#!/usr/bin/python3.5 # from xml.parsers.expat import ParserCreate class defaultsax(object): def __init__(self): self.db = {} def start_element(self, name, attrs): print('sax:start_elementname:%s,attrs:%s' % (name,str(attrs))) def end_element(self, name): print('sax:end_element:%s' % name) pass def char_data(self, text): print('sax:char_data: %s' % text) #pass xml = r'''<?xml version="1.0" encoding="UTF-8" standalone="yes" ?> <rss version="2.0" xmlns:yweather="http://xml.weather.yahoo.com/ns/rss/1.0" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#"> <channel> <title>Yahoo! Weather - Beijing, CN</title> <lastBuildDate>Wed, 27 May 2015 11:00 am CST</lastBuildDate> <yweather:location city="Beijing" region="" country="China"/> <yweather:units temperature="C" distance="km" pressure="mb" speed="km/h"/> <yweather:wind chill="28" direction="180" speed="14.48" /> <yweather:atmosphere humidity="53" visibility="2.61" pressure="1006.1" rising="0" /> <yweather:astronomy sunrise="4:51 am" sunset="7:32 pm"/> <item> <geo:lat>39.91</geo:lat> <geo:long>116.39</geo:long> <pubDate>Wed, 27 May 2015 11:00 am CST</pubDate> <yweather:condition text="Haze" code="21" temp="28" date="Wed, 27 May 2015 11:00 am CST" /> <yweather:forecast day="Wed" date="27 May 2015" low="20" high="33" text="Partly Cloudy" code="30" /> <yweather:forecast day="Thu" date="28 May 2015" low="21" high="34" text="Sunny" code="32" /> <yweather:forecast day="Fri" date="29 May 2015" low="18" high="25" text="AM Showers" code="39" /> <yweather:forecast day="Sat" date="30 May 2015" low="18" high="32" text="Sunny" code="32" /> <yweather:forecast day="Sun" date="31 May 2015" low="20" high="37" text="Sunny" code="32" /> </item> </channel> </rss> ''' handler = defaultsax() parser = ParserCreate() parser.StartElementHandler = handler.start_element parser.EndElementHandler = handler.end_element parser.CharacterDataHandler = handler.char_data parser.Parse(xml)
执行之后发现end_element字段没有什么有用的信息,所有将其删除之:
def end_element(self, name): #print('sax:end_element:%s' % name) pass
为了方便分析,char_data字段也先不显示:
def char_data(self, text): print('sax:char_data: %s' % text) #pass
改好后,执行脚本,获得以下内容(只截取一部分):
很明显,name的内容也没有我们需要的内容,不过要根据name对不同行内容做处理,attrs是我们需要的真正内容,attrs显示的格式明显是字典,这时就可以利用字典的key得到我们想要的,更改start_element段代码并增加__init__段:
def __init__(self): self.weater = {} #定义一个空字典 def start_element(self, name, attrs): self.weater['na'] = name if self.weater['na'] == 'yweather:location': #对name=yweather:location行的attrs做处理 print('国家:%s,城市:%s' % (attrs['country'],attrs['city']))
保存并执行脚本:
然后根据需要,对每个行做相应的截取,最后得到自己想要的。