match_spider/lzz_theme/utils/es_query.py

# -*- coding: utf-8 -*-
"""
Created on 2023-12-25 
---------
@summary: es
---------
@author: Lzz
"""
import sys
import os
sys.path.append(os.path.dirname(os.getcwd()))
from elasticsearch import Elasticsearch
from utils.title_participle import get_should


# es:
#   host: 172.17.4.184
#   usename: "jybid"
#   pwd: "Top2023_JEB01i@31"
#   port: !!int 19905
#   db: biddingall # es库别名


def es_client():
    cfg = {"host": "172.17.4.184",
           "port": 19905,
           "usename": "jybid",
           "pwd": "Top2023_JEB01i@31"}
    return Elasticsearch([{"host": cfg['host'], "port": cfg['port']}],http_auth=(cfg['usename'], cfg['pwd']))


def es_search(title: str, publish_time: int):
    """
    查询es

    :param title: 标题
    :param publish_time: 发布时间
    :return:
    """
    client = es_client()
    stime = publish_time - 432000  # 往前推5天
    etime = publish_time + 432000

    time_limit = {"range": {"publishtime": {"from": stime, "to": etime}}}
    should_list = get_should(title)   # 对标题进行分词组合query语句
    # 通过发布标题和发布时间范围查询
    query = {
        "query": {
            "bool": {
                "must": [time_limit],
                "should": should_list,
                "minimum_should_match": "10<90%",
            }
        }
    }
    result = client.search(index="biddingall", body=query, request_timeout=100)
    total = int(result['hits']['total']['value'])
    return total