Python 解析简单的XML数据

from urllib.request import urlopen
from xml.etree.ElementTree import parse

# Download the RSS feed and parse it
u = urlopen('http://planet.python.org/rss20.xml')
doc = parse(u)

# Extract and output tags of interest
for item in doc.iterfind('channel/item'):
  title = item.findtext('title')
  date = item.findtext('pubDate')
  link = item.findtext('link')

  print(title)
  print(date)
  print(link)
  print()

<"1.0"?>
<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/">
  <channel>
    <title>Planet Python</title>
    <link>http://planet.python.org/</link>
    <language>en</language>
    <description>Planet Python - http://planet.python.org/</description>
    <item>
      <title>Steve Holden: Python for Data Analysis</title>
      <guid>http://holdenweb.blogspot.com/...-data-analysis.html</guid>
      <link>http://holdenweb.blogspot.com/...-data-analysis.html</link>
      <description>...</description>
      <pubDate>Mon, 19 Nov 2012 02:13:51 +0000</pubDate>
    </item>
    <item>
      <title>Vasudev Ram: The Python Data model (for v2 and v3)</title>
      <guid>http://jugad2.blogspot.com/...-data-model.html</guid>
      <link>http://jugad2.blogspot.com/...-data-model.html</link>
      <description>...</description>
      <pubDate>Sun, 18 Nov 2012 22:06:47 +0000</pubDate>
    </item>
    <item>
      <title>Python Diary: Been playing around with Object Databases</title>
      <guid>http://www.pythondiary.com/...-object-databases.html</guid>
      <link>http://www.pythondiary.com/...-object-databases.html</link>
      <description>...</description>
      <pubDate>Sun, 18 Nov 2012 20:40:29 +0000</pubDate>
    </item>
    ...
  </channel>
</rss>

> doc
<xml.etree.ElementTree.ElementTree object at 0x101339510>
> e = doc.find('channel/title')
> e
<Element 'title' at 0x10135b310>
> e.tag
'title'
> e.text
'Planet Python'
> e.get('some_attribute')
>