gpt4 book ai didi

Python 操作 json、列表和字典

转载 作者:行者123 更新时间:2023-12-01 04:09:33 25 4
gpt4 key购买 nike

抱歉,篇幅较长,但我尽力做到完整。

我正在尝试获取以下数据 -(仅从更大的 json 文件中进行小样本采样,结构相同)

{
"count": 394,
"status": "ok",
"data": [
{
"md5": "cd042ba78d0810d86755136609793d6d",
"threatscore": 90,
"threatlevel": 0,
"avdetect": 0,
"vxfamily": "",
"domains": [
"dynamicflakesdemo.com",
"www.bountifulbreast.co.uk"
],
"hosts": [
"66.33.214.180",
"64.130.23.5",
],
"environmentId": "1",
},
{
"md5": "4f3a560c8deba19c5efd48e9b6826adb",
"threatscore": 65,
"threatlevel": 0,
"avdetect": 0,
"vxfamily": "",
"domains": [
"px.adhigh.net"
],
"hosts": [
"130.211.155.133",
"65.52.108.163",
"172.225.246.16"
],
"environmentId": "1",
}
]
}

如果“threatscore”超过 70,我想将其添加到此 json 结构中 -前任。 “数据”: [ { "md5": "cd042ba78d0810d86755136609793d6d", “威胁分数”:90,

{
"Event":
{"date":"2015-11-25",
"threat_level_id":"1",
"info":"HybridAnalysis",
"analysis":"0",
"distribution":"0",
"orgc":"SOC",
"Attribute": [
{"type":"ip-dst",
"category":"Network activity",
"to_ids":True,
"distribution":"3",
"value":"66.33.214.180"},
{"type":"ip-dst",
"category":"Network activity",
"to_ids":True,
"distribution":"3",
"value":"64.130.23.5"}
{"type":"domain",
"category":"Network activity",
"to_ids":True,
"distribution":"3",
"value":"dynamicflakesdemo.com"},
{"type":"domain",
"category":"Network activity",
"to_ids":True,
"distribution":"3",
"value":"www.bountifulbreast.co.uk"}
{"type":"md5",
"category":"Payload delivery",
"to_ids":True,
"distribution":"3",
"value":"cd042ba78d0810d86755136609793d6d"}]
}
}

这是我的代码 -

from datetime import datetime
import os
import json
from pprint import pprint

now = datetime.now()

testFile = open("feed.json")
feed = json.load(testFile)


for x in feed['data']:
if x['threatscore'] > 90:
data = {}
data['Event']={}
data['Event']["date"] = now.strftime("%Y-%m-%d")
data['Event']["threat_level_id"] = "1"
data['Event']["info"] = "HybridAnalysis"
data['Event']["analysis"] = 0
data['Event']["distribution"] = 3
data['Event']["orgc"] = "Malware"
data['Event']["Attribute"] = []
if 'hosts' in x:
data['Event']["Attribute"].append({'type': "ip-dst"})
data['Event']["Attribute"][0]["category"] = "Network activity"
data['Event']["Attribute"][0]["to-ids"] = True
data['Event']["Attribute"][0]["distribution"] = "3"
data["Event"]["Attribute"][0]["value"] =x['hosts']
if 'md5' in x:
data['Event']["Attribute"].append({'type': "md5"})
data['Event']["Attribute"][1]["category"] = "Payload delivery"
data['Event']["Attribute"][1]["to-ids"] = True
data['Event']["Attribute"][1]["distribution"] = "3"
data['Event']["Attribute"][1]['value'] = x['md5']
if 'domains' in x:
data['Event']["Attribute"].append({'type': "domain"})
data['Event']["Attribute"][2]["category"] = "Network activity"
data['Event']["Attribute"][2]["to-ids"] = True
data['Event']["Attribute"][2]["distribution"] = "3"
data['Event']["Attribute"][2]["value"] = x['domains']
attributes = data["Event"]["Attribute"]
data["Event"]["Attribute"] = []
for attribute in attributes:
for value in attribute["value"]:
if value == " ":
pass
else:
new_attr = attribute.copy()
new_attr["value"] = value
data["Event"]["Attribute"].append(new_attr)
pprint(data)

with open('output.txt', 'w') as outfile:
json.dump(data, outfile)

现在它似乎被清理了一点,但数据['md5']正在每个字母上分割,我认为这就像L3viathan之前所说的那样,我不断覆盖字典中的第一个元素......但我不知道如何让它继续追加???

{'Event': {'Attribute': [{'category': 'Network activity',
'distribution': '3',
'to-ids': True,
'type': 'ip-dst',
'value': u'216.115.96.174'},
{'category': 'Network activity',
'distribution': '3',
'to-ids': True,
'type': 'ip-dst',
'value': u'64.4.54.167'},
{'category': 'Network activity',
'distribution': '3',
'to-ids': True,
'type': 'ip-dst',
'value': u'63.250.200.37'},
{'category': 'Payload delivery',
'distribution': '3',
'to-ids': True,
'type': 'md5',
'value': u'7'},
{'category': 'Payload delivery',
'distribution': '3',
'to-ids': True,
'type': 'md5',
'value': u'1'},

最后仍然出现以下错误:回溯(最近一次调用最后一次): 文件“hybridanalysis.py”,第 34 行,位于 data['Event']["Attribute"][1]["category"] = "有效负载传送"IndexError:列表索引超出范围

最终目标是对其进行设置,以便我可以将事件发布到 MISP 中,但它们必须一次发布一个。

最佳答案

我认为这应该可以解决您的问题。我一次性添加了属性字典,并将数据移动到列表中(这更合适),但您可能想要删除包装事件的多余列表。

from datetime import datetime
import os
import json
from pprint import pprint

now = datetime.now()

testFile = open("feed.json")
feed = json.load(testFile)

data_list = []

for x in feed['data']:
if x['threatscore'] > 90:
data = {}
data['Event']={}
data['Event']["date"] = now.strftime("%Y-%m-%d")
data['Event']["threat_level_id"] = "1"
data['Event']["info"] = "HybridAnalysis"
data['Event']["analysis"] = 0
data['Event']["distribution"] = 3
data['Event']["orgc"] = "Malware"
data['Event']["Attribute"] = []
if 'hosts' in x:
data['Event']["Attribute"].append({
'type': 'ip-dst',
'category': 'Network activity',
'to-ids': True,
'distribution': '3',
'value': x['hosts']})
if 'md5' in x:
data['Event']["Attribute"].append({
'type': 'md5',
'category': 'Payload delivery',
'to-ids': True,
'distribution': '3',
'value': x['md5']})
if 'domains' in x:
data['Event']["Attribute"].append({
'type': 'domain',
'category': 'Network activity',
'to-ids': True,
'distribution': '3',
'value': x['domains']})
attributes = data["Event"]["Attribute"]
data["Event"]["Attribute"] = []
for attribute in attributes:
for value in attribute["value"]:
if value == " ":
pass
else:
new_attr = attribute.copy()
new_attr["value"] = value
data["Event"]["Attribute"].append(new_attr)
data_list.append(data)

with open('output.txt', 'w') as outfile:
json.dump(data_list, outfile)

关于Python 操作 json、列表和字典,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/35140637/

25 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com