本文實例講述了python解析xml文件操作的實現方法。分享給大家供大家參考。具體方法如下：
xml文件內容如下：
ma
xiaoju
Springs Widgets, Inc.
I think widgets are greate.You should buy lots of them forom
Spirngy Widgts, Inc
python代碼：
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)
希望本文所述對大家的Python程序設計有所幫助。
更多文章、技術交流、商務合作、聯系博主
微信掃碼或搜索：z360901061
微信掃一掃加我為好友
QQ號聯系： 360901061
您的支持是博主寫作最大的動力，如果您喜歡我的文章，感覺我的文章對您有幫助，請用微信掃描下面二維碼支持博主2元、5元、10元、20元等您想捐的金額吧，狠狠點擊下面給點支持吧，站長非常感激您！手機微信長按不能支付解決辦法：請將微信支付二維碼保存到相冊，切換到微信，然后點擊微信右上角掃一掃功能，選擇支付二維碼完成支付。
【本文對您有幫助就好】元
