import xml.dom.minidom as xmldom
import os
xml_filepath = os.path.abspath("./originalData/train.xml")
# xml_filepath=os.path.abspath("V5-13.xml")
# 得到文件对象
dom_obj = xmldom.parse(xml_filepath)
# 得到元素对象
element_obj = dom_obj.documentElement
# 获得子标签
sub_element_obj = element_obj.getElementsByTagName("weibo")
for i in range(len(sub_element_obj)):
if sub_element_obj[i].getAttribute("emotion-type1") != "none":
sub_element_obj1 = sub_element_obj[i].getElementsByTagName("sentence")
for j in range(len(sub_element_obj1)):
if sub_element_obj1[j].getAttribute("opinionated") == "Y":
print(sub_element_obj1[j].getAttribute("emotion-1-type"), end='\t')
print(sub_element_obj1[j].firstChild.data, end='')
print()
所对应的XML格式
<weibo id="1" emotion-type="none">
<sentence id="1" emotion_tag="N">三八节下午路过中牟县~见到很多美女~手执鲜花[鲜花]~一打听~这里不仅美女如云~而且是千古笫一帅哥潘安的故里。。。</sentence>
<sentence id="2" emotion_tag="N">[给力][萌]</sentence>
</weibo>
<weibo id="2" emotion-type="sadness">
<sentence id="1" emotion_tag="Y" emotion-1-type="like" emotion-2-type="none">源海都学愤怒鸟的声音，好像好厉害…</sentence>
<sentence id="2" emotion_tag="Y" emotion-1-type="sadness" emotion-2-type="none">还比愤怒鸟射击的动作，我为啥一千啊现在…</sentence>
<sentence id="3" emotion_tag="Y" emotion-1-type="sadness" emotion-2-type="anger">海赫还悄悄话了刚才，怎么不是我四千二的时候啊哈哈，悲愤！</sentence>
</weibo>
