ES查询语句

GET /_cat/indices


GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 20, 
  "query": {
    "match_all": {}
  },
  "_source": {
    "includes": ["articleId","article_index","article_en"]
  },
  "sort": [
    {
      "article_index": {
        "order": "desc"
      }
    }
  ]
}


GET seokeytagsdata/_mapping

 

GET  seokeytagsdata/_search
{
  "query": {
    "term": {
      "corekwdId": {
        "value": "2183894"
      }
    }
  }
}

GET seokeytagsdata_0818/_search
{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must_not": [
        {
          "exists": {
            "field": "tag_key_url"
          }
        }
      ]
    }
  }
}

GET seokeytagsdata_0818/_search
{
  "track_total_hits": true, 
  "query": {
    "match_all": {}
  }
}



GET seokeytagsdata/_search
{
  "track_total_hits": true, 
  "query": {
    "match_all": {}
  }
}

GET seojoindata/_search
{
  "size": 0,
  "aggs": {
    "group_by_category": {
      "terms": {
        "field": "seo_category_type.keyword",
        "size": 50
      },
      "aggs": {
        "group_by_part": {
          "terms": {
            "field": "seo_part_name.keyword",
            "size": 100
          },
          "aggs": {
            "group_by_part_url": {
              "terms": {
                "field": "seo_part_url",
                "size": 50
              }
            },
            "group_by_part_id": {
              "terms": {
                "field": "seo_part_Id.keyword",
                "size": 50
              }
            }
          }
        },
        "group_by_category_url": {
          "terms": {
            "field": "seo_category_url",
            "size": 50
          }
        },
        "group_by_category_id": {
          "terms": {
            "field": "seo_category_Id.keyword",
            "size": 50
          }
        }
      }
    }
  }
}

GET seojoindata/_search
{
  "track_total_hits": true, 
  "size": 40,
  "query": {
    "bool": {
      "should": [
        {
          "term": {
            "seo_part_Id.keyword": {
              "value": "seoc14"
            }
          }
        },
        {
          "term": {
            "seo_category_Id.keyword": {
              "value": "seoc14"
            }
          }
        }
      ]
    }
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ],
  "_source": [
    "coreKeyWord","otherkwdlist"
  ]
}

{
  "track_total_hits": true, 
  "size": 10000, 
  "query": {
    "wildcard": {
      "pubdate": {
        "value": "2020-06*"
      }
    }
  },
  "_source": ["article_url","pubdate"]
}



GET seojoindata/_mapping

GET seojoindata/_count


GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 500,
  "query": {
    "match_all": {}
  },
  "_source": {
    "includes": [
      "coreKeyWord", 
      "article_url",
      "title_en",
      "articleId",
      "fullurl"
    ]
  }
}

GET seojoindata/_search
{
  "size": 11,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist.tagId"
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "exists": {
                "field": "coreKeyWord.corekwdId"
              }
            }
          }
        },
        {
          "match": {
            "title_en": {
              "query": "Experts talk about the phosphating process before the primer is applied",
              "analyzer": "english",
              "minimum_should_match": "50%"
            }
          }
        }
      ],
      "must_not": [
        {
          "term": {
            "title_en.raw": {
              "value":  "Experts talk about the phosphating process before the primer is applied"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "articleId",
      "article_url",
      "title_en",
      "pubdate",
      "clickCount"
    ]
  }
}


GET seojoindata/_search
{
  "track_total_hits": true, 
  "size": 0, 
  "query": {
    "term": {
      "trans_date": {
        "value": "2020-07-28"
      }
    }
  }
}




GET seojoindata/_search
{
  "size": 1000, 
  "query": {
    "term": {
      "trans_date": {
        "value": "2020-07-28"
      }
    }
  },
  "_source": ["title_en","article_en"]
}


GET seojoindata/_search
{
  "query": {
    "term": {
      "title_en.raw": {
        "value": "FDA approved the first precise therapy for gastrointestinal stromal tumor"
      }
    }
  },
  "_source": ["title_en","article_en"]
}


GET seojoindata/_search
{
  "query": {
    "term": {
      "fullurl": {
        "value": "https://news.yaozh.com/archive/28331.html"
      }
    }
  },
  "_source": ["article_en","fullurl","title_en","title"]
}

GET seojoindata/_search
{
  "track_total_hits": true, 
  "size": 1000, 
  "query": {
     "term": {
       "endSource": {
         "value": "www.x-mol.com"
       }
     }
  },
  "_source": ["article_en","fullurl","endSource"]
}

GET seojoindata/_search
{
  "query": {
    "term": {
      "articleId": {
        "value":  "83548"
      }
    }
  }
}

GET seojoindata/_search
{
  "track_total_hits": true,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": "1"
            }
          }
        },
        {
          "term": {
            "seo_part_Id.keyword": {
              "value": "seoc2116"
            }
          }
        }
      ]
    }
  },
  "_source": [

    "article_index",
   
    "seo_part_name",
    "seo_part_url"
  ]
}

GET seojoindata/_search
{
  "query": {
    "match_all": {}
  },
  "_source": [
    "seo_part_Id",
    "seo_part_name",
    "seo_part_url"
  ]
}

GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist.tagId"
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "term": {
            "articleId": {
              "value": "5eba4dee8fdca9edee8882b8"
            }
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "bool": {
                "must": [
                  {
                    "exists": {
                      "field": "coreKeyWord.corekwdId"
                    }
                  }
                ]
              }
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "coreKeyWord",
      "seo_part_Id",
      "seo_part_name",
      "seo_part_url"
    ]
  }
}

GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "term": {
            "weekday.keyword": {
              "value": "Sunday"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "min_max_kId": {
      "stats": {
        "field": "article_index"
      }
    }
  }
}

GET seojoindata/_search
{
  "track_total_hits": true,
  "from":1790,
  "size": 100,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "term": {
            "weekday.keyword": {
              "value": "Sunday"
            }
          }
        }
      ]
    }
  },
  "sort": [
    {
      "article_index": {
        "order": "asc"
      }
    }
  ],
  "_source": [
    "article_url",
    "title_en",
    "weekday",
    "article_index",
    "pubdate"
  ]
}


GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 100,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "term": {
            "weekday.keyword": {
              "value": "Sunday"
            }
          }
        }
      ]
    }
  },
  "search_after": [0],
  "sort": [
    {
      "article_index": {
        "order": "asc"
      }
    }
  ],
  "_source": [
    "article_url",
    "title_en",
    "weekday",
    "article_index",
    "pubdate"
  ]
}


# 获取二级分类的关键词列表
GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "term": {
            "seo_part_Id.keyword": {
              "value": "seoc1111"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "min_max_kId": {
      "stats": {
        "field": "article_index"
      }
    }
  }
}


# 开始 35407
# 今天 52491
GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        },
        {
          "exists": {
            "field": "seo_category_Id"
          }
        }
      ]
    }
  }
}

GET seojoindata/_count


GET seojoindata/_search
{
  "query": {
    "match_all": {}
  },
  "_source": {
    "excludes": ["article_summery","title_en","article_en","taglist"]
  }
}



GET seojoindata/_search
{
  "size": 2,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "term": {
            "seo_part_Id.keyword": {
              "value": "seoc11_2"
            }
          }
        }
      ]
    }
  },
  "_source": [
    "taglist",
    "seo_category_type",
    "seo_category_url",
    "seo_part_name",
    "seo_part_url"
  ]
}

# 一级分类下的关键词
GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 100,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": "1"
            }
          }
        },
        {
          "term": {
            "seo_category_Id.keyword": {
              "value": "seoc14"
            }
          }
        }
      ]
    }
  },
  "sort": [
    {
      "article_index": {
        "order": "asc"
      }
    }
  ],
  "_source": [
    "coreKeyWord",
    "article_index",
    "seo_category_url",
    "seo_category_type"
  ]
}


GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "term": {
            "weekday.keyword": {
              "value": "Monday"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "min_max_kId": {
      "stats": {
        "field": "article_index"
      }
    }
  }
}


GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 20,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "term": {
            "weekday.keyword": {
              "value": "Monday"
            }
          }
        }
      ]
    }
  },
  "search_after": [
    2034
  ],
  "sort": [
    {
      "article_index": {
        "order": "asc"
      }
    }
  ],
  "_source": [
    "article_url",
    "title_en",
    "weekday",
    "article_index",
    "pubdate"
  ]
}



GET seojoindata/_search
{
  "track_total_hits": true, 
  "size": 10, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "seo_category_Id.keyword": {
              "value": "seoc14"
            }
          }
        }
      ]
    }
  },
  "sort": [
    {
      "article_index": {
        "order": "asc"
      }
    }
  ], 
  "_source": ["coreKeyWord","article_index"]
}


GET seojoindata/_search
{
  "size": 10, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "seo_part_Id.keyword": {
              "value": "seoc1420"
            }
          }
        }
      ]
    }
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ], 
  "_source": ["coreKeyWord"]
}


GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "seo_part_Id.keyword": {
              "value": "seoc1420"
            }
          }
        }
      ]
    }
  },
  "_source": ["otherkwdlist","pubdate","weekday"]
}





GET seojoindata/_search
{
  "query": {
    "term": {
      "articleId": {
        "value": "5e54adcad515cd71ed254315"
      }
    }
  },
  "_source": {
    "excludes": [
      "otherkwdlist", 
      "fullurl",
      "model",
      "title",
      "endSource"
    ]
  }
}


