how to prevent backslash while writing json file in pyspark - json

Question

I need to write a data into json file like in the below format using pyspark.
{
"list-item": [
{"author":"author1","title":"title1","pages":1,"email":"author1#gmail.com"},
{"author":"author2","title":"title2","pages":2,"email":"author2#gmail.com"},
{"author":"author3","title":"title3","pages":3,"email":"author3#gmail.com"},
{"author":"author4","title":"title4","pages":4,"email":"author4#gmail.com"},
],
"version": 1
}
I have written the below pyspark code but it write "" and adding "" at the beginning and end of each item. How to remove the backslash and double quote
import sys
from pyspark.sql import SparkSession
from pyspark.sql.types import *
from pyspark.sql.functions import col,to_json,struct,collect_list,lit
from datetime import datetime
from time import time
if __name__ == '__main__':
spark = SparkSession.builder.appName("Test").enableHiveSupport().getOrCreate()
schema = StructType([
StructField("author", StringType(), False),
StructField("title", StringType(), False),
StructField("pages", IntegerType(), False),
StructField("email", StringType(), False)
])
data = [
["author1", "title1", 1, "author1#gmail.com"],
["author2", "title2", 2, "author2#gmail.com"],
["author3", "title3", 3, "author3#gmail.com"],
["author4", "title4", 4, "author4#gmail.com"]
]
df = spark.createDataFrame(data, schema)
df=df.select(to_json(struct("author", "title", "pages", "email")).alias("json-data")).agg(collect_list("json-data").alias("list-item"))
df=df.withColumn("version",lit("1.0").cast(IntegerType()))
df.printSchema()
df.show(2, False)
curDT = datetime.now()
targetPath = curDT.strftime("%m-%d-%Y-%H-%M-%S")
df.write.format("json").mode("overwrite").option("escape", "").save(targetPath)
my code writes the json with backslash and double quote enclosed each item like below.how to remove those.Please help
{"list-item":["{\"author\":\"author1\",\"title\":\"title1\",\"pages\":1,\"email\":\"author1#gmail.com\"}","{\"author\":\"author2\",\"title\":\"title2\",\"pages\":2,\"email\":\"author2#gmail.com\"}","{\"author\":\"author3\",\"title\":\"title3\",\"pages\\":3,\"email\":\"author3#gmail.com\\"}","{\"author\":\"author4\",\"title\":\"title4\",\"pages\":4,\"email\":\"author4#gmail.com\"}"],"version":1}

Answer 1

The reason is that the type of the elements of the list-item array is string, and the \ is there to point this fact out.
To avoid that you can try:
import pyspark.sql.functions as f
from pyspark.sql.types import *
schema = StructType([
StructField("author", StringType(), False),
StructField("title", StringType(), False),
StructField("pages", IntegerType(), False),
StructField("email", StringType(), False)
])
data = [
["author1", "title1", 1, "author1#gmail.com"],
["author2", "title2", 2, "author2#gmail.com"],
["author3", "title3", 3, "author3#gmail.com"],
["author4", "title4", 4, "author4#gmail.com"]
]
df = spark.createDataFrame(data, schema)
df=df.groupby().agg(f.collect_list(f.struct(f.col('author'), f.col('title'), f.col('pages'), f.col('email'))).alias("list-item"))
df=df.withColumn("version",f.lit("1.0").cast(IntegerType()))
df.printSchema()
df.show(2, False)
df.write.format("json").mode("overwrite").option("escape", "").save('./TestJson')
and the output json file is gonna look like:
{"list-item":[{"author":"author1","title":"title1","pages":1,"email":"author1#gmail.com"},{"author":"author2","title":"title2","pages":2,"email":"author2#gmail.com"},{"author":"author3","title":"title3","pages":3,"email":"author3#gmail.com"},{"author":"author4","title":"title4","pages":4,"email":"author4#gmail.com"}],"version":1}