Python解析MDX词典数据并保存到Excel

https://gitcode.net/as604049322/blog_data/-/tree/master/mdx

pip install readmdict

pip install python-lzo

from readmdict import MDX

mdx_file = "help.mdx"
mdx = MDX(mdx_file, encoding='utf-8')
items = mdx.items()
for key, value in items:
    word = key.decode().strip()
    print(word, value.decode())
    break

a <link type="text/css" rel="stylesheet" href="jsmind.css"><script type="text/javascript" src="jsmind.js"></script><p id="jsmind_describe"></p><p id="jsmind_container"></p><script>jsMind.show({},{"meta":{"name":"etymology","version":"0.1"},"format":"node_array","data":[{"id":"a","isroot":true,"topic":"a","describe":"英[ə; eɪ]美[ə; e]art. 一"}]});document.getElementById('jsmind_container').style.height=document.querySelector('jmnodes').style.height;</script>

import re

json.loads(re.findall('"data":(\[.+\])}\);', value.decode())[0])

[{'id': 'a',
  'isroot': True,
  'topic': 'a',
  'describe': '英[ə; eɪ]美[ə; e]art. 一'}]

from readmdict import MDX
import re


mdx_file = "help.mdx"
mdx = MDX(mdx_file, encoding='utf-8')
items = mdx.items()
for key, value in items:
    word = key.decode().strip()
    topic = json.loads(re.findall('"data":(\[.+\])}\);', value.decode())[0])
    if word == "abalienate":
        print(word, topic)
        break

abalienate [{'id': 'abalienate', 'isroot': True, 'topic': 'abalienate', 'describe': "英[æb'eiljəneit]美[æb'eiljəneit]【法】 让渡, 转移, 让出"}, {'id': 'ab-', 'parentid': 'abalienate', 'direction': 'left', 'topic': 'ab-', 'describe': '表示从，来自（from）；从...离开，离开（away from, sway, off）；不，非，表否定（not, opposite）。在字母v 前缩略成a-，在字母c, t 前扩展为abs-。来自拉丁介词ab。'}, {'id': 'alienate', 'parentid': 'abalienate', 'direction': 'left', 'topic': 'alienate', 'describe': "英['eɪlɪəneɪt]vt. 使疏远, 离间, 转让\n【第三人称单数：alienates；现在分词：alienating；过去式：alienated】"}, {'id': 'alien', 'parentid': 'alienate', 'direction': 'left', 'topic': 'alien', 'describe': "英['eɪlɪən]美[ˈeliən,ˈeljən]n. 外国人, 外侨\na. 外国的, 相异的\n【复数：aliens；现在分词：aliening；过去分词：aliened】"}, {'id': '-ate', 'parentid': 'alienate', 'direction': 'left', 'topic': '-ate', 'describe': [['表动词，“做，造成”。']]}, {'id': 'ali-', 'parentid': 'alien', 'direction': 'left', 'topic': 'ali-', 'describe': [['= other, to change, 表示“其他的，改变状态”，来源于拉丁语 alius "another, other, different."']]}, {'id': '-en', 'parentid': 'alien', 'direction': 'left', 'topic': '-en', 'describe': [['表名词，“人或物”，有时构成小词或昵称。']]}]

from readmdict import MDX
import re
import json
import csv


def get_describe(describe):
    if isinstance(describe, (list, tuple)):
        return ';'.join(get_describe(i) for i in describe)
    else:
        return describe


def deal_node(node, result=[], num=-1):
    chars = "■□◆▲●◇△○★☆"
    for k, (d, cs) in node.items():
        if num >= 0:
            d = d.replace('\n', '')
            result.append(f"{'    '*num}{chars[num]} {k}: {d}")
        if cs:
            deal_node(cs, result, num+1)


def get_row(topic):
    id2children = {}
    root = {}
    for d in topic:
        node = id2children.get(d.get("parentid"), root)
        tmp = {}
        node[d['id']] = (get_describe(d['describe']), tmp)
        id2children[d['id']] = tmp
    name, (describe, _) = list(root.items())[0]
    txts = []
    deal_node(root, txts)
    other = "\n".join(txts)
    return name, describe, other


mdx_file = "help.mdx"
mdx = MDX(mdx_file, encoding='utf-8')
items = mdx.items()
data = []
for key, value in items:
    word = key.decode().strip()
    topic = json.loads(re.findall('"data":(\[.+\])}\);', value.decode())[0])
    name, describe, other = get_row(topic)
    data.append((name, describe, other))

with open(mdx_file.replace('.mdx', '-UTF8 .csv'), 'w', newline='', encoding='u8') as f:
    cw = csv.writer(f, delimiter=',')
    cw.writerow(["单词", "释义", "扩展"])
    cw.writerows(data)