GET seojoindata/_search
{
  "track_total_hits": true,
  "from": 0,
  "size": 20, 
  "query": {
    "bool": {
      "must": [
        {
          "nested": {
            "path": "otherkwdlist",
            "query": {
              "bool": {
                "must": [
                  {
                    "term": {
                      "otherkwdlist.keyId": {
                        "value": 5060
                      }
                    }
                  }
                ]
              }
            }
          }
        },

        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "title_en",
      "article_url",
      "pubdate",
      "articleId"
    ]
  }
}


GET seojoindata/_search
{
  "size": 0,
  "aggs": {
    "group_by_category": {
      "terms": {
        "field": "seo_category_type.keyword",
        "size": 50
      },
      "aggs": {
        "group_by_part": {
          "terms": {
            "field": "seo_part_name.keyword",
            "size": 100
          },
          "aggs": {
            "group_by_part_url": {
              "terms": {
                "field": "seo_part_url",
                "size": 50
              }
            },
            "group_by_part_id": {
              "terms": {
                "field": "seo_part_Id.keyword",
                "size": 50
              }
            }
          }
        },
        "group_by_category_url": {
          "terms": {
            "field": "seo_category_url",
            "size": 50
          }
        },
        "group_by_category_id": {
          "terms": {
            "field": "seo_category_Id.keyword",
            "size": 50
          }
        }
      }
    }
  }
}



GET seojoindata/_search
{
  "size": 5,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "term": {
            "seo_part_Id.keyword": {
              "value": "seoc1420"
            }
          }
        }
      ]
    }
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ],
  "_source": [
    "otherkwdlist"
  ]
}

GET seojoindata/_search
{
  "track_total_hits": true, 
  "from": 0,
  "size": 20, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist"
          }
        },
        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "term": {
            "is_valid": {
              "value": "1"
            }
          }
        },
        {
          "term": {
            "pubdate": {
              "value": "2020-05-06"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": ["article_url","title_en","pubdate"]
  }
}



GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist"
          }
        },
        {
          "exists": {
            "field": "weekday"
          }
        },
        {
          "term": {
            "is_valid": {
              "value": "1"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_week": {
      "terms": {
        "field": "weekday.keyword",
        "size": 12
      },
      "aggs": {
        "sort_by_click": {
          "top_hits": {
            "sort": [
              {
                "pubdate": {
                  "order": "desc"
                }
              },
              {
                "clickCount": {
                  "order": "desc"
                }
              }
            ],
            "size": 12,
            "_source": {
              "includes": [
                "article_url",
                "title_en",
                "pubdate"
              ]
            }
          }
        }
      }
    }
  }
}

# 按照星期 1-7 每个都获取对应的数据
GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 0, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist"
          }
        },
        {
          "exists": {
            "field": "weekday"
          }
        },
        {
          "term": {
            "is_valid": {
              "value": "1"
            }
          }
        }
         
      ]
    }
  },
  "aggs": {
    "group_by_week": {
      "terms": {
        "field": "weekday.keyword",
        "size": 13
      },
      "aggs": {
        "sort_by_click": {
          "top_hits": {
            "sort": [
              {
                "pubdate": {
                  "order": "desc"
                }
              },
              {
              "clickCount": {
                "order": "desc"
              }
            }], 
            "size": 13,
            "_source":{
              "includes": ["article_url","title_en","pubdate","weekday"]
            }
          }
        }
      }
    }
  }
}



# 当前月份的数据聚合
GET seojoindata/_search
{
  "track_total_hits": true, 
  "size": 0, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "exists": {
            "field": "taglist"
          }
        },
        {
          "term": {
            "is_valid": {
              "value": "1"
            }
          }
        },
        {
          "range": {
            "date_pubdate": {
              "gte": "2020-07-01",
              "lte": "2020-07-31",
              "format": "yyyy-MM-dd"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_now_day": {
      "date_histogram": {
        "field": "date_pubdate",
        "calendar_interval": "day",
        "format": "yyyy-MM-dd", 
        "min_doc_count": 0,
        "extended_bounds": {
          "min": "2020-07-01",
          "max": "2020-07-31"
        }
      }
    }
  }
}


# 按照年月日三层聚合
GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": "1"
            }
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "bool": {
            "filter": {
              "range": {
                "date_pubdate": {
                  "gte": 2020,
                  "lt": 2021, 
                  "format": "yyyy"
                }
              }
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_year": {
      "date_histogram": {
        "field": "date_pubdate",
        "calendar_interval": "year",
        "format": "yyyy",
        "min_doc_count": 0,
        "order": {
          "_key": "desc"
        }
      },
      "aggs": {
        "group_by_month": {
          "date_histogram": {
            "field": "date_pubdate",
            "calendar_interval": "month",
            "format": "yyyy-MM",
            "min_doc_count": 0,
            "order": {
              "_key": "desc"
            }
          },
          "aggs": {
            "group_by_day": {
              "date_histogram": {
                "field": "date_pubdate",
                "calendar_interval": "day",
                "format": "yyyy-MM-dd",
                "min_doc_count": 0,
                "order": {
                  "_key": "desc"
                }
              }
            }
          }
        }
      }
    }
  }
}

GET seojoindata/_search
{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_summery"
          }
        },
        {
          "exists": {
            "field": "taglist"
          }
        },
        {
          "term": {
            "is_valid": {
              "value": "1"
            }
          }
        }
      ]
    }
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ], 
  "_source": ["pubdate","date_pubdate"]
}


GET seojoindata_0610/_mapping

GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "is_valid": 1
        }
      }
    }
  },
  "aggs": {
    "group_by_category_type": {
      "terms": {
        "field": "seo_category_type.keyword",
        "size": 100
      },
      "aggs": {
        "show_category_url": {
          "terms": {
            "field": "seo_category_url",
            "size": 100
          }
        },
        "show_category_Id": {
          "terms": {
            "field": "seo_category_Id.keyword",
            "size": 100
          },
          "aggs": {
            "group_by_part_name": {
              "terms": {
                "field": "seo_part_name.keyword",
                "size": 100
              },
              "aggs": {
                "show_part_url": {
                  "terms": {
                    "field": "seo_part_url",
                    "size": 100
                  }
                },
                "show_part_Id": {
                  "terms": {
                    "field": "seo_part_Id.keyword",
                    "size": 100
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}


GET seojoindata/_search
{
  "track_total_hits": true, 
  "query": {
    "regexp": {"article_en": "[\u4e00-\u9fa5]"}
  },
  "_source": ["article_en","articleId","endSource","fullurl"]
}

GET seojoindata/_search
{
  "query": {
    "match_all": {}
  }
}

GET seojoindata/_search
{
  "size": 20,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist.tagId"
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "exists": {
                "field": "coreKeyWord.corekwdId"
              }
            }
          }
        },
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "exists": {
            "field": "seo_part_Id"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part": {
      "terms": {
        "field": "seo_part_name.keyword",
        "size": 50
      },
      "aggs": {
        "group_by_part_url": {
          "terms": {
            "field": "seo_part_url",
            "size": 1
          }
        },
        "group_by_part_Id": {
          "terms": {
            "field": "seo_part_Id.keyword",
            "size": 1
          }
        }
      }
    }
  }
}


GET seojoindata/_search
{
  "size": 2000,
  "query": {
    "bool": {
      "should": [
        {
          "term": {
            "FIELD": {
              "value": "VALUE"
            }
          }
        },{
          "term": {
            "FIELD": {
              "value": "VALUE"
            }
          }
        }
      ]
    }
  },
  "_source": {
     "includes": ["article_summery","article_en"]
  }
}


GET seojoindata/_search
{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must": [
       
      ]
    }
  },
  "_source": ["article_index","article_en"]
}

GET seojoindata/_search
{
  "track_total_hits": true, 
  "size": 10, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "seo_part_Id.keyword": {
              "value": "seoc2126"
            }
          }
        }
      ]
    }
  },
  "search_after":[2034],
  "sort": [
    {
      "article_index": {
        "order": "asc"
      }
    }
  ], 
  "_source": ["article_index","otherkwdlist"]
}


# otherkwdlist.keyId 的最大最小编号
GET seojoindata/_search
{
  "track_total_hits": true, 
  "size": 0,
  "query": {
    "constant_score": {
      "filter": {
        "term": {
          "seo_part_Id.keyword": "seoc2126"
        }
      },
      "boost": 1.2
    }
  },
  "aggs": {
    "group_by_otherkwd": {
      "nested": {
        "path": "otherkwdlist"
      },
      "aggs": {
        "min_max_kwdid": {
          "stats": {
            "field": "otherkwdlist.keyId"
          }
        }
      }
    },
    "group_by_article_index": {
      "stats": {
        "field": "article_index"
      }
    }
  }
}


# 对应文章编号
GET seojoindata/_search
{
  "size": 0,
  "query": {
    "constant_score": {
      "filter": {
        "term": {
          "seo_part_Id.keyword": "seoc2126"
        }
      },
      "boost": 1.2
    }
  },
  "aggs": {
    "group_by_otherkwd": {
      "stats": {
        "field": "article_index"
      }
    }
  }
}

