python读取xml文件

小咪咪 2023-07-10 14:27 3阅读 0赞

*  针对下面xml样式，提取其中内容

<emotionml category-set="http://www.w3.org/TR/emotion-voc/xml#big6" expressed-through="text" xmlns="http://www.w3.org/2009/10/emotionml">
    	<emotion id="0">
    		<category name="happiness" value="3"/>
    		<clause cause="N" id="1" keywords="N">
    			<text>Her love of dirt gave way to an inclination for finery</text>
    		</clause>
    		<clause cause="N" id="2" keywords="N">
    			<text> and she grew clean as she grew smart</text>
    		</clause>
    		<clause cause="Y" id="3" keywords="Y">
    			<text> she had now the pleasure of sometimes hearing her father and mother remark on her personal improvement</text>
    			<cause begin="39" id="1" lenth="64">hearing her father and mother remark on her personal improvement</cause>
    			<keywords keywords-begin="17" keywords-lenth="8">pleasure</keywords>
    		</clause>
    		<clause cause="N" id="4" keywords="N">
    			<text>"Catherine grows quite a good-looking girl -- she is almost pretty today</text>
    		</clause>
    		<clause cause="N" id="5" keywords="N">
    			<text>" were words which caught her ears now and then</text>
    		</clause>
    		<clause cause="N" id="6" keywords="N">
    			<text> and how welcome were the sounds</text>
    		</clause>
    		<clause cause="N" id="7" keywords="N">
    			<text> To look almost pretty is an acquisition of higher delight to a girl who has been looking plain the first fifteen years of her life than a beauty from her cradle can ever receive.</text>
    		</clause>
    	</emotion>
    	<emotion id="1">
    		<category name="happiness" value="3"/>
    		<clause cause="N" id="1" keywords="N">
    			<text>Her love of dirt gave way to an inclination for finery</text>
    		</clause>
    		<clause cause="N" id="2" keywords="N">
    			<text> and she grew clean as she grew smart</text>
    		</clause>
    		<clause cause="N" id="3" keywords="N">
    			<text> she had now the pleasure of sometimes hearing her father and mother remark on her personal improvement</text>
    		</clause>
    		<clause cause="N" id="4" keywords="N">
    			<text>"Catherine grows quite a good-looking girl -- she is almost pretty today</text>
    		</clause>
    		<clause cause="N" id="5" keywords="N">
    			<text>" were words which caught her ears now and then</text>
    		</clause>
    		<clause cause="N" id="6" keywords="N">
    			<text> and how welcome were the sounds</text>
    		</clause>
    		<clause cause="Y" id="7" keywords="Y">
    			<text> To look almost pretty is an acquisition of higher delight to a girl who has been looking plain the first fifteen years of her life than a beauty from her cradle can ever receive.</text>
    			<cause begin="1" id="1" lenth="21">To look almost pretty</cause>
    			<keywords keywords-begin="51" keywords-lenth="7">delight</keywords>
    		</clause>
    	</emotion>
    </emotionml>

*  代码如下：

import os
    import xml.etree.ElementTree as ET
    
    p_path = os.path.abspath(os.path.dirname(os.getcwd()))
    path = os.path.join(p_path,'threedata/emotion_cause_english_test.xml')
    
    tree = ET.parse(path)
    root = tree.getroot()
    
    # print('root-tag:',root.tag,',root-attrib:',root.attrib,',root-text:',root.text)
    
    for child in root:
         print('编号：',child.attrib['id'])
         for index, sub in enumerate(child):
             if index == 0:
                 print('hh：', sub.attrib['name'])
                 print('hhv：', sub.attrib['value'])
             else:
                 print('sub.attrib：',sub.attrib)
                 for index, ssub in enumerate(sub):
                     # print('ssub.attrib:', ssub.attrib)
                     if not ssub.attrib:
                         print('content：', ssub.text)
                     elif 'begin' in ssub.attrib:
                         print('att：', ssub.attrib)
                         print('causecontent：', ssub.text)
                     else:
                         print('wprdatt：', ssub.attrib)
                         print('wordtext：', ssub.text)