正则表达式嵌套匹配

<133_3><135_3><116_2>The other system worked for about 1 month</116_2> got some good images <137_3>on it then it started doing the same thing as the first one</137_3> so then I quit using either camera now they are just sitting and collecting dust.</135_3></133_3>

{
  "The other system worked for about 1 month got some good images on it then it started doing the same thing as the first one so then I quit using either camera now they are just sitting and collecting dust.": [133, 135],
  "The other system worked for about 1 month": [116],
  "on it then it started doing the same thing as the first one": [137]
}

import re
import xml.etree.ElementTree as ET

def get_nested_tags(string):
  """
  提取嵌套标记和它们之间的内容

  Args:
    string: 包含嵌套标记的字符串

  Returns:
    一个词典，其中键是嵌套标记之间的内容，值是嵌套标记的ID
  """

  # 使用XML解析器将字符串解析成DOM树
  root = ET.fromstring(string)

  # 使用递归算法遍历DOM树，提取嵌套标记和它们之间的内容
  result = {}
  def traverse(node, tag_ids):
    # 如果当前节点是文本节点，则将文本内容作为键，将tag_ids作为值添加到result中
    if node.tag == "text":
      result[node.text] = tag_ids
    # 如果当前节点是元素节点，则递归遍历其子节点
    else:
      for child in node:
        traverse(child, tag_ids + [int(node.tag[1:-2])])

  traverse(root, [])

  # 将result中的键值对转换为字典
  return dict(result)

# 测试一下
string = "<133_3><135_3><116_2>The other system worked for about 1 month</116_2> got some good images <137_3>on it then it started doing the same thing as the first one</137_3> so then I quit using either camera now they are just sitting and collecting dust.</135_3></133_3>"
result = get_nested_tags(string)
print(result)

{
  "The other system worked for about 1 month got some good images on it then it started doing the same thing as the first one so then I quit using either camera now they are just sitting and collecting dust.": [133, 135],
  "The other system worked for about 1 month": [116],
  "on it then it started doing the same thing as the first one": [137]
}