整理一系列尝试...除语句外？

Question

我已经编写了一个脚本，用于将Kustomer API中的数据传递到我们的数据库中，尽管它工作得很好，但有点混乱，但我想知道是否有一个更优雅的解决方案。我正在将结果行定义为字典，然后推送至MySQL，但是当其中的某些值并非始终在JSON中可用时，就会出现混乱的情况。

对于每个可能不存在或可能不存在的数据点，这导致了try / except语句。

是否有更好的方法？下面的代码。

    try:
        record_data = {
            'id': record['id'],
            'created_at': str(datetime.strptime(record['attributes']['createdAt'], '%Y-%m-%dT%H:%M:%S.%fZ'))[:-7],
            'last_activity_at': str(datetime.strptime(record['attributes']['lastActivityAt'], '%Y-%m-%dT%H:%M:%S.%fZ'))[:-7],
            'first_marked_done': None,
            'last_marked_done': None,
            'assigned_team': record['attributes']['assignedTeams'][0] if record['attributes']['assignedTeams'] != [] else None,
            'conversation_type': None,
            'conversation_category': None,
            'conversation_subcategory': None,
            'message_count': record['attributes']['messageCount'],
            'note_count': record['attributes']['noteCount'],
            'satisfaction': record['attributes']['satisfaction'],
            'status': None,
            'email': 1 if len(list(filter(lambda x: x == 'email', record['attributes']['channels']))) > 0 else 0,
            'chat': 1 if len(list(filter(lambda x: x == 'chat', record['attributes']['channels']))) > 0 else 0,
            'priority': record['attributes']['priority'],
            'direction': 'outbound' if record['attributes']['direction'] == 'out' else 'in',
            'nlp_score': None,
            'nlp_sentiment': None,
            'waiting_for': None,
            'sla_breach': None,
            'sla_status': None,
            'breached_sla': None,
            'breached_at': None
        }
        try:
            record_data['status'] = record['attributes']['status']
        except KeyError:
            pass
        try:
            record_data['conversation_type'] = record['attributes']['custom']['typeStr']
            record_data['conversation_category'] = str(record['attributes']['custom']['categoryTree']).split('.')[0]
            record_data['conversation_subcategory'] = str(record['attributes']['custom']['categoryTree']).split('.')[1] if len(str(record['attributes']['custom']['categoryTree']).split('.')) > 1 else None
        except KeyError:
            pass
        try:
            record_data['waiting_for'] = record['attributes']['custom']['typeStr']
        except KeyError:
            pass
        try:
            record_data['first_marked_done'] = str(datetime.strptime(record['attributes']['firstDone']['createdAt'], '%Y-%m-%dT%H:%M:%S.%fZ'))[:-7]
            record_data['last_marked_done'] = str(datetime.strptime(record['attributes']['lastDone']['createdAt'], '%Y-%m-%dT%H:%M:%S.%fZ'))[:-7]

        except KeyError:
            pass
        try:
            record_data['sla_breach'] = 0 if record['attributes']['sla']['breached'] is False else 1
            record_data['sla_status'] = record['attributes']['sla']['status']
            if record_data['sla_breach'] == 1:
                try:
                    record_data['breached_sla'] = record['attributes']['sla']['breach']['metric']
                    record_data['breached_at'] = record['attributes']['sla']['breach']['at']
                except KeyError:
                    for m in record['attributes']['sla']['metrics']:
                        try:
                            if record['attributes']['sla']['metrics'][m]['breachAt'] == record['attributes']['sla']['summary']['firstBreachAt']:
                                record_data['breached_sla'] = m
                                record_data['breached_at'] = str(datetime.strptime(record['attributes']['sla']['summary']['firstBreachAt'], '%Y-%m-%dT%H:%M:%S.%fZ'))[:-7]
                        except KeyError:
                            pass
        except KeyError:
            record_data['sla_breach'] = 0
        print(record_data)
        self.db.insert_update(KustomerConversations(**record_data))

    except KeyError:
        pass

Answer 1

首先，您应该尝试在可能的情况下使用指定默认值的dict.get。接下来，您可以考虑使用contextmanager使您的代码更加清晰。考虑一下：

try:
    record_data['status'] = record['attributes']['status']
except KeyError:
    pass
try:
    record_data['conversation_type'] = record['attributes']['custom']['typeStr']
except KeyError:
    pass
try:
    record_data['waiting_for'] = record['attributes']['custom']['typeStr']
except KeyError:
    pass
try:
    record_data['first_marked_done'] = record['attributes']['firstDone']['createdAt']
except KeyError:
    pass

现在已重写，可以确保一致错误处理，而无需重复逻辑：

from contextlib import contextmanager

@contextmanager
def error_handling():
    try:
        yield
    except KeyError:
        pass

with error_handling():
    record_data['status'] = record['attributes']['status']
with error_handling():
    record_data['conversation_type'] = record['attributes']['custom']['typeStr']
with error_handling():
    record_data['waiting_for'] = record['attributes']['custom']['typeStr']
with error_handling():
    record_data['first_marked_done'] = record['attributes']['firstDone']['createdAt']

您可以为希望应用的各种规则定义任意数量的函数，例如error_handling。

Answer 2

您可以使用函数，该函数为您提供嵌套字典中的元素，并且如果不存在则不引发异常。

像这个快速草稿一样：

def get_nested_dict_value(src_dict, *nested_keys, **kwargs):
    """
    Get value of some nested dict by series of keys with default value.
    Example:
    instead of: 
        x = data['a']['b']['c']['d']
    use
        x = get_nested_dict_value(data, 'a', 'b', 'c', 'd')
    or, if you need some non-None default value, add default=xxx kwarg:
        x = get_nested_dict_value(data, 'a', 'b', 'c', 'd', default=0)
    """
    default = kwargs.get("default", None)
    pointer = src_dict
    i = 0
    for key in nested_keys:
        i += 1
        if key in pointer:
            pointer = pointer[key]
            if i == len(nested_keys):
                return pointer
        else:
            return default

所以，而不是：

try:    
    record_data['conversation_type'] = record['attributes']['custom']['typeStr']
except Exception:
    pass

您只需输入：

record_data['conversation_type'] = get_nested_dict_value(record, 'attributes', 'custom', 'typeStr')

Answer 3

输入和输出端的不同命名约定使我们难以超越明确分配的明确性。保留版本的精确语义（例如，即使没有conversation_category，它也不会分配typeStr，即使{{1 }}可用）排除某些选择（例如使数据结构在每次访问 时通过categoryTree / try进行循环）；您可以通过对输入数据进行更多假设来做得更好。

尽管如此，除了except already mentioned之外，您还可以使用内置函数（dict.get，any和or）和引入一个辅助函数和一些临时变量以使代码更具可读性：

dict

虽然您可能有一个针对它的策略，但在这种情况下，我建议将其余的# this gives one digit of the hour for me...? def ptime(s): return str(datetime.strptime(s,'%Y-%m-%dT%H:%M:%S.%fZ'))[:-7] try: attr=record['attributes'] cust=attr.get('custom',{}) # defer KeyErrors into the below record_data = dict( id = record['id'], created_at = ptime(attr['createdAt']), last_activity_at = ptime(attr['lastActivityAt']), first_marked_done = None, last_marked_done = None, assigned_team = attr['assignedTeams'][0] or None, conversation_type = None, conversation_category = None, conversation_subcategory = None, message_count = attr['messageCount'], note_count = attr['noteCount'], satisfaction = attr['satisfaction'], status = attr.get('status'), email = int(any(x == 'email' for x in attr['channels'])), chat = int(any(x == 'chat' for x in attr['channels'])), priority = attr['priority'], direction = 'outbound' if attr['direction'] == 'out' else 'in', nlp_score = None, nlp_sentiment = None, waiting_for = cust.get('typeStr'), sla_breach = 0, sla_status = None, breached_sla = None, breached_at = None ) try: record_data['conversation_type'] = cust['typeStr'] cat=str(cust['categoryTree']).split('.') record_data['conversation_category'] = cat[0] record_data['conversation_subcategory'] = cat[1] if len(cat) > 1 else None except KeyError: pass try: record_data['first_marked_done'] = ptime(attr['firstDone']['createdAt']) record_data['last_marked_done'] = ptime(attr['lastDone']['createdAt']) except KeyError: pass try: sla=attr['sla'] record_data['sla_breach'] = 0 if sla['breached'] is False else 1 record_data['sla_status'] = sla['status'] if record_data['sla_breach'] == 1: try: record_data['breached_sla'] = sla['breach']['metric'] record_data['breached_at'] = sla['breach']['at'] except KeyError: for m,v in sla['metrics'].items(): try: v=v['breachAt'] if v == sla['summary']['firstBreachAt']: record_data['breached_sla'] = m record_data['breached_at'] = ptime(v) except KeyError: pass except KeyError: pass print(record_data) self.db.insert_update(KustomerConversations(**record_data)) except KeyError: pass 子句写在一行上：这有助于对暂定代码进行可视化包围。