{
"_id" : ObjectID("xxxx"),
"text" : "Something interesting ...",
"entities" : {
"user_mentions" : [
{
"screen_name" : "somebody_else",
...
}
],
"urls" : [],
"hashtags": []
},
"user" : {
"friends_count" : 544,
"screen_name" : "somebody",
"followers_count" : 100,
}
}
from pymongo import MongoClient
import pprint
client = MongoClient("mongodb://localhost:27017")
db = client.twitter
def most_tweets():
result = db.tweets.aggregate([
{ "$group" : {"_id" : "$user.screen_name",
"count": {"$sum" : 1}}},
{ "$sort" : {"count" : -1 }}
])
return result
if __name__ == '__main__':
result = most_tweets()
pprint.pprint(result)