Created
December 17, 2012 15:54
-
-
Save jibs/4319351 to your computer and use it in GitHub Desktop.
copy all data in elasticsearch to a local file using pyes
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
import pyes | |
import simplejson as json | |
SOURCE =['SERVER:9200'] | |
sconn = pyes.ES(SOURCE) | |
def scroll_gen(index): | |
q = '{"query":{"match_all":{}}, "size": 15000}' | |
s = sconn.search_raw(json.loads(q), scroll="5m", indices=index) | |
scroll_id = s._scroll_id | |
yield s.hits.hits | |
scroll = sconn.search_scroll(scroll_id) | |
while scroll.hits.hits: | |
yield scroll.hits.hits | |
scroll = sconn.search_scroll(scroll_id) | |
scroll_id = scroll._scroll_id | |
# print "scroll_id: %s" % scroll_id | |
def copy_data(): | |
index = 'index_name' | |
appendfile = open(index + '-copy.json', 'w') | |
sgen = scroll_gen(index) | |
for count, res in enumerate(sgen): | |
for records, hit in enumerate(res): | |
appendfile.write(json.dumps(dat) + '\n') | |
if count % 1000 == 0: | |
print count | |
def main(): | |
copy_data() | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment