使用 pymongo 从集合中获取 Mongo 字段名称

Question

I am trying to get fields names from the MongoDB using pymongo. Is there a way to do that?

Mongo Collection Format:

    "_id" : ObjectId("5e7a773721ee63712e9d25a3"),
    "effective_date" : "2020-03-24",
    "data" : [
        {
            "Year" : 2020,
            "month" : 1,
            "Day" : 28,
            "views" : 4994,
            "clicks" : 3982
        },
        {
            "Year" : 2020,
            "month" : 1,
            "Day" : 17,
            "views" : 1987,
            "clicks" : 3561
        },
        .
        .
        .
       ]

Is there a way I can get field names: I want to get: _id, effective_date, data.Year, data.month, data.Day, data.views, data.clicks

This is what I have:

from datetime import datetime, timedelta, date
import pymongo
from pymongo import MongoClient
from pymongo.read_preferences import ReadPreference
from pprint import pprint
from bson.son import SON
from bson import json_util
from bson.json_util import dumps, loads
import re


client = pymongo.MongoClient(host='mongodb://00.00.00.0:00000')
db = client.collection
pprint(db)

def get_results(filters):

    col=db.results
    res = col.find()

    res = list(res)

    return dumps(res, indent=4)

Is there a way for me to get just the field names using pymongo?

Answer 1

We are not really filtering or aggregating in the example; we are doing a big find() and then we want all the field names. There is no projection either. So assuming that we are dragging over all the data anyway, let the client side do the work. Here's something that will capture unique field names including through arrays and give you a count of each unique field name as well:

r = [
    {"_id":0, "A":"A", "data":[
            {"Y":2020,"day":3,"clicks":12},
            {"Y":2020,"day":4,"clicks":192}
            ]} ,
    {"_id":1, "B":{"foo":"bar"}, "data":[
            {"Y":2020,"day":3,"clicks":888,"corn":"dog"},
            {"Y":2020,"day":4,"clicks":999,"zing":"zap"}
            ]} ,
    {"_id":2, "B":{"foo":"bit"} },
    {"_id":3, "B":{"fin":"bar"} }
]
coll.insert(r)

fieldNames = {}

def addFldName(s):
    if s not in fieldNames:
        fieldNames[s] = 0
    fieldNames[s] += 1

def process(path, v):
    addFldName(path)
    if("dict" == v.__class__.__name__):
        walkMap(path, v)
    elif("list" == v.__class__.__name__):
        walkList(path, v)

def walkMap(path, doc):
    dot = "" if path is "" else "."
    for k, v in doc.iteritems():
        s = path + dot + k
        process(s, v)

def walkList(path, array):
    dot = "" if path is "" else "."
    for n in range(0,len(array)):
        s = path + dot + str(n)
        process(s, array[n])

for doc in coll.find():
    walkMap("", doc)

print(fieldNames)

{u'A': 1, u'data.1.clicks': 2, u'B': 3, u'data.0': 2, u'data.1': 2, u'data.0.Y': 2, u'data.1.zing': 1, u'data.0.day': 2, u'B.fin': 1, u'B.foo': 2, u'data.1.Y': 2, u'_id': 4, u'data': 2, u'data.0.corn': 1, u'data.0.clicks': 2, u'data.1.day': 2}

It's a little weird, but yes, data.0.clicks is unique and shows up in 2 docs.