Querying in mongodb 3.4 - mongodb

Question

I have large XML files which I had to convert in json and store in mongodb. The python code for conversion and insertion is:
import pymysql
import re
import json
import xmltodict
from pymongo import MongoClient
# Open Database Connection.
db = pymysql.connect("fffff","ddd","fgf","hnj")
# prepare a cursor object
cursor = db.cursor()
# execute SQL query
cursor.execute("SELECT jlp.appid, convert(MAX(lex.response) using utf8) FROM jos_lender_portfolio jlp INNER JOIN jos_lexnex_data lex ON jlp.appid = lex.appid\
group by appid limit 10;")
# Fetch all rows
data = cursor.fetchall()
a = (r'(?=<response>)(.*)(?<=</response>)')
def cleanxml(xml):
if re.findall(a, xml, re.S):
file = re.findall(a, xml, re.S)[0]
else:
file = "<response>NA</response>"
return file
data = list(data)
client = MongoClient()
db = client['lexnex']
collection = db['test']
for row in data:
thexml = cleanxml(row[1])
jsonString = json.dumps(xmltodict.parse(thexml), indent = 4)
d = json.loads(jsonString)
newdict = {"caseid" : row[0]}
newdict.update(d)
jsondata = json.dumps(newdict, indent = 3)
f = json.loads(jsondata)
db.test.insert_one(f)
Now, the problem: I'm very new to mongodb and having problem in querying my database.I have the following json:
"_id":ObjectId("5aeff8537871560bf05d8c25"),
"caseid":44136,
"response":{
"Header":{
"TransactionId":"18092257R1069402",
"Status":"0"
},
"Records":{
"Record":[
{
"Filings":{
"Filing":{
"Type":"INITIAL FILING",
"Date":{
"Day":"23",
"Month":"9",
"Year":"2008"
}
}
},
"FilingJurisdiction":"NY",
"MatchedParty":{
"PartyType":"D",
"Address":{
"City":"BROOKLYN",
"State":"NY",
},
"OriginName":"GOLDLINE"
},
"Secureds":{
"Secured":{
"Addresses":{
"Address":{
"City":"SCHAUMBURG",
"State":"IL"
}
}
}
}
},
{
,
"Filings":{
"Filing":{
"Type":"INITIAL FILING",
"Date":{
"Day":"23",
"Month":"9",
"Year":"2008"
}
}
},
"FilingJurisdiction":"NY",
"MatchedParty":{
"PartyType":"D",
"Address":{
"City":"BROOKLYN",
"State":"NY",
},
"OriginName":"GOLD"
},
"Secureds":{
"Secured":{
"Addresses":{
"Address":{
"City":"SCHAUMBURG",
"State":"IL"
}
}
}
}
}
]
}
}
This is a small portion of a very big document and there are more than a million such documents. Now, the expected result which I want is for every caseid, some part of the Filings and the Secureds. Here's the sample expected output:
"_id":ObjectId("5aeff8537871560bf05d8c25"),
"caseid":44136,
"Filings":{
[
"Filing":{
"Type":"INITIAL FILING",
"Date":{
"Day":"23",
"Month":"9",
"Year":"2008"
}
},
"Secureds":{
"Secured":{
"Addresses":{
"Address":{
"City":"SCHAUMBURG",
"State":"IL"
}
}
}
},
{
"Filing":{
"Type":"INITIAL FILING",
"Date":{
"Day":"23",
"Month":"9",
"Year":"2008"
}
}
},
"Secureds":{
"Secured":{
"Addresses":{
"Address":{
"City":"SCHAUMBURG",
"State":"IL"
}
}
}
}
]
}
There are several caseids and each one has 0 or more filings. I have no clue how to do it. I know the basics like simple queries. But this, I think, requires $unwind and $group together. What I have written so far is nothing but just this:
db.test.aggregate([{$unwind:{path: '$response'}},{"$group":{_id:{caseid:"$caseid"}}}])
Please help.