Python json数组拆分为多个数组

我正在阅读api的内容https://myapi.com/allcolor“）转换为数据帧，使用azure databricks笔记本中下面的pyspark代码。当我以某种方式将json内容读入数据帧时，带有一个“colors”数组的json负载被转换为多个数组

代码：

spark.sql("set spart.databricks.delta.preview.enabled=true")
spark.sql("set spart.databricks.delta.retentionDutationCheck.preview.enabled=false")
import json
import requests
from requests.auth import HTTPDigestAuth
import pandas as pd
user = "username"
password = "password"
myResponse = requests.get('https://myapi.com/allcolor', auth=(user, password))
if(myResponse.ok):
  jData = json.loads(myResponse.content)
  s1 = json.dumps(jData)
  #load data from api
  x = json.loads(s1)
  data = pd.read_json(json.dumps(x))
  #create dataframe
  spark_df = spark.createDataFrame(data)
  spark_df.show()          
  spark.conf.set("fs.azure.account.key.<your-storage-account-name>.blob.core.windows.net","<your-storage-account-access-key>")
  spark_df.write.mode("overwrite").json("wasbs://<container>@<storage-account-name>.blob.core.windows.net/<directory>/")
else:
  myResponse.raise_for_status()

{
  "colors": [
    {
      "color": "black",
      "category": "hue",
      "type": "primary",
      "code": {
        "rgba": [
          255,
          255,
          255,
          1
        ],
        "hex": "#000"
      }
    },
    {
      "color": "white",
      "category": "value",
      "code": {
        "rgba": [
          0,
          0,
          0,
          1
        ],
        "hex": "#FFF"
      }
    },
    {
      "color": "red",
      "category": "hue",
      "type": "primary",
      "code": {
        "rgba": [
          255,
          0,
          0,
          1
        ],
        "hex": "#FF0"
      }
    },
    {
      "color": "blue",
      "category": "hue",
      "type": "primary",
      "code": {
        "rgba": [
          0,
          0,
          255,
          1
        ],
        "hex": "#00F"
      }
    },
    {
      "color": "yellow",
      "category": "hue",
      "type": "primary",
      "code": {
        "rgba": [
          255,
          255,
          0,
          1
        ],
        "hex": "#FF0"
      }
    },
    {
      "color": "green",
      "category": "hue",
      "type": "secondary",
      "code": {
        "rgba": [
          0,
          255,
          0,
          1
        ],
        "hex": "#0F0"
      }
    }
  ]
}

{
  "colors": 
    {
      "color": "black",
      "category": "hue",
      "type": "primary",
      "code": {
        "rgba": [
          255,
          255,
          255,
          1
        ],
        "hex": "#000"
      }
    }
    }
{
  "colors":     
    {
      "color": "white",
      "category": "value",
      "code": {
        "rgba": [
          0,
          0,
          0,
          1
        ],
        "hex": "#FFF"
      }
    }
    }

结果数据帧：

spark.sql("set spart.databricks.delta.preview.enabled=true")
spark.sql("set spart.databricks.delta.retentionDutationCheck.preview.enabled=false")
import json
import requests
from requests.auth import HTTPDigestAuth
import pandas as pd
user = "username"
password = "password"
myResponse = requests.get('https://myapi.com/allcolor', auth=(user, password))
if(myResponse.ok):
  jData = json.loads(myResponse.content)
  s1 = json.dumps(jData)
  #load data from api
  x = json.loads(s1)
  data = pd.read_json(json.dumps(x))
  #create dataframe
  spark_df = spark.createDataFrame(data)
  spark_df.show()          
  spark.conf.set("fs.azure.account.key.<your-storage-account-name>.blob.core.windows.net","<your-storage-account-access-key>")
  spark_df.write.mode("overwrite").json("wasbs://<container>@<storage-account-name>.blob.core.windows.net/<directory>/")
else:
  myResponse.raise_for_status()

{
  "colors": [
    {
      "color": "black",
      "category": "hue",
      "type": "primary",
      "code": {
        "rgba": [
          255,
          255,
          255,
          1
        ],
        "hex": "#000"
      }
    },
    {
      "color": "white",
      "category": "value",
      "code": {
        "rgba": [
          0,
          0,
          0,
          1
        ],
        "hex": "#FFF"
      }
    },
    {
      "color": "red",
      "category": "hue",
      "type": "primary",
      "code": {
        "rgba": [
          255,
          0,
          0,
          1
        ],
        "hex": "#FF0"
      }
    },
    {
      "color": "blue",
      "category": "hue",
      "type": "primary",
      "code": {
        "rgba": [
          0,
          0,
          255,
          1
        ],
        "hex": "#00F"
      }
    },
    {
      "color": "yellow",
      "category": "hue",
      "type": "primary",
      "code": {
        "rgba": [
          255,
          255,
          0,
          1
        ],
        "hex": "#FF0"
      }
    },
    {
      "color": "green",
      "category": "hue",
      "type": "secondary",
      "code": {
        "rgba": [
          0,
          255,
          0,
          1
        ],
        "hex": "#0F0"
      }
    }
  ]
}

{
  "colors": 
    {
      "color": "black",
      "category": "hue",
      "type": "primary",
      "code": {
        "rgba": [
          255,
          255,
          255,
          1
        ],
        "hex": "#000"
      }
    }
    }
{
  "colors":     
    {
      "color": "white",
      "category": "value",
      "code": {
        "rgba": [
          0,
          0,
          0,
          1
        ],
        "hex": "#FFF"
      }
    }
    }

---

json.dumps（x）

看起来像源文件吗？Hi@Kris，No

json.dumps（x）

有多个数组。

jData

与源代码相同。如果

jData

正确，那么对我来说

pd.DataFrame（jData['colors'）

似乎可以工作。Hi@Kris，

pd.DataFrame（jData['colors'）

仍然给我多个数组。