexml.Model):
    list = fields.List(Section)

def makeSoup(url):
    return BeautifulSoup(urllib2.urlopen(url).read())

def main():
    soup = makeSoup("http://www.somewebsite.com")

    sectionList = []

    for li in soup.find('ul', {'class':"Nav_fm"}).find_all('li', {'class':"MenuLevel_0"}):
    atzSection = Section()
    atzSection.section = li.a.string

    for innerLi in li.find_all('li', {'class':"MenuLevel_1"}):
        atzSection.entries.append(innerLi.a.string)
        # Somehow store innlerLi.a['href'] in atzSection

    sectionList.append(atzSection)

    atzList = AtoZ(list=sectionList)

    f = open("C:\atoz.xml", "w")
    f.write(atzList.render(pretty=True))
    f.close()

if __name__ == '__main__':
    main()

如上所示，生成的XML是这样的：

<?xml version="1.0" ?>
<AtoZ>
    <Section section="#">
        <Entry>...</Entry>
        <Entry>...</Entry>
        <Entry>...</Entry>
        <Entry>...</Entry>
    </Section>
    ...
    <Section section="Z">
        <Entry>...</Entry>
        <Entry>...</Entry>
        <Entry>...</Entry>
        <Entry>...</Entry>
    </Section>
</AtoZ>

现在想要让每个<Entry>都有一个<href>属性。

2. 解决方案

注释1中给出的解决方案是重新定义Section.entries，使其成为一个由Entry项组成的列表，如下所示：

class Entry(dexml.Model):
    href = fields.String() 
    ...

class Section(dexml.Model):
    section = fields.String()
    entries = fields.List(fields.Model(Entry), tagname='Entry')

现在，就可以在渲染XML时为每个<Entry>添加一个<href>属性。

以下是完整的代码。

import dexml
import urllib2
from dexml import fields
from bs4 import BeautifulSoup

class Entry(dexml.Model):
    href = fields.String()
    content = fields.String()

class Section(dexml.Model):
    section = fields.String()
    entries = fields.List(fields.Model(Entry), tagname='Entry')

class AtoZ(dexml.Model):
    list = fields.List(Section)

def makeSoup(url):
    return BeautifulSoup(urllib2.urlopen(url).read())

def main():
    soup = makeSoup("http://www.somewebsite.com")

    sectionList = []

    for li in soup.find('ul', {'class':"Nav_fm"}).find_all('li', {'class':"MenuLevel_0"}):
    atzSection = Section()
    atzSection.section = li.a.string

    for innerLi in li.find_all('li', {'class':"MenuLevel_1"}):
        atzEntry = Entry()
        atzEntry.href = innerLi.a['href']
        atzEntry.content = innerLi.a.string
        atzSection.entries.append(atzEntry)

    sectionList.append(atzSection)

    atzList = AtoZ(list=sectionList)

    f = open("C:\atoz.xml", "w")
    f.write(atzList.render(pretty=True))
    f.close()

if __name__ == '__main__':
    main()

生成的XML现在如下所示：

<?xml version="1.0" ?>
<AtoZ>
    <Section section="#">
        <Entry href="...">...</Entry>
        <Entry href="...">...</Entry>
        <Entry href="...">...</Entry>
        <Entry href="...">...</Entry>
    </Section>
    ...
    <Section section="Z">
        <Entry href="...">...</Entry>
        <Entry href="...">...</Entry>
        <Entry href="...">...</Entry>
        <Entry href="...">...</Entry>
    </Section>
</AtoZ>

这就是利用dexml为标记添加属性的方法。