python解析xml

import xml.dom.minidom
from pandas import Series
# 存储句子
data_list = []
# 存储句子标注极性
label_list = []

if __name__ == ‘__main__‘:
    # 获取xml文件
    document_tree = xml.dom.minidom.parse(‘../data/SMP2019_ECISA_Train.xml‘)
    # 获取文件中的元素
    collection = document_tree.documentElement
    # 打印文件
    # print(collection.toxml())

    # 获取xml文件中子标签内容
    Doc_node = collection.getElementsByTagName("Doc")
    for i in range(len(Doc_node)):
        sentence_node = Doc_node[i].getElementsByTagName("Sentence")
        for j in range(len(sentence_node)):
            # 剔除没有标注的数据
            if sentence_node[j].getAttribute("label") == "0"                     or sentence_node[j].getAttribute("label") == "1"                     or sentence_node[j].getAttribute("label") == "2":
                # 获取句子数据
                sentence = sentence_node[j].firstChild.data
                # 获取句子标注的极性
                label = sentence_node[j].getAttribute("label")
                data_list.append(sentence)
                label_list.append(label)
    # 打印数据
    with open("trainSMP.txt", "w") as f:
        for l in range(len(data_list)):
            f.write("__label__"+label_list[l]+" "+data_list[l]+"\n")
        # print(data_list[l]+"\t"+label_list[l])
        # print(‘\n‘)