我正在使用这个 Python XML 序列化库dexml。我不太清楚如何在我从对象生成的这个 xml 中的某些标签上放置属性。我通读了文档,除非我看不懂,否则我找不到一个很好的解释。
这是涉及的代码。
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 = []
# You might wonder about the length of this; I *could* split it up
# into variables to make it shorter. Also, the chaining is because
# the 'li' I want are only inside of a <ul class="Nav_fm>".
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()
这是生成的 XML。
<?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>
我想<Entry href="...">...</Entry>
为每个<Entry>
.