如何使用嵌套字典和列表遍歷json的所有鍵？

Question

我需要修改以下json文件test.json：

{
  "install": {
    "site": {
      "acls": {
        "dns": {
          "authorized_ports": ["53:tcp", "53:udp"]
        }
      },
      "network": {
        "clusters": {
          "__ip_range_1__": {
            "dhcpstart": "__ip__",
            "dhcpend": "__ip__",
            "adminip": "__ip__"
          },
          "__ip_range_2__": {
            "dhcpstart": "__ip__",
            "dhcpend": "__ip__",
            "adminip": "__ip__"
          }
        }
      }
    }
  }
}

以上是縮寫，原始文件中還有更多條目。 我每個站點都有幾個這樣的文件，因此每個文件的__ip_range_x__和每個IP都不同。 我需要向每個__ip_range_x__元素添加條目。 新條目是存儲在mod.json中的字典詞典（下面的interface_config ）：

{
  "path": "{install}{site}{network}{clusters}{*}",
  "install" :  {
    "site": {
      "network": {
        "clusters": {
          "__iprange": {
            "interface_config": {
              "framesize": "1500",
              "framesize_vm": "1500"
            }
          }
        }
      }
    }
  }
}

我還需要在原始json文件的不同部分中添加其他條目。

現在，我只是想遍歷test.json中的所有元素。 最終，我想為test.json中的每個元素構建一個路徑，並將其與mod.json中的路徑進行匹配以修改test.json。 但是，我無法將所有元素都打印在原始文件中。 我當前的代碼：

import json
import pprint

def traverse(d, path=None):
    if path is None:
        path = []
    for item,val  in d.iteritems():
        if isinstance(item, dict):
            for k,v in item.iteritems():
                print k
                traverse(v)
        elif isinstance(item, list):
            for j in item:
                (traverse(j))
        else:
            print item
        if isinstance(val, dict):
            for k,v in val.iteritems():
                print k
                traverse(v)
        elif isinstance(val, list):
            for j in val:
                (traverse(j))
with open("test.json", "r") as jf:
    data = json.load(jf)
traverse(data)

上面的輸出是：

$ ./now.py
install
site
acls
dns
authorized_ports
Traceback (most recent call last):
  File "./now.py", line 51, in <module>
    traverse(data)
  File "./now.py", line 23, in traverse
    traverse(v)
  File "./now.py", line 23, in traverse
    traverse(v)
  File "./now.py", line 26, in traverse
    (traverse(j))
  File "./now.py", line 9, in traverse
    for item,val  in d.iteritems():
AttributeError: 'unicode' object has no attribute 'iteritems'

我知道我的第一個iteritems調用在錯誤的位置，但我只是無法確定遞歸...任何指針都iteritems贊賞。 順便說一句，我在使用Python 2。

編輯

我要處理的實際json比上面列出的更為復雜。 這是一個編輯的版本：

{
  "install": {
    "site": {
      "acls": {
        "dns": {
          "authorized_ports": ["53:tcp", "53:udp"]
        }
      },
      "network": {
        "clusters": {
          "__ip_range_1__": {
            "dhcpstart": "__ip__",
            "dhcpend": "__ip__",
            "adminip": "__ip__"
          },
          "__ip_range_2__": {
            "dhcpstart": "__ip__",
            "dhcpend": "__ip__",
            "adminip": "__ip__"
          }
        }
      }
    }
  }
  "config": {
    "ippool": [
      {
        "pool_name": "/ippool1",
        "pool_description": "IP Pool1",
        "ranges": [["__ip__", "__ip__"]]
      },
      {
        "pool_name": "/ippool2",
        "pool_description": "IP Pool2",
        "ranges": [["__ip__", "__ip__"]]
      }
    ],
    "storage": [
      {
        "account": "/root",
        "credentials": {
          "account": "admin",
          "service": "storage",
          "user": "admin",
          "password": "pass"
        }
      }
    ]

  }
}

我修改了Paul Panzer的答案，使其包含以下列表：

def traverse(d, path=[]):
    for k, v  in d.iteritems():
        yield path + [k], v
        if isinstance(v, dict):
            for k,v in traverse(v, path + [k]):
                yield k,v
        elif isinstance(v, list):
            for k in v:
                traverse(k, path + [])

但是，以上內容並未在ippool和存儲列表中顯示元素。 一旦遇到字典列表，出於某種原因就不會遍歷它。

Answer 1

這是traverse例程的清理版本。 它只是遍歷嵌套的字典/列表； 為了清楚起見，我刪減了所有其他內容。 希望能幫助到你。

master = {
  "install": {
    "site": {
      "acls": {
        "dns": {
          "authorized_ports": ["53:tcp", "53:udp"]
        }
      },
      "network": {
        "clusters": {
          "__ip_range_1__": {
            "dhcpstart": "__ip__",
            "dhcpend": "__ip__",
            "adminip": "__ip__"
          },
          "__ip_range_2__": {
            "dhcpstart": "__ip__",
            "dhcpend": "__ip__",
            "adminip": "__ip__"
          }
        }
      }
    }
  },
  "config": {
    "ippool": [
      {
        "pool_name": "/ippool1",
        "pool_description": "IP Pool1",
        "ranges": [["__ip__", "__ip__"]]
      },
      {
        "pool_name": "/ippool2",
        "pool_description": "IP Pool2",
        "ranges": [["__ip__", "__ip__"]]
      }
    ],
    "storage": [
      {
        "account": "/root",
        "credentials": {
          "account": "admin",
          "service": "storage",
          "user": "admin",
          "password": "pass"
        }
      }
    ]

