python解析xml文件为pdf_python 解析xml文件

https://www.cnblogs.com/handsome1013/p/10058838.html

ET.Parser 用法

https://www.cnblogs.com/yezuhui/p/6853323.html

Python3 xml解析模块xml.etree.ElementTree简介

删除重复xml节点

import xml.etree.ElementTree as ET----------导入xml模块

root = ET.parse('GHO.xml')------------------分析指定xml文件

tree = root.getroot()-----------------------获取第一标签

data = tree.find('Data')--------------------查找第一标签中'Data'标签

for obs in data:----------------------------历遍'Data'中的所有标签

for item in obs:------------------------历遍'Data'中的'obs'标签下的所有标签

key = item.attrib()-----------------提取key值参数

print(list(key))--------------------输出key值

如何读取属性及节点内容。

怎样将data中的 id,name及其值取出来？

问题解释

两种方式：

1.先取得node

String strID = node.getAttributes().getNamedItem("id").getNodeValue();

String strName = node.getAttributes().getNamedItem("name").getNodeValue();

2.先取得element

String strID = element.getAttribute("id");

String strName = element.getAttribute("name");

小练习

#!/usr/bin/env python

import sys

import xml.etree.ElementTree as ET

tree = ET.parse('abcdefg.xml')

root = tree.getroot()

iter_elem = root.findall('.//*')

print(len(iter_elem))

#elem = root.find('')

#print iter_elem

for element in iter_elem:

if element is None:

continue

if element.text is None:

continue

print("hello")

context=[]

src_elem = element.find("source")

if src_elem is None:

continue

context.append(src_elem.text)

print( "attri :%s"%src_elem.attrib)

print("tag :%s"%src_elem.tag)

#for item in src_elem:

# key = item.text()

# print list(key)

del duplicatd node:

import xml.etree.ElementTree as ET

path = 'in.xml'

tree = ET.parse(path)

root = tree.getroot()

prev = None

def elements_equal(e1, e2):

if type(e1) != type(e2):

return False

if e1.tag != e1.tag: return False

if e1.text != e2.text: return False

if e1.tail != e2.tail: return False

if e1.attrib != e2.attrib: return False

if len(e1) != len(e2): return False

return all([elements_equal(c1, c2) for c1, c2 in zip(e1, e2)])

for page in root: # iterate over pages

elems_to_remove = []

for elem in page:

if elements_equal(elem, prev):

print("found duplicate: %s" % elem.text) # equal function works well

elems_to_remove.append(elem)

continue

prev = elem

for elem_to_remove in elems_to_remove:

page.remove(elem_to_remove)

tree.write("out.xml")