解析doc文档中XML段落的个数(Python实现)

# -*- coding:utf-8 -*-
'''
anslysis_doc.py

功能：解析doc文档中xml段落的个数
步骤：
'''

import os
import re
from docx import Document


def get_xml_count(path):
    '''
    :param path: doc文档的绝对路径
    :return: 返回doc文档中XML段落的个数
    '''

    # print('doc文件： %s' %path)
    doc = Document(path)
    count = 0
    flag = True
    for paragraph in doc.paragraphs:
        # print(paragraph.text)
        if flag:
            regex = re.match(r'^<[A-Z]+>$', paragraph.text)   # 首次匹配到XML的标签，eg:<ACL>
            if regex:
                value = regex.group(0)   # 获取标签内容
                flag = False
                count += 1
        elif re.match(value, paragraph.text):        # 以首次获取的标签内容对剩下段落做正则匹配
            count += 1
    return count


if __name__ == '__main__':
    path_dir = 'D:\\workspace_py\\FILES'
    sum = 0
    for file in os.listdir(path_dir):
        path = path_dir + '/' + file
        count = get_xml_count(path)
        print('%s文件中，符合条件XML个数： %s' % (path, count))
        sum += count
    print('总的符合条件XML个数：%s' % sum)


# path = 'D:\\workspace_py\\FILES\\Comware ACL NETCONF XML API Action Reference.docx'
# count = get_xml_count(path)
# print(count)