  }
}

def traverse(dict_or_list, path=[]):
    if isinstance(dict_or_list, dict):
        iterator = dict_or_list.iteritems()
    else:
        iterator = enumerate(dict_or_list)
    for k, v in iterator:
        yield path + [k], v
        if isinstance(v, (dict, list)):
            for k, v in traverse(v, path + [k]):
                yield k, v

for path, node in traverse(master):
    print path

輸出：

['config']
['config', 'ippool']
['config', 'ippool', 0]
['config', 'ippool', 0, 'ranges']
['config', 'ippool', 0, 'ranges', 0]
['config', 'ippool', 0, 'ranges', 0, 0]
['config', 'ippool', 0, 'ranges', 0, 1]
['config', 'ippool', 0, 'pool_name']
['config', 'ippool', 0, 'pool_description']
['config', 'ippool', 1]
['config', 'ippool', 1, 'ranges']
['config', 'ippool', 1, 'ranges', 0]
['config', 'ippool', 1, 'ranges', 0, 0]
['config', 'ippool', 1, 'ranges', 0, 1]
['config', 'ippool', 1, 'pool_name']
['config', 'ippool', 1, 'pool_description']
['config', 'storage']
['config', 'storage', 0]
['config', 'storage', 0, 'credentials']
['config', 'storage', 0, 'credentials', 'account']
['config', 'storage', 0, 'credentials', 'password']
['config', 'storage', 0, 'credentials', 'user']
['config', 'storage', 0, 'credentials', 'service']
['config', 'storage', 0, 'account']
['install']
['install', 'site']
['install', 'site', 'acls']
['install', 'site', 'acls', 'dns']
['install', 'site', 'acls', 'dns', 'authorized_ports']
['install', 'site', 'acls', 'dns', 'authorized_ports', 0]
['install', 'site', 'acls', 'dns', 'authorized_ports', 1]
['install', 'site', 'network']
['install', 'site', 'network', 'clusters']
['install', 'site', 'network', 'clusters', '__ip_range_2__']
['install', 'site', 'network', 'clusters', '__ip_range_2__', 'dhcpend']
['install', 'site', 'network', 'clusters', '__ip_range_2__', 'adminip']
['install', 'site', 'network', 'clusters', '__ip_range_2__', 'dhcpstart']
['install', 'site', 'network', 'clusters', '__ip_range_1__']
['install', 'site', 'network', 'clusters', '__ip_range_1__', 'dhcpend']
['install', 'site', 'network', 'clusters', '__ip_range_1__', 'adminip']
['install', 'site', 'network', 'clusters', '__ip_range_1__', 'dhcpstart']

Answer 2

似乎您希望使此操作變得不必要的復雜：

with open("test.json", "r") as jf:
    data = json.load(jf)
with open("mod.json", "r") as mf:
    mod = json.load(mf)

ip_ranges = data['install']['site']['network']['clusters']
for rng, val in mod['install']['site']['network']['clusters'].items():
    data[rng]["interface_config"] = val["interface_config"]

Answer 3

來自AChampion的修改后的代碼，用於在具有動態鍵的字典的所有元素下添加條目：

with open(args.masterjson, "r") as masterjf:
    data = json.load(masterjf)
with open(args.modjson, "r") as modjf:
    mod = json.load(modjf)

new_value = mod['install']['site']['network']['clusters']['__iprange']['interface_config']
for rng, val in data['install']['site']['network']['clusters'].items():
    data['install']['site']['network']['clusters'][rng]["interface_config"] = new_value

上面在集群中的每個IP范圍下添加了一個新的字典詞典。 輸出：

master BEFORE update:
{u'dhcpend': u'__ip__', u'adminip': u'__ip__', u'dhcpstart': u'__ip__'}
{u'dhcpend': u'__ip__', u'adminip': u'__ip__', u'dhcpstart': u'__ip__'}
master AFTER update:
{'interface_config': {u'framesize_vm': u'1500', u'framesize': u'1500'}, u'dhcpend': u'__ip__', u'adminip': u'__ip__', u'dhcpstart': u'__ip__'}
{'interface_config': {u'framesize_vm': u'1500', u'framesize': u'1500'}, u'dhcpend': u'__ip__', u'adminip': u'__ip__', u'dhcpstart': u'__ip__'}