Created
August 21, 2016 08:32
-
-
Save yuanotes/62fdd3b03a67e7d6bb9b1c3c61816805 to your computer and use it in GitHub Desktop.
Process elastic search json result to csv.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# coding=utf-8 | |
import re | |
import os.path | |
import sys | |
import json | |
PATH = os.path.dirname(os.path.abspath(__file__)) | |
def get_file_name(name): | |
result = re.search(r'(\w+)\.[^\.]+$', name) | |
if result: | |
return result.group(1) | |
else: | |
return name | |
# RESP_FILE = os.path.join(PATH, sys.argv[1]) | |
RESP_FILE = os.path.join(PATH, "ydy_0821.json") | |
CSV_FILE = "%s.csv" % get_file_name(RESP_FILE) | |
with open(RESP_FILE, 'r') as in_file: | |
with open(CSV_FILE, 'w') as out_file: | |
in_json = json.load(in_file) | |
result_map = in_json["aggregations"]["2"]["buckets"] | |
out_file.write('运动员,声量\n') | |
for ydy_name in result_map.keys(): | |
buckets = result_map[ydy_name]["3"]["buckets"] | |
for bucket in buckets: | |
ydy_data = [ydy_name] | |
ydy_data.append(bucket["key_as_string"].replace("T00:00:00.000+08:00","")) | |
ydy_data.append(str(bucket["doc_count"])) | |
out_file.write((",".join(ydy_data) + '\n').encode('utf-8')) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment