Python --解析xml

目录

1， sax解析xml

1， sax解析xml

dom会把整个xml文件读入到内存，占用内存大，sax是流模式， 边读边解析，占用内存小

#! /usr/bin/env/python3
# -*- coding: utf-8 -*-
 
'''解析xml中的天气字段'''
 
from xml.parsers.expat import ParserCreate
 
xml = '''
    
    1
    1
    OK
    10000
    
        
            北京市
            110000
            北京
            2021-05-14 18:33:48
            
                
                    2021-05-14
                    5
                    多云
                    小雨
                    26
                    17
                    东南
                    东南
                    ≤3
                    ≤3
                
                
                    2021-05-15
                    6
                    小雨
                    小雨
                    21
                    14
                    北
                    北
                    4
                    4
                
                
                    2021-05-16
                    7
                    多云
                    晴
                    25
                    13
                    西
                    西
                    ≤3
                    ≤3
                
                
                    2021-05-17
                    1
                    晴
                    晴
                    30
                    15
                    西南
                    西南
                    ≤3
                    ≤3
                
            
        
    
'''
 
class MySaxHandler(object):
    def __init__(self, city='Beijing'):
        # 城市字段
        self.city = city
        # 一天天气
        self.one_day_weather = {}
        # 所有天天气
        self.all_day_weather = []
        # 指定城市的所有天气
        self.weather = {'city': self.city, 'forecasts': self.all_day_weather}
        # 天气字段
        self.weather_attrs_list = ['date', 'week', 'dayweather', 'nightweather',         
                                  'daytemp', 'nighttemp', 'daywind', 'nightwind']
 
    def start_element_handler(self, name, attrs):
        '''
        开始标签处理方法
        :param name: 标签名称
        :param attrs: 标签属性
        :return:
        '''
        self.start_element_name = name
        self.start_element_attrs = attrs
 
    def end_element_handler(self, name):
        '''
        结束标签处理方法
        :param name: 标签名称
        :return:
        '''
        self.end_element_name = name
 
        if self.end_element_name in self.weather_attrs_list:
            self.one_day_weather[self.end_element_name] = self.text
 
        if len(self.one_day_weather) == len(self.weather_attrs_list):
            self.all_day_weather.append(self.one_day_weather)
            self.one_day_weather = {}
 
    def chardata_handler(self, text):
        '''
        标签信息处理方法
        :param text: 标签信息
        :return:
        '''
        self.text = text
 
def parser_xml(xml):
    my_handler = MySaxHandler()
    parser = ParserCreate()
    parser.StartElementHandler = my_handler.start_element_handler
    parser.EndElementHandler = my_handler.end_element_handler
    parser.CharacterDataHandler = my_handler.chardata_handler
    # 解析xml
    parser.Parse(xml)
 
    return my_handler.weather
 
 
if __name__ == "__main__":
    result = parser_xml(xml)
 
    print(result)
 
----------------------------------------------------------------------------------
# 输出
"C:\Program Files\Python311\python.exe" D:\python_core_programming_learn\chapter_7_dict_set\notes.py 
{'city': 'Beijing', 'forecasts': [{'date': '2021-05-14', 'week': '5', 'dayweather': '多云', 'nightweather': '小雨', 'daytemp': '26', 'nighttemp': '17', 'daywind': '东南', 'nightwind': '东南'}, {'date': '2021-05-15', 'week': '6', 'dayweather': '小雨', 'nightweather': '小雨', 'daytemp': '21', 'nighttemp': '14', 'daywind': '北', 'nightwind': '北'}, {'date': '2021-05-16', 'week': '7', 'dayweather': '多云', 'nightweather': '晴', 'daytemp': '25', 'nighttemp': '13', 'daywind': '西', 'nightwind': '西'}, {'date': '2021-05-17', 'week': '1', 'dayweather': '晴', 'nightweather': '晴', 'daytemp': '30', 'nighttemp': '15', 'daywind': '西南', 'nightwind': '西南'}]}