Index CSV to ElasticSearch in Python
This kind of task is easier with the lower-level elasticsearch-py
library:
from elasticsearch import helpers, Elasticsearch
import csv
es = Elasticsearch()
with open('/tmp/x.csv') as f:
reader = csv.DictReader(f)
helpers.bulk(es, reader, index='my-index', doc_type='my-type')
If you want to create elasticsearch
database from .tsv/.csv
with strict types and model for a better filtering u can do something like that :
class ElementIndex(DocType):
ROWNAME = Text()
ROWNAME = Text()
class Meta:
index = 'index_name'
def indexing(self):
obj = ElementIndex(
ROWNAME=str(self['NAME']),
ROWNAME=str(self['NAME'])
)
obj.save(index="index_name")
return obj.to_dict(include_meta=True)
def bulk_indexing(args):
# ElementIndex.init(index="index_name")
ElementIndex.init()
es = Elasticsearch()
//here your result dict with data from source
r = bulk(client=es, actions=(indexing(c) for c in result))
es.indices.refresh()