python: xmlhelper

xml:

<?xml version="1.0"?>
<data>
    <country name="Liechtenstein">
        <rank>1</rank>
        <year>2008</year>
        <gdppc>141100</gdppc>
        <neighbor name="Austria" direction="E"/>
        <neighbor name="Switzerland" direction="W"/>
    </country>
    <country name="Singapore">
        <rank>4</rank>
        <year>2011</year>
        <gdppc>59900</gdppc>
        <neighbor name="Malaysia" direction="N"/>
    </country>
    <country name="Panama">
        <rank>68</rank>
        <year>2011</year>
        <gdppc>13600</gdppc>
        <neighbor name="Costa Rica" direction="W"/>
        <neighbor name="Colombia" direction="E"/>
    </country>
</data>

# encoding: utf-8
# 版权所有 2023 涂聚文有限公司
# 许可信息查看：
# 描述： pip install beautifulsoup4
# Author    : geovindu,Geovin Du 涂聚文.
# IDE       : PyCharm 2023.1 python 311
# Datetime  : 2023/7/16 22:17
# User      : geovindu
# Product   : PyCharm
# Project   : pythonTkinterDemo
# File      : XmlHelper.py
# explain   : 学习


from xml.dom import minidom
import xml.etree.ElementTree as ET
import csv
import requests
import os
import sys

def readXml(url):
    tree = ET.parse(url)
    root = tree.getroot()
    for child in root:
        print(child.tag, child.attrib)


def writeXml(url):
    # 实例化Document树
    doc = minidom.Document()
    # 创建根结点，XML必须存在root元素
    root_node = doc.createElement('root')
    # 将元素挂载在doc树中
    doc.appendChild(root_node)

    # 创建子元素
    c_node1 = doc.createElement('movie')
    root_node.appendChild(c_node1)
    # 设置该元素存储数据
    c_node1.setAttribute('shelf', 'New Arrivals')
    # 二级子结点
    c_node2 = doc.createElement('type')
    c_node1.appendChild(c_node2)
    # 也用DOM创建文本结点，把文本结点（文字内容）看成子结点
    c_text = doc.createTextNode("War, Thriller")
    c_node2.appendChild(c_text)
    try:
        with open(url, 'w', encoding='UTF-8') as f:
            # 第一个参数是目标文件对象
            doc.writexml(f, indent='', addindent='\t', newl='\n', encoding='UTF-8')
    except Exception as e:
        print('错误：', e)


def loadRSS():
    # url of rss feed
    url = 'http://www.hindustantimes.com/rss/topnews/rssfeed.xml'

    # creating HTTP response object from given url
    resp = requests.get(url)

    # saving the xml file
    with open('topnewsfeed.xml', 'wb') as f:
        f.write(resp.content)


def parseXML(xmlfile):
    # create element tree object
    tree = ET.parse(xmlfile)

    # get root element
    root = tree.getroot()

    # create empty list for news items
    newsitems = []

    # iterate news items
    for item in root.findall('./channel/item'):

        # empty news dictionary
        news = {}

        # iterate child elements of item
        for child in item:

            # special checking for namespace object content:media
            if child.tag == '{http://search.yahoo.com/mrss/}content':
                news['media'] = child.attrib['url']
            else:
                news[child.tag] = child.text.encode('utf8')

        # append news dictionary to news items list
        newsitems.append(news)

    # return news items list
    return newsitems


def savetoCSV(newsitems, filename):
    # specifying the fields for csv file
    fields = ['guid', 'title', 'pubDate', 'description', 'link', 'media']

    # writing to csv file
    with open(filename, 'w') as csvfile:
        # creating a csv dict writer object
        writer = csv.DictWriter(csvfile, fieldnames=fields)

        # writing headers (field names)
        writer.writeheader()

        # writing data rows
        writer.writerows(newsitems)


def main():
    # load rss from web to update existing xml file
    loadRSS()

    # parse xml file
    newsitems = parseXML('topnewsfeed.xml')

    # store news items in a csv file
    savetoCSV(newsitems, 'geovindu.csv')