GET seojoindata/_search
{
  "size": 0,
  "aggs": {
    "group_by_category": {
      "terms": {
        "field": "seo_category_type.keyword",
        "size": 50
      },
      "aggs": {
        "group_by_part": {
          "terms": {
            "field": "seo_part_name.keyword",
            "size": 100
          },
          "aggs": {
            "group_by_part_url": {
              "terms": {
                "field": "seo_part_url",
                "size": 50
              }
            },
            "group_by_part_id": {
              "terms": {
                "field": "seo_part_Id.keyword",
                "size": 50
              }
            }
          }
        },
        "group_by_category_url": {
          "terms": {
            "field": "seo_category_url",
            "size": 50
          }
        },
        "group_by_category_id": {
          "terms": {
            "field": "seo_category_Id.keyword",
            "size": 50
          }
        }
      }
    }
  }
}





GET seojoindata/_search
{
  "size":10,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "term": {
            "seo_part_Id.keyword": {
              "value": "seoc2126"
            }
          }
        }
      ]
    }
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ], 
  "_source": ["otherkwdlist","seo_part_Id"]
}

GET seojoindata_0610/_search
{
  "size": 0,
  "aggs": {
    "group_by_category": {
      "terms": {
        "field": "seo_category_type.keyword",
        "size": 10
      },
      "aggs": {
        "group_by_part": {
          "terms": {
            "field": "seo_part_name.keyword",
            "size": 100
          },
          "aggs": {
            "group_by_other": {
              "nested": {
                "path": "otherkwdlist"
              },
              "aggs": {
                "group_by_other_kwd": {
                  "terms": {
                    "field": "otherkwdlist.keyname.raw",
                    "size": 50
                  },
                  "aggs": {
                    "distinct": {
                      "cardinality": {
                        "field": "otherkwdlist.keyname.raw"
                      }
                    }
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}


GET seokeytagsdata/_search
{
  "query": {
    "terms": {
      "corekwd.raw": [
        "amuc_1100",
        "a _",
        "amuc_1100 akkermansia"
      ]
    }
  }
}

GET seokeytagsdata/_search
{
  "query": {
    "term": {
      "corekwd.raw": {
        "value": "before ach can be inactivated _______ must be present"
      }
    }
  }
}


GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 200,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "term": {
            "weekday.keyword": {
              "value": "Tuesday"
            }
          }
        }
      ]
    }
  },
  "search_after": [0],
  "sort": [
    {
      "article_index": {
        "order": "asc"
      }
    }
  ], 
  "_source": ["article_url","title_en","weekday","article_index"]
}


GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "term": {
            "weekday.keyword": {
              "value": "Monday"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "min_max_kId": {
      "stats": {
        "field": "article_index"
      }
    }
  }
}


GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "is_valid"
          }
        }
      ]
    }
  },
  "sort": [
    {
      "article_index": {
        "order": "asc"
      }
    }
  ], 
  "_source": ["seo_category_url","seo_part_url","is_valid","article_index"]
}

# Site Index1 按照分类 产品大类 小类
GET seojoindata/_search
{
  "size": 0,
  "aggs": {
    "group_by_category": {
      "terms": {
        "field": "seo_category_type.keyword",
        "size": 50
      },
      "aggs": {
        "group_by_part": {
          "terms": {
            "field": "seo_part_name.keyword",
            "size": 100
          },
          "aggs": {
            "group_by_part_url": {
              "terms": {
                "field": "seo_part_url",
                "size": 50
              }
            },
            "group_by_part_id": {
              "terms": {
                "field": "seo_part_Id.keyword",
                "size": 50
              }
            }
          }
        },
        "group_by_category_url": {
          "terms": {
            "field": "seo_category_url",
            "size": 50
          }
        },
        "group_by_category_id": {
          "terms": {
            "field": "seo_category_Id.keyword",
            "size": 50
          }
        }
      }
    }
  }
}


GET seojoindata/_search
{
  "query": {
    "match_all": {}
  },
  "_source": ["otherkwdlist","seo"]
}


# Site Index 2 一级分类下的二级对应的关键词 top 50
GET seojoindata_0610/_search
{
  "size": 0,
  "aggs": {
    "group_by_category": {
      "terms": {
        "field": "seo_category_type.keyword",
        "size": 10
      },
      "aggs": {
        "group_by_part": {
          "terms": {
            "field": "seo_part_name.keyword",
            "size": 100
          },
          "aggs": {
            "group_by_other": {
              "nested": {
                "path": "otherkwdlist"
              },
              "aggs": {
                "group_by_other_kwd": {
                  "terms": {
                    "field": "otherkwdlist.keyname_after.raw",
                    "size": 50
                  },
                  "aggs": {
                    "distinct": {
                      "cardinality": {
                        "field": ""
                      }
                    }
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}

# 3 按照关键词的搜索量排序
GET seokeytagsdata/_search
{
  "size": 0, 
  "query": {
    "bool": {
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 1
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_click": {
      "terms": {
        "field": "clickCount",
        "size": 100
      },
      "aggs": {
        "show_key": {
          "terms": {
            "field": "corekwd.raw", 
            "size": 100
          }
        }
      }
    }
  }
}

# 4 按照关键词匹配的文章数排序
GET seokeytagsdata/_search
{
  "size": 0, 
  "query": {
    "bool": {
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 1
            }
          }
        }
      ]
    }
  }, 
  "aggs": {
    "group_by_match": {
      "terms": {
        "field": "match_count",
        "size": 100
      },
      "aggs": {
        "show_keys": {
          "terms": {
            "field": "corekwdId",
            "size": 30
          }
        }
      }
    }
  }
}

# 4  按照星期
GET seojoindata/_search
{
  "size": 2000, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "weekday"
          }
        }
      ]
    }
  },
  "_source": ["weekday","seo_category_Id","seo_part_name","article_summery","articleId"]
}

GET seojoindata/_count

GET seojoindata/_search
{
  "size": 2000, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_index"
          }
        }
      ]
    }
  },
  "sort": [
    {
      "article_index": {
        "order": "asc"
      }
    }
  ], 
  "_source": ["weekday","articleId","article_index"]
}


GET seojoindata/_search
{
  "track_total_hits": true, 
  "size": 200, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "weekday"
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "term": {
            "weekday.keyword": {
              "value": "Tuesday"
            }
          }
        }
      ]
    }
  },
  "_source": ["weekday","seo_category_Id","seo_part_name","title_en","article_url","pubdate"],
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ]
  
}



GET seojoindata/_search
{
  "track_total_hits": true, 
  "query": {
    "term": {
      "weekday.keyword": {
        "value": "Monday"
      }
    }
  }
}




GET seojoindata/_mapping


GET seojoindata/_count

# POST seojoindata/_delete_by_query

GET seojoindata/_search
{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        }
      ]
    }
  }
}


GET seokeytagsdata/_search
{
  "query": {
   "term": {
     "corekwdId": {
       "value": "130645"
     }
   }
  }
}



GET seokeytagsdata/_search
{
  "query": {
    "terms": {
      "corekwdId": [
        "130645"
      ]
    }
  },
  "_source": ["corekwd","after_keytag","tag_key_url"]
}




GET seokeytagsdata/_search
{
  "query": {
  "regexp": {
    "corekwd.raw": "_+"
  }
    
  }
}


GET seojoindata/_doc/wnRnFnIBcd8f2VExRGIx

GET seojoindata/_count

GET seojoindata/_search
{
  "query": {
    "term": {
      "endSource": {
        "value": "mp.souhu.com "
      }
    }
  }
}

GET seojoindata/_search
{
  "query": {
    "term": {
      "articleId": {
        "value": "5e5638c2e42464a085d7755a"
      }
    }
  }
}


GET seokeytagsdata/_search
{
  "size": 1000,
  "query": {
    "term": {
      "keywords_type": {
        "value": 1
      }
    }
  },
  "_source": ["corekwdId","match_count"]
}



GET seojoindata_backup/_search
{
  "query": {
    "term": {
      "articleId": {
        "value": "5eba799e8fdca9edee88f27c"
      }
    }
  },
  "_source": ["article_summery","article_en"]
}


GET seojoindata/_search
{
  "size": 2000,
  "query": {
    "regexp": {
      "pubdate": "2020-05-*.*"
    }
  },
  "_source": ["article_summery","articleId"]
}





GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist.tagId"
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "exists": {
                "field": "coreKeyWord.corekwdId"
              }
            }
          }
        },
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "term": {
            "seo_category_Id.keyword": {
              "value": "seoc14"
            }
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part_Id": {
      "terms": {
        "field": "seo_part_Id.keyword",
        "size": 50
      },
      "aggs": {
        "top_articles": {
          "top_hits": {
            "sort": [
              {
                "pubdate": {
                  "order": "desc"
                }
              }
            ],
            "size": 10,
            "_source": {
              "includes": [
                "title_en",
                "article_url",
                "articleId",
                "part_Id",
                "part_name",
                "category_type",
                "category_Id",
                "seo_part_url",
                "seo_part_Id",
                "seo_part_name",
                "seo_category_url",
                "seo_category_type",
                "seo_category_Id",
                "article_summery",
                "pubdate"
              ]
            }
          }
        }
      }
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "coreKwdCount",
      "model",
      "clickCount"
    ]
  }
}


GET seojoindata/_search
{
  "size": 10,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist.tagId"
          }
        },
        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "exists": {
                "field": "coreKeyWord.corekwdId"
              }
            }
          }
        },
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "term": {
            "seo_category_Id.keyword": {
              "value": "seoc14"
            }
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        }
      ]
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "coreKeyWord",
      "originalKeyWord",
      "model",
      "part_Id",
      "part_name"
    ]
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ]
}


GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 4000,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist.tagId"
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "bool": {
                "must": [
                  {
                    "exists": {
                      "field": "coreKeyWord.corekwdId"
                    }
                  }
                ]
              }
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "title_en",
      "articleId",
      "article_url"
    ]
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ]
}


GET seojoindata/_count

GET _analyze
{
  "text": "I am so excited to going to the x-school",
  "analyzer": "standard"
}

GET seokeytagsdata/_search
{
  "size":2000,
  "query": {
    "match_all": {}
  },
  "_source": ["corekwdId","match_count"]
}


GET seokeytagsdata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        },
        {
          "regexp": {
            "corekwd.raw": "a.*"
          }
        }
      ]
    }
  },
  "aggs": {
    "min_max_kId": {
      "stats": {
        "field": "corekwdId"
      }
    }
  }
}
GET seojoindata/_search
{
  "query": {
    "term": {
      "articleId": {
        "value": "5ebad8338fdca9edee896934"
      }
    }
  }
}


GET seokeytagsdata_back/_coun

# DELETE seojoindata_back

 

GET seokeytagsdata_back/_mapping

GET seokeytagsdata/_count
 
GET seokeytagsdata/_search
{
  "size":1000,
  "query": {
    "terms": {
      "corekwdId": [
        563996
         
      ]
    }
  },
  "_source": {
    "includes": ["corekwdId","match_count"]
  }
}


GET seojoindata_prefix/_search
{
  "query": {
    "exists": {
      "field": "article_summery"
    }
  },
  "_source": ["article_summery","title_en"]
}


GET seojoindata_prefix/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_summery"
          }
        }
      ]
    }
  }
}


GET seojoindata_prefix/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "articleId": {
              "value": "5eba79c48fdca9edee88f2d8"
            }
          }
        }
      ],
      "should": [
        {
          "match": {
            "article_en": {
              "query": "hiring in texas city",
              "minimum_should_match": "60%"
            }
          }
        }
      ]
    }
  },
  "highlight": {
    "no_match_size": 250,
    "fragment_size": 250,
    "number_of_fragments": 1,
    "pre_tags": [
      ""
    ],
    "post_tags": [
      ""
    ],
    "fields": {
      "article_en": {
        "type": "plain"
      }
    }
  },
  "_source": {
    "includes": ["articleId"]
  }
}

GET seojoindata_prefix/_search
{
  "query": {
    "nested": {
      "path": "coreKeyWord",
      "query": {
        "bool": {
          "must": [
            {
              "exists": {
                "field": "coreKeyWord.corekwd"
              }
            }
          ]
        }
      }
    }
  },
  "_source": ["coreKeyWord","title_en","originalKeyWord"]
}


GET seojoindata_prefix/_search
{
  "size":1000,
  "query": {
    "match_all": {}
  }
}

GET seojoindata_prefix/_search
{
  "size": 500, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_summery"
          }
        },
        {
          "exists": {
            "field": "taglist"
          }
        }
      ]
    }
  },
  "_source": ["article_summery","articleId","coreKeyWord"]
}


GET seojoindata/_search
{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist"
          }
        }
      ]
    }
  },
  "_source": {
    "excludes": ["article_en","article_summery","article_keys"]
  }
}


GET seokeytagsdata/_search
{
  "track_total_hits": true, 
  "size": 2000, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "tag_key_url"
          }
        }
      ]
    }
  },
  "_source": {
    "includes": ["corekwdId","corekwd","tag_key_url"]
  }
}

GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "is_valid": 1
        }
      }
    }
  },
  "aggs": {
    "group_by_category": {
      "terms": {
        "field": "seo_category_type.keyword",
        "size": 100
      },
      "aggs": {
        "group_by_category_url":{
          "terms": {
            "field": "seo_category_url",
            "size": 1
          }
        },
        "group_by_category_Id": {
          "terms": {
            "field": "seo_category_Id.keyword",
            "size": 1
          }
        }
      }
    }
  }
}

GET seojoindata_back/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist.tagId"
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "exists": {
                "field": "coreKeyWord.corekwdId"
              }
            }
          }
        },
        {
          "term": {
            "seo_category_Id.keyword": {
              "value": "seoc14"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_tag_name": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 10
      },
      "aggs": {
        "group_by_tag_url":{
          "terms": {
            "field": "taglist.tag_url",
            "size": 1
          }
        },
        "group_by_tag_Id": {
          "terms": {
            "field": "taglist.tagId",
            "size": 1
          }
        }
      }
    }
  }
}


GET seojoindata_back/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist.tagId"
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "exists": {
                "field": "coreKeyWord.corekwdId"
              }
            }
          }
        },
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "term": {
            "seo_category_Id.keyword": {
              "value": "seoc14"
            }
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part_Id": {
      "terms": {
        "field": "seo_part_Id.keyword",
        "size": 50
      },
      "aggs": {
        "top_articles": {
          "top_hits": {
            "sort": [
              {
                "pubdate": {
                  "order": "desc"
                }
              }
            ],
            "size": 10,
            "_source": {
              "includes": [
                "title_en",
                "taglist", 
                "articleId",
                "part_Id",
                "part_name",
                "article_url", 
                "category_type",
                "category_Id",
                "seo_part_url",
                "seo_part_Id",
                "seo_part_name",
                "seo_category_url",
                "seo_category_type",
                "seo_category_Id",
                "article_summery",
                "pubdate"
              ]
            }
          }
        }
      }
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "coreKwdCount",
      "model",
      "clickCount"
    ]
  }
}

GET seojoindata_back/_search
{
  "size": 0,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "is_valid": 1
        }
      }
    }
  },
  "aggs": {
    "group_by_category_type": {
      "terms": {
        "field": "seo_category_type.keyword",
        "size": 100
      },
      "aggs": {
        "show_category_url":{
          "terms": {
            "field": "seo_category_url",
            "size": 100
          }
        },
        "show_category_Id": {
          "terms": {
            "field": "seo_category_Id.keyword",
            "size": 100
          },
          "aggs": {
            "group_by_part_name": {
              "terms": {
                "field": "seo_part_name.keyword",
                "size": 100
              },
              "aggs": {
                "show_part_url":{
                  "terms": {
                    "field": "seo_part_url",
                    "size": 100
                  }
                },
                "show_part_Id": {
                  "terms": {
                    "field": "seo_part_Id.keyword",
                    "size": 100
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}

GET seojoindata_back/_search
{
  "track_total_hits": true,
  "size": 400,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_en"
          }
        }
      ]
    }
  },
  "_source": {
    "excludes": ["article_en","article_summery","model","fullurl","clickCount","article_keys","title","part_name","pubdate"]
  }
}

GET  seojoindata/_search
{
  "query": {
    "term": {
      "articleId": {
        "value": "5ebae4798fdca9edee89730c"
      }
    }
  }
}

GET  seojoindata/_search
{
  "track_total_hits": true, 
  "size": 200, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "exists": {
            "field": "article_url"
          }
        }
      ]
    }
  }
}

PUT seojoindata_0610
{
  "mappings": {
    "properties": {
      "article_index": {
        "type": "long"
      },
      "articleId": {
        "type": "keyword"
      },
      "article_en": {
        "type": "text",
        "analyzer": "english"
      },
      "article_hot_flag": {
        "type": "long"
      },
      "article_keys": {
        "type": "text",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        }
      },
      "article_summery": {
        "type": "text",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        }
      },
      "article_url": {
        "type": "keyword"
      },
      "category_Id": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      },
      "category_type": {
        "type": "keyword"
      },
      "clickCount": {
        "type": "long"
      },
      "coreKeyWord": {
        "type": "nested",
        "properties": {
          "corekwd": {
            "type": "text",
            "analyzer": "english"
          },
          "corekwdId": {
            "type": "long"
          },
          "corekwd_after": {
            "type": "text",
            "fields": {
              "raw": {
                "type": "keyword",
                "ignore_above": 512
              }
            },
            "analyzer": "english"
          },
          "tag_key_url": {
            "type": "keyword"
          }
        }
      },
      "coreKwdCount": {
        "type": "long"
      },
      "del_flag": {
        "type": "long"
      },
      "doc": {
        "properties": {
          "article_summery": {
            "type": "text",
            "fields": {
              "keyword": {
                "type": "keyword",
                "ignore_above": 256
              }
            }
          }
        }
      },
      "endSource": {
        "type": "keyword"
      },
      "fullurl": {
        "type": "keyword"
      },
      "is_valid": {
        "type": "long"
      },
      "model": {
        "type": "keyword"
      },
      "originalKeyWord": {
        "type": "text",
        "analyzer": "english"
      },
      "otherkwdlist": {
        "type": "nested",
        "properties": {
          "keyId": {
            "type": "long"
          },
          "keyname": {
            "type": "text",
            "fields": {
              "raw": {
                "type": "keyword",
                "ignore_above": 512
              }
            },
            "analyzer": "english"
          },
          "keyname_after": {
            "type": "text",
            "fields": {
              "raw": {
                "type": "keyword",
                "ignore_above": 256
              }
            },
            "analyzer": "english"
          },
          "otherkwdurl": {
            "type": "text",
            "fields": {
              "keyword": {
                "type": "keyword",
                "ignore_above": 256
              }
            }
          },
          "tag_key_url": {
            "type": "keyword"
          }
        }
      },
      "part_Id": {
        "type": "keyword"
      },
      "part_name": {
        "type": "keyword"
      },
      "part_type": {
        "type": "keyword"
      },
      "pubdate": {
        "type": "keyword"
      },
      "relatedKeyWords": {
        "type": "nested",
        "properties": {
          "rtdkwd": {
            "type": "text",
            "analyzer": "english"
          },
          "rtdkwdId": {
            "type": "long"
          },
          "rtdkwd_after": {
            "type": "text",
            "fields": {
              "raw": {
                "type": "keyword",
                "ignore_above": 256
              }
            },
            "analyzer": "english"
          },
          "rtdkwdurl": {
            "type": "keyword"
          }
        }
      },
      "relatedTags": {
        "type": "nested",
        "properties": {
          "tag": {
            "type": "keyword"
          },
          "tagId": {
            "type": "long"
          },
          "tag_after": {
            "type": "text",
            "fields": {
              "raw": {
                "type": "keyword",
                "ignore_above": 256
              }
            },
            "analyzer": "english"
          },
          "tag_url": {
            "type": "keyword"
          }
        }
      },
      "seo_category_Id": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      },
      "seo_category_type": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      },
      "seo_category_url": {
        "type": "keyword"
      },
      "seo_part_Id": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      },
      "seo_part_name": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      },
      "seo_part_url": {
        "type": "keyword"
      },
      "taglist": {
        "properties": {
          "tag": {
            "type": "text",
            "fields": {
              "raw": {
                "type": "keyword"
              }
            }
          },
          "tagId": {
            "type": "long"
          },
          "tag_after": {
            "type": "text",
            "fields": {
              "raw": {
                "type": "keyword",
                "ignore_above": 256
              }
            }
          },
          "tag_key_url": {
            "type": "keyword"
          }
        }
      },
      "title": {
        "type": "text"
      },
      "title_en": {
        "type": "text",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        },
        "analyzer": "english"
      },
      "update": {
        "properties": {
          "_id": {
            "type": "text",
            "fields": {
              "keyword": {
                "type": "keyword",
                "ignore_above": 256
              }
            }
          },
          "_index": {
            "type": "text",
            "fields": {
              "keyword": {
                "type": "keyword",
                "ignore_above": 256
              }
            }
          }
        }
      },
      "weekday": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      }
    }
  }
}

