python解析xml文件操作实例
程序员文章站
2023-11-04 15:54:34
本文实例讲述了python解析xml文件操作的实现方法。分享给大家供大家参考。具体方法如下：
xml文件内容如下：
本文实例讲述了python解析xml文件操作的实现方法。分享给大家供大家参考。具体方法如下：
xml文件内容如下：
<?xml version="1.0" ?>
<!--simple xml document__chapter 8-->
<book>
<title>
sample xml thing
</title>
<author>
<name>
<first>
ma
</first>
<last>
xiaoju
</last>
</name>
<affiliation>
springs widgets, inc.
</affiliation>
</author>
<chapter number="1">
<title>
first
</title>
<para>
i think widgets are greate.you should buy lots of them forom
<company>
spirngy widgts, inc
</company>
</para>
</chapter>
</book>
python代码：
from xml.dom import minidom, node
import re, textwrap
class samplescanner:
""""""
def __init__(self, doc):
"""constructor"""
assert(isinstance(doc, minidom.document))
for child in doc.childnodes:
if child.nodetype == node.element_node and \
child.tagname == "book":
self.handle_book(child)
def handle_book(self, node):
for child in node.childnodes:
if child.nodetype != node.element_node:
continue
if child.tagname == "title":
print "book titile is:", self.gettext(child.childnodes)
if child.tagname == "author":
self.handle_author(child)
if child.tagname == "chapter":
self.handle_chapter(child)
def handle_chapter(self, node):
number = node.getattribute("number")
print "number:", number
title_node = node.getelementsbytagname("title")
print "title:", self.gettext(title_node)
for child in node.childnodes:
if child.nodetype != node.element_node:
continue
if child.tagname == "para":
self.handle_chapter_para(child)
def handle_chapter_para(self, node):
company = ""
company = self.gettext(node.getelementsbytagname("company"))
print "chapter:para:company", company
def handle_author(self, node):
for child in node.childnodes:
if child.nodetype != node.element_node:
continue
if child.tagname == "name":
self.handle_author_name(child)
if child.tagname == "affiliation":
print "affiliation:", self.gettext(child.childnodes)
def handle_author_name(self, node):
first = ""
last = ""
for child in node.childnodes:
if child.nodetype != node.element_node:
continue
if child.tagname == "first":
first = self.gettext(child.childnodes)
if child.tagname == 'last':
last = self.gettext(child.childnodes)
print "firstname:%s,lastname:%s" % (first, last)
def gettext(self, nodelist):
retlist = []
for node in nodelist:
if node.nodetype == node.text_node:
retlist.append(node.wholetext)
elif node.haschildnodes:
retlist.append(self.gettext(node.childnodes))
return re.sub('\s+', " ", ''.join(retlist))
if __name__=="__main__":
doc = minidom.parse("simple.xml")
sample = samplescanner(doc)
希望本文所述对大家的python程序设计有所帮助。