Question

这是我的数据

data = [
    {
        "title": "Main Topic 1",
        "num": "Type 1",
        "text": "Some Text",
        "sub": [
            {
                "title": "Sub Topic 1",
                "num": "1",
                "text": "Some more Text",
                "sub": [
                    {
                        "num": "(a)",
                        "text": "This is the actual text for the topic 1(a)",
                    },
                    {
                        "num": "(b)",
                        "text": "This is the actual text for the topic 1(b)",
                    },
                ],
            },
            {
                "title": "Sub Topic 2",
                "num": "2",
                "text": "This is the actual text for the topic 2",
            },
        ],
    },
    {
        "title": "Main Topic 2",
        "num": "Type 2",
        "text": "Some Text",
        "sub": [
            {
                "title": "Sub Topic 3",
                "num": "3",
                "text": "Some more Text",
                "sub": [
                    {
                        "num": "(a)",
                        "text": "This is the actual text for the topic 3(a)",
                    },
                    {
                        "num": "(b)",
                        "text": "This is the actual text for the topic 3(b)",
                    },
                ],
            },
            {
                "title": "Sub Topic 4",
                "num": "4",
                "text": "This is the actual text for the topic 4",
            },
        ],
    },
]

现在，我想要这样的输出：

{'title': 'Main Topic 1~Sub Topic 1~NA', 'num': 'Type 1~1~(a)', 'text': 'This is the actual text for the topic 1(a)'}
{'title': 'Main Topic 1~Sub Topic 1~NA', 'num': 'Type 1~1~(b)', 'text': 'This is the actual text for the topic 1(b)'}
{'title': 'Main Topic 1~Sub Topic 2', 'num': 'Type 1~2', 'text': 'This is the actual text for the topic 2'}
{'title': 'Main Topic 2~Sub Topic 3~NA', 'num': 'Type 2~3~(a)', 'text': 'This is the actual text for the topic 3(a)'}
{'title': 'Main Topic 2~Sub Topic 3~NA', 'num': 'Type 2~3~(b)', 'text': 'This is the actual text for the topic 3(b)'}
{'title': 'Main Topic 2~Sub Topic 4', 'num': 'Type 2~4', 'text': 'This is the actual text for the topic 4'}

这是我要实现的代码：

def get_each_provision(title, num, text):
    provision = {}
    provision['title'] = title
    provision['num'] = num
    provision['text'] = text
    return provision


def get_consolidated_provisions(data):
    provisions = []
    for level1 in data:

        title_level1 = level1['title']
        num_level1 = level1['num']
        text_level1 = level1['text']

        if 'sub' in level1:

            level2_subs = level1['sub']
            for level2 in level2_subs:

                title_level2 = '%s~%s'%(title_level1, level2['title'])
                num_level2 = '%s~%s'%(num_level1, level2['num'])
                text_level2 = level2['text']

                if 'sub' in level2:

                    level3_subs = level2['sub']
                    for level3 in level3_subs:

                        title = '%s~%s'%(title_level2, level3.get('title', 'NA'))
                        num = '%s~%s'%(num_level2, level3['num'])
                        text = level3['text']
                        provisions.append(get_each_provision(title, num, text))

                else:
                    provisions.append(get_each_provision(title_level2, num_level2, text_level2))

        else:
            provisions.append(get_each_provision(title_level1, num_level1, text_level1))

    return provisions

print('----------------------------------------------')
provisions = get_consolidated_provisions(data)
for each_provision in provisions:
    print(each_provision)

它按预期工作正常。我要实现的目标是-基本上从每个词典和子词典中获得最低级别的“文本”（在键“ sub”下）我的问题有两个方面：（1）是否有更好的方法来实现这一目标？（2）如果存在另一级字典列表，我的代码将中断。我可以再申请一个级别，但希望不要。

如果您想知道，上面的变量“ data”是通过提取pdf文件获得的json格式。如变量“ data”所示，数据提取成功。想法是确定每个小节及其前导序列“ num”和“ title”。

要注意的要点：（1）最低级别没有键“ title”，并且（2）最低级别字典没有键“ sub”。两者均如变量数据所示。

Answer 1

您应该使用递归来完成“拼合”此词典列表。

def flatten(items):
    new_list = []
    for i in items:
        if "sub" in i:
            new_dict = {}
            for k, v in i.items():
                if not k == "sub":
                    new_dict[k] = v
            new_list.append(new_dict)
            new_list += flatten(i["sub"])
        else:
            new_list.append(i)
    return new_list

# I've tested this with your data
flatten(data)

遍历字典的多层

1 个答案: