Python 提取JSON标记并构建新的JSON

与此类似，我想提取一些JSON片段，并根据我需要的信息构建一个新的JSON。 我尝试使用以下代码：

wanted_milestones_ids =  [ch_epic['milestone_id'],ch_epic['stats']['num_points'] for ch_epic in ch_epics if ch_epic['milestone_id'] is not None and set(CLUBHOUSE_PROJECT_IDS).intersection(ch_epic['project_ids']) and ch_epic['id'] == 16919]

过滤器工作正常，实际上我可以得到值。问题是，我获得了所有值或一个值，我需要其中的一些值，这就是为什么我尝试使用“Chu epic['milestone\u id']，Chu epic['stats']['num_points']”但出现了一个错误

我怎样才能完成这项任务？下面是原始的JSON代码，我想提取：Id、milestone_Id和num_points

{
    "archived": false,
    "started": false,
    "entity_type": "epic",
    "labels": [
      {
        "entity_type": "label",
        "id": 1305552,
        "created_at": "2018-10-01T16:37:13Z",
        "updated_at": "2018-11-13T14:25:23Z",
        "name": "random name",
        "color": "#e885d1",
        "external_id": null,
        "archived": false
      }
    ],
    "external_tickets": [],
    "mention_ids": [],
    "member_mention_ids": [],
    "project_ids": [
      2022
    ],
    "completed_at_override": null,
    "started_at": null,
    "completed_at": null,
    "name": "Randome Name",
    "completed": false,
    "state": "to do",
    "milestone_id": 195343762,
    "requested_by_id": "Goofy",
    "epic_state_id": 50230002327020,
    "started_at_override": null,
    "updated_at": "2019-08-08T21:19:00Z",
    "group_mention_ids": [],
    "support_tickets": [],
    "follower_ids": [
      "Donald"
    ],
    "owner_ids": [],
    "external_id": null,
    "id": 16965,
    "position": 961,
    "deadline": null,
    "stats": {
      "num_points_done": 1,
      "average_cycle_time": 32223231706,
      "num_stories_unstarted": 2,
      "last_story_update": "2019-10-02T12:24:08Z",
      "num_points_started": 1,
      "num_points_unstarted": 3,
      "num_stories_started": 1,
      "num_stories_unestimated": 2,
      "average_lead_time": 3305323270,
      "num_points": 5,
      "num_stories_done": 2
    },
    "created_at": "2019-03-28T16:39:50Z"
  }

---

我不知道你为什么要把这个复杂化

也许我错过了什么

下面是一个简单的摘录：

import json

data = r'{ "archived": false, "started": false, "entity_type": "epic", "labels": [ { "entity_type": "label", "id": 1305552, "created_at": "2018-10-01T16:37:13Z", "updated_at": "2018-11-13T14:25:23Z", "name": "random name", "color": "#e885d1", "external_id": null, "archived": false } ], "external_tickets": [], "mention_ids": [], "member_mention_ids": [], "project_ids": [ 2022 ], "completed_at_override": null, "started_at": null, "completed_at": null, "name": "Randome Name", "completed": false, "state": "to do", "milestone_id": 195343762, "requested_by_id": "Goofy", "epic_state_id": 50230002327020, "started_at_override": null, "updated_at": "2019-08-08T21:19:00Z", "group_mention_ids": [], "support_tickets": [], "follower_ids": [ "Donald" ], "owner_ids": [], "external_id": null, "id": 16965, "position": 961, "deadline": null, "stats": { "num_points_done": 1, "average_cycle_time": 32223231706, "num_stories_unstarted": 2, "last_story_update": "2019-10-02T12:24:08Z", "num_points_started": 1, "num_points_unstarted": 3, "num_stories_started": 1, "num_stories_unestimated": 2, "average_lead_time": 3305323270, "num_points": 5, "num_stories_done": 2 }, "created_at": "2019-03-28T16:39:50Z" }'

data = data.replace('\n', '')
json_data = json.loads(data)
id = json_data['labels'][0]['id']
milestone_id = json_data['milestone_id']
num_points = json_data['stats']['num_points']

print("id:\t\t{}".format(id))
print("milestone_id:\t{}".format(milestone_id))
print("num_points:\t{}".format(num_points))

output = {'id':id, 'milestone_id':milestone_id, 'num_points':num_points}
final_output = json.dumps(output)

print("\njson:\t\t" + final_output)

输出

id:             1305552
milestone_id:   195343762
num_points:     5

json:           {"num_points": 5, "id": 1305552, "milestone_id": 195343762}

---

您可以尝试使用JSON包

如果将JSON保存在一个名为example.JSON的文件中，该文件与python脚本位于同一目录中。您可以使用以下代码来获取所需的字段

import json

with open("example.json", "r") as read_file:
    data = json.load(read_file)

output_file = json.dumps({'id':data['id'], 'milestone_id':data['milestone_id'], 'num_points':data['stats']['num_points']})

---

使其适应多个值：

import json

data = r'[{ "archived": false, "started": false, "entity_type": "epic", "labels": [ { "entity_type": "label", "id": 1305552, "created_at": "2018-10-01T16:37:13Z", "updated_at": "2018-11-13T14:25:23Z", "name": "random name", "color": "#e885d1", "external_id": null, "archived": false } ], "external_tickets": [], "mention_ids": [], "member_mention_ids": [], "project_ids": [ 2022 ], "completed_at_override": null, "started_at": null, "completed_at": null, "name": "Randome Name", "completed": false, "state": "to do", "milestone_id": 195343762, "requested_by_id": "Goofy", "epic_state_id": 50230002327020, "started_at_override": null, "updated_at": "2019-08-08T21:19:00Z", "group_mention_ids": [], "support_tickets": [], "follower_ids": [ "Donald" ], "owner_ids": [], "external_id": null, "id": 16965, "position": 961, "deadline": null, "stats": { "num_points_done": 1, "average_cycle_time": 32223231706, "num_stories_unstarted": 2, "last_story_update": "2019-10-02T12:24:08Z", "num_points_started": 1, "num_points_unstarted": 3, "num_stories_started": 1, "num_stories_unestimated": 2, "average_lead_time": 3305323270, "num_points": 5, "num_stories_done": 2 }, "created_at": "2019-03-28T16:39:50Z" },{ "archived": false, "started": false, "entity_type": "epic", "labels": [ { "entity_type": "label", "id": 1305552, "created_at": "2018-10-01T16:37:13Z", "updated_at": "2018-11-13T14:25:23Z", "name": "random name", "color": "#e885d1", "external_id": null, "archived": false } ], "external_tickets": [], "mention_ids": [], "member_mention_ids": [], "project_ids": [ 2022 ], "completed_at_override": null, "started_at": null, "completed_at": null, "name": "Randome Name", "completed": false, "state": "to do", "milestone_id": 195343762, "requested_by_id": "Goofy", "epic_state_id": 50230002327020, "started_at_override": null, "updated_at": "2019-08-08T21:19:00Z", "group_mention_ids": [], "support_tickets": [], "follower_ids": [ "Donald" ], "owner_ids": [], "external_id": null, "id": 16965, "position": 961, "deadline": null, "stats": { "num_points_done": 1, "average_cycle_time": 32223231706, "num_stories_unstarted": 2, "last_story_update": "2019-10-02T12:24:08Z", "num_points_started": 1, "num_points_unstarted": 3, "num_stories_started": 1, "num_stories_unestimated": 2, "average_lead_time": 3305323270, "num_points": 5, "num_stories_done": 2 }, "created_at": "2019-03-28T16:39:50Z" }]'

data = data.replace('\n', '')
json_data = json.loads(data)
output = []
for milestone in json_data:
    id = milestone['labels'][0]['id']
    milestone_id = milestone['milestone_id']
    num_points = milestone['stats']['num_points']

# print("id:\t\t{}".format(id))
# print("milestone_id:\t{}".format(milestone_id))
# print("num_points:\t{}".format(num_points))

    output.append({'id':id, 'milestone_id':milestone_id, 'num_points':num_points})
final_output = json.dumps(output)
print("\njson:\t\t" + final_output)

输出：

json: [{"id": 1305552, "milestone_id": 195343762, "num_points": 5}, {"id": 1305552, "milestone_id": 195343762, "num_points": 5}]

---

谢谢它起作用了，我把它适应了多种价值观，而且效果很好。谢谢。非常高兴它对您有用@DanielLuevanoAlonso！尝试运行您的示例，我得到了：output_file=json.dumps（{'id'：data['id']，'milestone_id'：data['milestone_id']，'num_points'：data['stats']['num_points']}）TypeError:列表索引必须是整数或片，而不是str