In [ ]:

    

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import elasticsearch
import unicodedata
import csv

es = elasticsearch.Elasticsearch(["localhost:9200"])


    

In [ ]:

    

index_name="weiboscope"
meme_keywords="杜甫很忙"
csv_file="杜甫很忙.csv"


    

In [25]:

    

res = es.search(index=index_name, body={"query": {"match": { "text" : "'杜甫很忙'" }}})
data_size=res['hits']['total']
print("Total %d Hits" % data_size)

res2 = es.search(index=index_name, body={"query": {"match": { "text" : "'杜甫很忙'" }}}, size=10)
results=res2['hits']['hits']
print("%d Hits Retreived" % len(results))


    

    




Total 705362 Hits
10 Hits Retreived

In [26]:

    

# get headers
headers=[value for value in sample["_source"]]


    

In [50]:

    

# then open a csv file, and loop through the results, writing to the csv
with open(csv_file, 'wb') as csvfile: 
    filewriter = csv.writer(csvfile)
    # create column header row
    filewriter.writerow(headers)
    for sample in results: 
        row=[]
        for id in sample["_source"]:
            if type(sample["_source"][id]) == unicode : data = sample["_source"][id].encode("utf-8") 
            else : data = sample["_source"][id] 
            row.append(data)

        filewriter.writerow(row)

print "Done. Data saved in %s"%csv_file


    

    




Done. Data saved in 杜甫很忙.csv

In [ ]: