详细解读Python中解析XML数据的方法

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()

Steve Holden: Python for Data Analysis
Mon, 19 Nov 2012 02:13:51 +0000
http://holdenweb.blogspot.com/2012/11/python-for-data-analysis.html

Vasudev Ram: The Python Data model (for v2 and v3)
Sun, 18 Nov 2012 22:06:47 +0000
http://jugad2.blogspot.com/2012/11/the-python-data-model.html

Python Diary: Been playing around with Object Databases
Sun, 18 Nov 2012 20:40:29 +0000
http://www.pythondiary.com/blog/Nov.18,2012/been-...-object-databases.html

Vasudev Ram: Wakari, Scientific Python in the cloud
Sun, 18 Nov 2012 20:19:41 +0000
http://jugad2.blogspot.com/2012/11/wakari-scientific-python-in-cloud.html

Jesse Jiryu Davis: Toro: synchronization primitives for Tornado coroutines
Sun, 18 Nov 2012 20:17:49 +0000
http://feedproxy.google.com/~r/EmptysquarePython/~3/_DOZT2Kd0hQ/

<?xml version="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')
>>>

from xml.etree.ElementTree import iterparse

def parse_and_remove(filename, path):
  path_parts = path.split('/')
  doc = iterparse(filename, ('start', 'end'))
  # Skip the root element
  next(doc)

  tag_stack = []
  elem_stack = []
  for event, elem in doc:
    if event == 'start':
      tag_stack.append(elem.tag)
      elem_stack.append(elem)
    elif event == 'end':
      if tag_stack == path_parts:
        yield elem
        elem_stack[-2].remove(elem)
      try:
        tag_stack.pop()
        elem_stack.pop()
      except IndexError:
        pass

from xml.etree.ElementTree import parse
from collections import Counter

potholes_by_zip = Counter()

doc = parse('potholes.xml')
for pothole in doc.iterfind('row/row'):
  potholes_by_zip[pothole.findtext('zip')] += 1
for zipcode, num in potholes_by_zip.most_common():
  print(zipcode, num)

from collections import Counter

potholes_by_zip = Counter()

data = parse_and_remove('potholes.xml', 'row/row')
for pothole in data:
  potholes_by_zip[pothole.findtext('zip')] += 1
for zipcode, num in potholes_by_zip.most_common():
  print(zipcode, num)

>>> data = iterparse('potholes.xml',('start','end'))
>>> next(data)
('start', <Element 'response' at 0x100771d60>)
>>> next(data)
('start', <Element 'row' at 0x100771e68>)
>>> next(data)
('start', <Element 'row' at 0x100771fc8>)
>>> next(data)
('start', <Element 'creation_date' at 0x100771f18>)
>>> next(data)
('end', <Element 'creation_date' at 0x100771f18>)
>>> next(data)
('start', <Element 'status' at 0x1006a7f18>)
>>> next(data)
('end', <Element 'status' at 0x1006a7f18>)
>>>

elem_stack[-2].remove(elem)