统计XML目录中元素中的单词出现次数

import xml.etree.ElementTree as ET
import re

def count_word_occurrences(xml_file, element_name):
    # 解析XML文件
    tree = ET.parse(xml_file)
    root = tree.getroot()

    # 遍历XML元素
    word_count = {}
    for element in root.iter(element_name):
        # 提取文本内容
        text = element.text

        # 分割单词
        words = re.findall(r'\w+', text.lower())

        # 统计单词出现次数
        for word in words:
            if word in word_count:
                word_count[word] += 1
            else:
                word_count[word] = 1

    return word_count

# 示例用法
xml_file = 'example.xml'
element_name = 'content'
result = count_word_occurrences(xml_file, element_name)

# 输出结果
for word, count in result.items():
    print(f'{word}: {count}次')