python批量从es取数据的方法(文档数超过10000)-创新互联

如下所示:

创新互联建站是专业的红安网站建设公司,红安接单;提供网站设计制作、网站设计,网页设计,网站设计,建网站,PHP网站建设等专业做网站服务;采用PHP框架,可快速的进行红安网站开发网页制作和功能扩展;专业做搜索引擎喜爱的网站,专业的做网站团队,希望更多企业前来合作!
"""
提取文档数超过10000的数据
按照某个字段的值具有唯一性进行升序,
按照@timestamp进行降序,
第一次查询,先将10000条数据取出,
取出最后一个时间戳,
在第二次查询中,设定@timestamp小于将第一次得到的最后一个时间戳,
同时设定某个字段的值具有唯一性进行升序,
按照@timestamp进行降序,
"""

from elasticsearch import Elasticsearch
import os

write_path = "E:\\公司\\案例数据采集\\olt告警案例分析\\10000_data.txt"
es = Elasticsearch(hosts="", timeout=1500)
write_file = open(write_path, "a+")


def _first_query():
  index_ = "gather-010"
  _source = ["TWICE_BOOK_TIME", "@timestamp"]
  try:
    rs = es.search(index=index_, body={
      "size": 10000,
      "query": {
        "match_all": {}
      },
      "sort": [
        {
          "@timestamp": {
            "order": "desc"
          }
        },
        {
          "TASK_RECEIVE_ID.keyword": {
            "order": "asc"
          }
        }
      ],
      "_source": _source
    })
    return rs
  except:
    raise Exception("{0} search error".format(index_))


def _get_first_data(first_rs):
  i = 0
  if first_rs:
    for hit in first_rs['hits']['hits']:
      IptvAccount = hit['_source']['TWICE_BOOK_TIME']
      timestamp = hit['_source']['@timestamp']
      if IptvAccount is None:
        IptvAccount = ""
      write_file.write(IptvAccount + "," + timestamp + "\n")
      i += 1
      if i == 10000:
        return timestamp


def _second_query(timestamp):
  index_ = "gather-010"
  _source = ["TWICE_BOOK_TIME", "@timestamp"]
  try:
    rs = es.search(index=index_, body={
      "size": 10000,
      "query": {
        "bool": {
          "filter": {
            "range": {
              "@timestamp": {
                "lt": timestamp
              }
            }
          }
        }
      },
      "sort": [
        {
          "@timestamp": {
            "order": "desc"
          }
        },
        {
          "TASK_RECEIVE_ID.keyword": {
            "order": "asc"
          }
        }
      ],
      "_source": _source
    })
    return rs
  except:
    raise Exception("{0} search error".format(index_))


if __name__ == "__main__":
  first_rs = _first_query()
  first_timestamp = _get_first_data(first_rs)
  print(first_timestamp)
  while True:
    second_rs = _second_query(first_timestamp)
    first_timestamp = _get_first_data(second_rs)
    if first_timestamp is None:
      break
    print(first_timestamp)

新闻名称:python批量从es取数据的方法(文档数超过10000)-创新互联
文章出自:http://scyanting.com/article/cdhoji.html