# seojoindata_prefix
PUT seojoindata_backup
{
    "mappings" : {
      "properties" : {
        "articleId" : {
          "type" : "keyword"
        },
        "article_en" : {
          "type" : "text",
          "analyzer" : "english"
        },
        "article_hot_flag" : {
          "type" : "long"
        },
        "article_keys" : {
          "type" : "text",
          "fields" : {
            "raw" : {
              "type" : "keyword"
            }
          }
        },
        "article_summery" : {
          "type" : "text",
          "fields" : {
            "raw" : {
              "type" : "keyword"
            }
          }
        },
        "category_Id" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "category_type" : {
          "type" : "keyword"
        },
        "clickCount" : {
          "type" : "long"
        },
        "coreKeyWord" : {
          "type" : "nested",
          "properties" : {
            "corekwd" : {
              "type" : "text",
              "analyzer" : "english"
            },
            "corekwdId" : {
              "type" : "long"
            },
            "tag_key_url":{
              "type" : "keyword"
            },
            "corekwd_after" : {
              "type" : "text",
              "fields" : {
                "raw" : {
                  "type" : "keyword",
                  "ignore_above" : 512
                }
              },
              "analyzer" : "english"
            }
          }
        },
        "coreKwdCount" : {
          "type" : "long"
        },
        "del_flag" : {
          "type" : "long"
        },
        "endSource" : {
          "type" : "keyword"
        },
        "fullurl" : {
          "type" : "keyword"
        },
        "article_url":{
          "type": "keyword"
        },
        "is_valid" : {
          "type" : "long"
        },
        "model" : {
          "type" : "keyword"
        },
        "originalKeyWord" : {
          "type" : "text",
          "analyzer" : "english"
        },
        "otherkwdlist" : {
          "type" : "nested",
          "properties" : {
            "keyId" : {
              "type" : "long"
            },
            "keyname" : {
              "type" : "text",
              "analyzer" : "english"
            },
            "tag_key_url":{
              "type" : "keyword"
            },
            "keyname_after" : {
              "type" : "text",
              "fields" : {
                "raw" : {
                  "type" : "keyword",
                  "ignore_above" : 256
                }
              },
              "analyzer" : "english"
            }
          }
        },
        "part_Id" : {
          "type" : "keyword"
        },
        "part_name" : {
          "type" : "keyword"
        },
        "part_type" : {
          "type" : "keyword"
        },
        "pubdate" : {
          "type" : "keyword"
        },
        "relatedKeyWords" : {
          "type" : "nested",
          "properties" : {
            "rtdkwd" : {
              "type" : "text",
              "analyzer" : "english"
            },
            "rtdkwdId" : {
              "type" : "long"
            },
            "rtdkwdurl":{
              "type":"keyword"
            },
            "rtdkwd_after" : {
              "type" : "text",
              "fields" : {
                "raw" : {
                  "type" : "keyword",
                  "ignore_above" : 256
                }
              },
              "analyzer" : "english"
            }
          }
        },
        "relatedTags" : {
          "type" : "nested",
          "properties" : {
            "tag" : {
              "type" : "keyword"
            },
            "tagId" : {
              "type" : "long"
            },
            "tag_url":{
              "type" : "keyword"
            },
            "tag_after" : {
              "type" : "text",
              "fields" : {
                "raw" : {
                  "type" : "keyword",
                  "ignore_above" : 256
                }
              },
              "analyzer" : "english"
            }
          }
        },
        "seo_category_url":{
          "type" : "keyword"
        },
        "seo_category_Id" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "seo_category_type" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "seo_part_url":{
          "type" : "keyword"
        },
        "seo_part_Id" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "seo_part_name" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "taglist" : {
          "properties" : {
            "tag" : {
              "type" : "text",
              "fields" : {
                "raw" : {
                  "type" : "keyword"
                }
              }
            },
            "tag_key_url":{
              "type" : "keyword"
            },
            "tagId" : {
              "type" : "long"
            },
            "tag_after" : {
              "type" : "text",
              "fields" : {
                "raw" : {
                  "type" : "keyword",
                  "ignore_above" : 256
                }
              }
            }
          }
        },
        "title" : {
          "type" : "text"
        },
        "title_en" : {
          "type" : "text",
          "fields" : {
            "raw" : {
              "type" : "keyword"
            }
          },
          "analyzer" : "english"
        }
      }
    }
}




GET seokeytagsdata/_search
{
  "track_total_hits": true, 
  "size": 1000, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "keywords_type": {
              "value": 0
            }
          }
        },
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": ["corekwdId","corekwd","match_count"]
  }
}


GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist.tagId"
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "exists": {
                "field": "coreKeyWord.corekwdId"
              }
            }
          }
        },
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "exists": {
            "field": "seo_part_Id"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part": {
      "terms": {
        "field": "seo_part_name.keyword",
        "size": 100
      },
      "aggs": {
        "group_by_part_Id": {
          "terms": {
            "field": "seo_part_Id.keyword",
            "size": 1
          }
        }
      }
    }
  }
}

GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "is_valid": 1
        }
      }
    }
  },
  "aggs": {
    "group_by_category_type": {
      "terms": {
        "field": "seo_category_type.keyword",
        "size": 100
      },
      "aggs": {
        "show_category_Id": {
          "terms": {
            "field": "seo_category_Id.keyword",
            "size": 100
          }
        }
      }
    }
  }
}
# 72715
# 1990
GET seokeytagsdata/_search
{
  "query": {
    "term": {
      "corekwdId": {
        "value": 853202
      }
    }
  }
}


GET seojoindata/_search
{
  "track_total_hits": true, 
  "size": 5000, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist.tagId"
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "bool": {
                "must": [
                  {
                    "exists": {
                      "field": "coreKeyWord.corekwdId"
                    }
                  }
                ]
              }
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "title_en","articleId"
    ]
  }
}


GET seojoindata/_search
{
  "query": {
    "term": {
      "articleId": {
        "value": "5e5cb407ac4d35eb38becc30"
      }
    }
  },
  "_source": ["title_en","fullurl","title"]
}

GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist.tagId"
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "exists": {
                "field": "coreKeyWord.corekwdId"
              }
            }
          }
        },
        {
          "term": {
            "articleId": {
              "value": "5e54d3dbd515cd71ed25571d"
            }
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "term": {
                "coreKeyWord.corekwd_after.raw": {
                  "value": "zirconium orbital diagram"
                }
              }
            }
          }
        }
      ]
    }
  },
  "_source": {
    "excludes": [
      "fullurl",
      "model",
      "title",
      "endSource"
    ]
  },
  "highlight": {
    "no_match_size": 180,
    "number_of_fragments": 4,
    "pre_tags": [
      "<span>"
    ],
    "post_tags": [
      "</span>"
    ],
    "fields": {
      "article_en": {
        "type": "plain"
      }
    }
  }
}

GET seojoindata/_search
{
  "query": {
    "term": {
      "articleId": {
        "value": "5e563ab6e42464a085d77657"
      }
    }
  }
}


GET seojoindata/_search
{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist.tagId"
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "exists": {
                "field": "coreKeyWord.corekwdId"
              }
            }
          }
        },
        {
          "term": {
            "taglist.tag_after.raw": {
              "value": "dme solvent"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "title_en",
      "articleId",
      "part_Id",
      "part_name",
      "category_type",
      "category_Id",
      "seo_part_Id",
      "seo_part_name",
      "seo_category_type",
      "seo_category_Id",
      "article_summery",
      "taglist",
      "pubdate",
      "clickCount"
    ]
  },
  "highlight": {
    "fields": {
      "article_en": {
        "type": "plain",
        "number_of_fragments": 4,
        "pre_tags": [
          "<span>"
        ],
        "post_tags": [
          "</span>"
        ],
        "no_match_size": 180
      },
      "title_en": {
        "type": "plain",
        "no_match_size": 800,
        "pre_tags": [
          "<span>"
        ],
        "post_tags": [
          "</span>"
        ]
      }
    }
  }
}


GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "term": {
                "coreKeyWord.corekwd_after.raw": {
                  "value": "darrow yannet diagram"
                }
              }
            }
          }
        }
      ]
    }
  }
}


GET seojoindata/_mapping

GET seojoindata/_search
{
  "query": {
    "match_all": {}
  },
  "_source": "article_summery"
}

GET seojoindata/_search
{
  "query": {
    "term": {
      "article_en": {
        "value": ""
      }
    }
  }
}

# 5e573f22abe6408d7b0d52b7 
GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "articleId": {
              "value": "5e5fcfe38b83f7500c76786c"
            }
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "term": {
                "coreKeyWord.corekwd_after.raw": {
                  "value": "wss m6c65 a2 dot 4 lv"
                }
              }
            }
          }
        }
      ]
    }
  },
  "_source": {
    "excludes": [
      "fullurl",
      "model",
      "title",
      "endSource"
    ]
  },
  "highlight": {
    "no_match_size": 180,
    "number_of_fragments": 4,
    "pre_tags": [
      "<span>"
    ],
    "post_tags": [
      "</span>"
    ],
    "fields": {
      "article_en": {
        "type": "plain"
      }
    }
  }
}

GET seojoindata/_search
{
  "query": {
    "term": {
      "articleId": {
        "value": "5e5fcfe38b83f7500c76786c"
      }
    }
  }
}

GET seojoindata/_search
{
  "track_total_hits": true, 
  "size": 0, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "taglist.tagId": {
              "value":  1559977
            }
          }
        }
      ]
    }
  }
}


GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "endSource": {
              "value": "www.bbaqw.com"
            }
          }
        },
        {
          "term": {
            "model": {
              "value": "营养强化剂"
            }
          }
        }
      ]
    }
  } 
  
}


GET seokeytagsdata_back/_search
{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "keywords_type": {
              "value": 0
            }
          }
        },
        {
          "exists": {
            "field": "key_title"
          }
        }
      ]
    }
  }
}


GET seokeytagsdata_back/_search
{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "key_title"
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        }
      ]
    }
  }
}


PUT seokeytagsdata
{
    "mappings" : {
      "properties" : {
        "after_keytag" : {
          "type" : "text",
          "fields" : {
            "raw" : {
              "type" : "keyword"
            }
          },
          "analyzer" : "english"
        },
        "clickCount" : {
          "type" : "long"
        },
        "corekwd" : {
          "type" : "text",
          "fields" : {
            "raw" : {
              "type" : "keyword"
            }
          },
          "analyzer" : "english"
        },
        "corekwdId" : {
          "type" : "long"
        },
        "del_flag" : {
          "type" : "long"
        },
        "key_desc" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "key_title" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "keywords_type" : {
          "type" : "long"
        },
        "match_count" : {
          "type" : "long"
        }
      }
    }
}


GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "exists": {
            "field": "seo_part_Id"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part": {
      "terms": {
        "field": "seo_part_name.keyword",
        "size": 100
      },
      "aggs": {
        "group_by_part_Id": {
          "terms": {
            "field": "seo_part_Id.keyword",
            "size": 1
          }
        }
      }
    }
  }
}


GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "seo_part_Id.keyword": "seoc2129_1"
          }
        },
        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        }
        
      ]
    }
  },
  "aggs": {
    "group_by_tags": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 10
      },
      "aggs": {
        "group_by_tagId": {
          "terms": {
            "field": "taglist.tagId",
            "size": 1
          }
        }
      }
    }
  }
}


GET seojoindata/_search
{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "taglist.tag_after.raw": {
              "value": "fda organizational chart"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "title_en",
      "articleId",
      "part_Id",
      "part_name",
      "category_type",
      "category_Id",
      "seo_part_Id",
      "seo_part_name",
      "seo_category_type",
      "seo_category_Id",
      "article_summery",
      "taglist",
      "pubdate",
      "clickCount"
    ]
  },
  "highlight": {
    "fields": {
      "article_en": {
        "type": "plain",
        "number_of_fragments": 4,
        "pre_tags": [
          "<span>"
        ],
        "post_tags": [
          "</span>"
        ],
        "no_match_size": 180
      },
      "title_en": {
        "no_match_size": 800,
        "type": "plain",
        "pre_tags": [
          "<span>"
        ],
        "post_tags": [
          "</span>"
        ]
      }
    }
  }
}

GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "match": {
            "title_en": {
              "query": "2b gel",
              "minimum_should_match": "50%"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "articleId",
      "title_en",
      "clickCount",
      "article_summery",
      "pubdate"
    ]
  },
  "highlight": {
    "fields": {
      "article_en": {
        "type": "plain",
        "number_of_fragments": 4,
        "pre_tags": ["<span>"],
        "post_tags": ["</span>"],
        "no_match_size": 180
      },
      "title_en": {
        "type": "plain",
        "pre_tags": ["<span>"],
        "post_tags": ["</span>"]
      }
    }
  }
}

GET seokeytagsdata/_mapping

GET /seokeytagsdata/_count
GET /seojoindata/_count
GET /seokeytagsdata/_search
{
  "query": {
    "term": {
      "corekwdId": {
        "value":  909227
      }
    }
  }
}



GET /seokeytagsdata/_search
{
  "track_total_hits": true, 
  "query": {
   "bool": {
     "must": [
       {
         "range": {
           "match_count": {
             "gte": 1
           }
         }
       },
       {
         "term": {
           "keywords_type": {
             "value": 1
           }
         }
       }
        
     ]
   }
  }
}

GET /seojoindata/_mapping
GET seojoindata_back/


GET seojoindata/_search
{
  "track_total_hits": true,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist"
          }
        },
        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "terms": {
            "seo_part_Id.keyword": [
              "seoc2129"
            ]
          }
        }
      ]
    }
  }
}

# 查询文章关键词
GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "articleId": {
              "value": "5e5efec3bdee44a1d6e79df3"
            }
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "bool": {
                "must": [
                  {
                    "exists": {
                      "field": "coreKeyWord.corekwdId"
                    }
                  }
                ]
              }
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "coreKeyWord"
    ]
  }
}


GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "seo_part_Id.keyword": "seoc25_2"
          }
        },
        {
          "exists": {
            "field": "title_en"
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_tags": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 10
      },
      "aggs": {
        "group_by_tagId": {
          "terms": {
            "field": "taglist.tagId",
            "size": 1
          }
        }
      }
    }
  }
}

GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "articleId": {
              "value": "5e5efec3bdee44a1d6e79df3"
            }
          }
        },
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "term": {
                "coreKeyWord.corekwd_after.raw": {
                  "value": "zinc oxide nanoparticles research paper"
                }
              }
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "coreKeyWord",
      "otherkwdlist"
    ]
  },
  "highlight": {
    "fields": {
      "article_en": {
        "type": "plain",
        "number_of_fragments": 4,
        "pre_tags": [
          "<span>"
        ],
        "post_tags": [
          "</span>"
        ],
        "no_match_size": 180
      }
    }
  }
}






GET seojoindata/_search
{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "endSource": {
              "value": "peptide.org.cn"
            }
          }
        },
        {
          "term": {
            "part_Id": {
              "value": "c1522"
            }
          }
        }
      ]
    }
  }
}





GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "articleId": {
              "value": "5e4f90f9d515cd752334603f"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "excludes": [
      "fullurl",
      "model",
      "title",
      "endSource"
    ]
  }
}

GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 10,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "taglist.tagId": {
              "value": 891305
            }
          }
        }
      ]
    }
  }
}

GET seojoindata/_search
{
  "query": {
    "term": {
      "taglist.tag.raw": "fda organizational chart"
    }
  },
  "_source": [
    "coreKeyWord",
    "originalKeyWord",
    "articleId"
  ]
}

# 查询关键词
GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "seo_part_Id.keyword": "seoc1431"
          }
        },
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_tags": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 10
      },
      "aggs": {
        "group_by_tagId": {
          "terms": {
            "field": "taglist.tagId",
            "size": 1
          }
        }
      }
    }
  }
}

GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "seo_part_Id.keyword": "seoc1420"
          }
        },
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_tags": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 10
      },
      "aggs": {
        "group_by_tagId": {
          "terms": {
            "field": "taglist.tagId",
            "size": 1
          }
        }
      }
    }
  }
}

GET seojoindata/_search
{
  "track_total_hits": true,
  "from": 0,
  "size": 20,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "seo_part_Id.keyword": "seoc1420"
        }
      },
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        },
        {
          "exists": {
            "field": "taglist.tag"
          }
        }
      ]
    }
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ],
  "_source": {
    "excludes": [
      "article_en",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "model",
      "coreKeyWord",
      "clickCount"
    ]
  }
}



GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "taglist.tag_after.raw": {
              "value": "alendronate used for"
            }
          }
        }
      ]
    }
  },
  "_source": "taglist"
}


GET seojoindata/_search
{
  "size": 200,
  "query": {
    "bool": {
      "should": [
        {
          "match": {
            "title_en": {
              "query": "alendronate used for",
              "analyzer": "english",
              "minimum_should_match": "80%"
            }
          }
        },
        {
          "match": {
            "article_en": {
              "query": "alendronate used for",
              "analyzer": "english",
              "minimum_should_match": "80%"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "coreKeyWord",
      "fullurl",
      "article_keys",
      "article_summery",
      "endSource",
      "model",
      "title"
    ]
  }
}

GET seojoindata/_search
{
  "size": 200,
  "query": {
    "bool": {
      "should": [
        {
          "match": {
            "title_en": {
              "query": "alendronate used for",
              "analyzer": "english",
              "minimum_should_match": "80%"
            }
          }
        },
        {
          "match_phrase": {
            "title_en": {
              "query": "alendronate used for",
              "analyzer": "english",
              "slop": 5
            }
          }
        },
        {
          "match_phrase": {
            "article_en": {
              "query": "alendronate used for",
              "analyzer": "english",
              "slop": 3
            }
          }
        },
        {
          "match": {
            "article_en": {
              "query": "alendronate used for",
              "analyzer": "english",
              "minimum_should_match": "80%"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "coreKeyWord",
      "fullurl",
      "article_keys",
      "article_summery",
      "endSource",
      "model",
      "title"
    ]
  }
}

GET seojoindata/_search
{
  "query": {
    "match_all": {}
  }
}


GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "articleId": {
              "value": "5e57410cabe6408d7b0d53bd"
            }
          }
        }
      ]
    }
  }
}


GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist"
          }
        },
        {
          "term": {
            "taglist.tag.raw": {
              "value": "1 bromopropane"
            }
          }
        }
      ]
    }
  }
}

GET seojoindata/_search
{
  "query": {
    "term": {
      "articleId": {
        "value": "5e5fd6348b83f7500c767d56"
      }
    }
  }
}
# 5e549e01d515cd71ed253be3
# 5e549e01d515cd71ed253be3

# PD-L1/PD-1 axis in GBM

GET seojoindata/_search
{"query": {"term": {"articleId": "5ed0beebf0d4878c0ae54101"}}, "_source": ["articleId","title_en"]}

#{"query": {"term": {"trans_date": {"value": "2020-06-01"}}}}

POST seojoindata/_update_by_query
{
  "script": {
    "source": "ctx._source.title_en='PD-L1/PD-1 axis in GBM';",
    "lang": "painless"
  },
  "query": {
    "term": {
      "articleId": "5ed0beebf0d4878c0ae54101"
    }
  }
}

# 239500
POST seokeytagsdata/_update_by_query
{
  "script": {
    "source": "ctx._source.match_count=0;",
    "lang": "painless"
  },
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "corekwdId": {
              "value": 21741
            }
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        }
      ]
    }
  }
}


GET seokeytagsdata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_click": {
      "top_hits": {
        "size": 10,
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ],
        "_source": {
          "includes": [
            "corekwdId",
            "corekwd",
            "clickCount"
          ]
        }
      }
    }
  }
}




GET seokeytagsdata/_search
{
  "track_total_hits": true, 
  "query": {
    "term": {
      "corekwd.raw": {
        "value": "alendronate used for"
      }
    }
  }
}




GET seokeytagsdata/_search
{
  "query": {
    "term": {
      "match_count": {
        "value": 0
      }
    }
  },
  "_source": ["keywords_type","match_count"]
}

#  查询tag词
GET seokeytagsdata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        },
        {
          "terms": {
            "corekwd.raw": [
              "benadryl cream ingredients"
            ]
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "corekwd",
      "corekwdId",
      "after_keytag",
      "keywords_type",
      "clickCount",
      "match_count"
    ]
  }
}

GET seojoindata_back/_search
{
  "query": {
    "match_all": {}
  },
  "_source": {
    "includes": ["taglist","coreKeyWord","otherkwdlist","originalKeyWord"]
  }
}

GET seojoindata_back/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "exists": {
                "field": "coreKeyWord.corekwd_after"
              }
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": ["taglist","coreKeyWord","otherkwdlist","originalKeyWord"]
  }
}


GET seokeytagsdata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        },
         {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_click":{
      "top_hits": {
        "size": 10,
        "sort": [
        {
          "clickCount": {
            "order": "desc"
          }
        }
        ],
        "_source": {
          "includes": ["corekwdId","corekwd","clickCount"]
        }
      }
    }
  }
}

# 对tag词进行聚合 统计每个词的数量
GET /seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "term": {
            "seo_category_Id.keyword": {
              "value": "seoc14"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_tag_name": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 10
      },
      "aggs": {
        "group_by_tag_Id": {
          "terms": {
            "field": "taglist.tagId",
            "size": 1
          }
        }
      }
    }
  }
}

GET /seojoindata/_search
{
  "query": {
    "match_all": {}
  },
  "_source": "clickCount"
}

GET /seojoindata/_search
{
  "track_total_hits": true, 
  "size": 0,
  "aggs": {
    "group_by_tag_name": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 5000
      }
    }
  }
}

#  
GET /seojoindata/_search
{
  "track_total_hits": true, 
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist"
          }
        },
        {
          "term": {
            "taglist.tag.raw": {
              "value": "dollywood"
            }
          }
        }
      ]
    }
  }
}


GET seojoindata/_search
{
  "track_total_hits": true,
  "query": {
    "bool": {
      "must": [
        {
          "nested": {
            "path": "coreKeyWord",
            "query": {
              "exists": {
                "field": "coreKeyWord.corekwd"
              }
            }
          }
        }

      ]
    }
  }
}

GET seojoindata/_search
{
  "track_total_hits": true,
  "query": {
    
    "nested": {
      "path": "coreKeyWord",
      "query": {
        "bool": {
          "must": [
            {
              "term": {
                "is_valid": {
                  "value": 1
                }
              }
            },
            {
              "exists": {
                "field": "article_summery"
              }
            },
            {
              "exists": {
                "field": "coreKeyWord.corekwd"
              }
            }
          ]
        }
      }
    }
  }
}

GET seojoindata/_search
{
  "query": {
    "match_all": {}
  }
}

GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "match": {
            "taglist.tag": {
              "query": "",
              "minimum_should_match": "50%"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_tag_name": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 10
      },
      "aggs": {
        "group_by_tag_Id": {
          "terms": {
            "field": "taglist.tagId",
            "size": 1
          }
        }
      }
    }
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ]
}

GET seokeytagsdata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        },
        {
          "regexp": {
            "corekwd.raw": "a.*"
          }
        },
         {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_click":{
      "top_hits": {
        "size": 10,
        "sort": [
        {
          "clickCount": {
            "order": "desc"
          }
        }
        ],
        "_source": {
          "includes": ["corekwdId","corekwd","clickCount"]
        }
      }
    }
  }
}


GET seokeytagsdata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "filter": {
        "prefix": {
          "corekwd.raw": "a"
        }
      }, 
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 0
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_click":{
      "top_hits": {
        "size": 10,
        "sort": [
        {
          "clickCount": {
            "order": "desc"
          }
        }
        ]
      }
    }
  }
}


POST seojoindata/_update_by_query
{
  "script": {
    "source": "ctx._source.seo_part_name='Medicines Company News';",
    "lang": "painless"
  },
  "query": {
    "term": {
      "seo_part_Id.keyword": {
        "value": "seoc11_1"
      }
    }
  }
}

GET seojoindata/_search
{
  "query": {
    "bool": {
      "filter": {
        "term": {
          "seo_part_Id.keyword": "seoc11_1"
        }
      },
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        },
        {
          "exists": {
            "field": "taglist"
          }
        }
      ]
    }
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ],
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "model",
      "coreKeyWord",
      "clickCount"
    ]
  }
}

GET seojoindata/_search
{
  "query": {
   "term": {
      "seo_part_Id.keyword": {
        "value": "seoc11_1"
      }
    }
  }
}


GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "exists": {
            "field": "seo_part_Id"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part": {
      "terms": {
        "field": "seo_part_name.keyword",
        "size": 50
      },
      "aggs": {
        "group_by_part_Id": {
          "terms": {
            "field": "seo_part_Id.keyword",
            "size": 1
          }
        }
      }
    }
  }
}

GET seojoindata/_search
{
  "query": {
    "match_all": {}
  }
}

GET seojoindata/_search
{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        },
        {
          "match": {
            "title_en": {
              "query": "salem zoom care",
              "minimum_should_match": "50%"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "articleId",
      "title_en",
      "clickCount",
      "article_summery",
      "pubdate"
    ]
  },
  "highlight": {
    "pre_tags": [
      "<span>"
    ],
    "post_tags": [
      "</span>"
    ],
    "fields": [{
      "title_en": {
        "type": "plain"
      }
    },
    {
      "article_en": {
        "type":"plain"
      }
    }
    ]
  }
}
GET /seokeytagsdata/_search
{
  "query": {
    "bool": {
      "filter": {
        "term": {
          "keywords_type": 1
        }
      },
      "must": [
        {
          "terms": {
            "corekwdId": [
              131136,
              151308
            ]
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "corekwdId",
      "corekwd",
      "match_count"
    ]
  }
}

GET /seokeytagsdata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        },
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_click": {
      "top_hits": {
        "size": 10,
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ]
      }
    }
  }
}

 

GET /seokeytagsdata/_search
{
  "size": 7,
  "query": {
    "bool": {
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        },
        {
          "match": {
            "after_keytag": {
              "query": "3 inch polyiso insulation r value",
              "minimum_should_match": "60%"
            }
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        }
      ],
      "must_not": [
        {
          "term": {
            "after_keytag.raw": {
              "value": "3 inch polyiso insulation r value"
            }
          }
        }
      ]
    }
  }
}


{
  "query": {
    "bool": {
      "must_not": [
        {
          "term": {
            "corekwd.raw": {
              "value": "VALUE"
            }
          }
        }
      ]
    }
  }
}

GET seojoindata/_search
POST seojoindata/_update_by_query
{
   "script": {
    "source": "ctx._source.article_summery='''Paint knowledge how about Akzo Nobel Powder Coating Recommended introduction: powder coating is a kind of coating with different form from general coating, which is in powder form.''';ctx._source.article_en='''Paint knowledge how about Akzo Nobel Powder Coating Recommended introduction: powder coating is a kind of coating with different form from general coating, which is in powder form. <br/><br/>It is a new type of coating, because of its own advantages and more and more known by people. <br/><br/>Let's introduce Akzo Nobel Powder coating. <br/><br/>Akzo Nobel Powder coating is a cost-effective coating solution, which can be applied to different kinds of products. <br/><br/>After the treatment of static electricity and fire baking, a tough and durable coating surface will be formed, with the least impact on the environment. <br/><br/>Since the introduction of this technology, powder coating has been able to continue to maintain the coating "I want to see you" I want to see you "I want to see you" I want to see you "I want to see you''';",
    "lang": "painless"
  },
  "query": {
    "term": {
      "articleId": {
        "value": "5e573a51abe6408d7b0d5036"
      }
    }
  }
}

{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "term": {
            "seo_category_Id.keyword": {
              "value": "seoc14"
            }
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part_Id": {
      "terms": {
        "field": "seo_part_Id.keyword",
        "size": 30
      },
      "aggs": {
        "top_articles": {
          "top_hits": {
            "sort": [
              {
                "pubdate": {
                  "order": "desc"
                }
              }
            ],
            "size": 10,
            "_source": {
              "includes": [
                "title_en",
                "articleId",
                "part_Id",
                "part_name",
                "category_type",
                "category_Id",
                "seo_part_Id",
                "seo_part_name",
                "seo_category_type",
                "seo_category_Id",
                "article_summery",
                "pubdate"
              ]
            }
          }
        }
      }
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "coreKwdCount",
      "model",
      "clickCount"
    ]
  }
}

GET /seojoindata/_search
{
  "track_total_hits": true,
  "size": 10,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "seo_part_Id.keyword": "seoc1113"
        }
      },
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        },
        {
          "exists": {
            "field": "taglist"
          }
        }
      ]
    }
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ],
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "model",
      "coreKeyWord",
      "clickCount"
    ]
  }
}


GET seokeytagsdata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 0
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_click": {
      "top_hits": {
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ],
        "size": 15
      }
    }
  }
}

GET seokeytagsdata/_search
{
  "track_total_hits": true, 
  "size": 10,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "keywords_type": {
              "value": 0
            }
          }
        },
        {
          "exists": {
            "field": "key_title"
          }
        }
      ]
    }
  }
}

POST seokeytagsdata/_update_by_query
{
  "script": {
    "source": "ctx._source.clickCount=0;",
    "lang": "painless"
  },
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "corekwdId": {
              "value": 1933
            }
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        }
      ]
    }
  }
}

GET seokeytagsdata/_search
{
  "size": 0,
  "query": {
    "constant_score": {
      "filter": {
        "range": {
          "keywords_type": {
            "gte": 0
          }
        }
      },
      "boost": 1.2
    }
  },
  "aggs": {
    "group_by_match_count": {
      "terms": {
        "field": "match_count",
        "size": 15
      },
      "aggs": {
        "top_match": {
          "top_hits": {
            "sort": [
              {
                "match_count": {
                  "order": "desc"
                }
              }
            ],
            "size": 15
          }
        }
      }
    }
  }
}


{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "corekwdId": {
              "value": 954773
            }
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        }
      ]
    }
  }
}


GET seojoindata/_mapping/

GET seojoindata/_search
{
  "size":1000,
  "query": {
    "match_all": {}
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ], 
  "_source": {
    "includes": ["pubdate"]
  }
}







GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "exists": {
            "field": "seo_part_Id"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part": {
      "terms": {
        "field": "seo_part_name.keyword",
        "size": 50
      },
      "aggs": {
        "group_by_part_Id": {
          "terms": {
            "field": "seo_part_Id.keyword",
            "size": 1
          }
        }
      }
    }
  }
}



POST seojoindata/_update_by_query
"script": {
    "source": "ctx._source.seo_part_Id='seoc2115_1';",
    "lang": "painless"
  },
GET seojoindata/_search
{
  
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "seo_category_Id.keyword": {
              "value": "seoc21"
            }
          }
        },
        {
          "term": {
            "seo_part_name.keyword": {
              "value": "Anticaking Agent Knowledge"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": ["seo_category_Id","seo_part_Id","seo_part_name"]
  }
}


POST seojoindata/_update_by_query
{
  "script": {
    "source": "ctx._source.clickCount=0;",
    "lang": "painless"
  },
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "seo": {
              "value": "5e5c97a2ba25c1e16609c6c8"
            }
          }
        }
      ]
    }
  }
}


GET seojoindata/_search
{
  "track_total_hits": true, 
  "query": {
    "term": {
      "seo_part_Id.keyword": {
        "value": "seoc11_2"
      }
    }
  }
}

GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "articleId": {
              "value": "5e5c97a2ba25c1e16609c6c8"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": ["articleId","clickCount","coreKeyWord","otherkwdlist"]
  }
}

GET seojoindata/_search
{
  "size": 10,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "term": {
            "seo_category_Id.keyword": {
              "value": "seoc14"
            }
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        }
      ]
    }
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ], 
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "coreKeyWord",
      "originalKeyWord",
      "model",
      "part_Id",
      "part_name"
    ]
  }
}

{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "exists": {
            "field": "seo_part_Id"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part": {
      "terms": {
        "field": "seo_part_name.keyword",
        "size": 50
      },
      "aggs": {
        "group_by_part_Id": {
          "terms": {
            "field": "seo_part_Id.keyword",
            "size": 1
          }
        }
      }
    }
  }
}


{
  "track_total_hits": true,
  "size": 10,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "seo_part_Id.keyword": "seoc1420"
        }
      },
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        },
        {
          "exists": {
            "field": "taglist"
          }
        }
      ]
    }
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ],
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "model",
      "coreKeyWord",
      "clickCount"
    ]
  }
}


{
  "size": 1,
  "query": {
    "bool": {
      "should": [
        {
          "term": {
            "seo_category_Id.keyword": {
              "value": "seoc1420"
            }
          }
        },
        {
          "term": {
            "seo_part_Id.keyword": {
              "value": "seoc1420"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "category_Id",
      "category_type",
      "part_Id",
      "part_name",
      "seo_category_Id",
      "seo_category_type",
      "seo_part_Id",
      "seo_part_name"
    ]
  }
}

{
  "track_total_hits": true,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        },
        {
          "match": {
            "title_en": {
              "query": "375 abi lane bath pa",
              "minimum_should_match": "35%"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "articleId",
      "title_en",
      "clickCount",
      "article_summery",
      "pubdate"
    ]
  },
  "highlight": {
    "pre_tags": [
      "<span>"
    ],
    "post_tags": [
      "</span>"
    ],
    "fields": {
      "title_en": {
        "type": "plain"
      }
    }
  }
}


GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "term": {
            "seo_category_Id.keyword": {
              "value": "seoc14"
            }
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part_Id": {
      "terms": {
        "field": "seo_part_Id.keyword",
        "size": 30
      },
      "aggs": {
        "top_articles": {
          "top_hits": {
            "sort": [
              {
                "pubdate": {
                  "order": "desc"
                }
              }
            ],
            "size": 10,
            "_source": {
              "includes": [
                "title_en",
                "articleId",
                "part_Id",
                "part_name",
                "category_type",
                "category_Id",
                "seo_part_Id",
                "seo_part_name",
                "seo_category_type",
                "seo_category_Id",
                "article_summery",
                "pubdate"
              ]
            }
          }
        }
      }
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "coreKwdCount",
      "model",
      "clickCount"
    ]
  }
}

{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "endSource": {
              "value": "www.zyzhan.com"
            }
          }
        },
        {
          "term": {
            "model": {
              "value": "药机词典"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": ["category_Id","category_type","seo_category_Id","seo_category_type","seo_part_Id","endSource","model","seo_part_name"]
  }
}

GET seojoindata/_search
{
  "size": 10,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "term": {
            "seo_category_Id.keyword": {
              "value": "seoc14"
            }
          }
        },
        {
          "exists": {
            "field": "article_en"
          }
        }
      ]
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "coreKeyWord",
      "originalKeyWord",
      "model",
      "part_Id",
      "part_name"
    ]
  }
}



{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "filter": {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
      }
    }
  },
  "aggs": {
    "group_by_category": {
      "terms": {
        "field": "seo_category_type.keyword",
        "size": 100
      }
    }
  }
}



POST seojoindata/_update_by_query
{
  "script": {
    "source": "ctx._source.seo_part_name='Feed Industry News';",
    "lang": "painless"
  },
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "endSource": {
              "value": "www.ew9z.com"
            }
          }
        },
        {
          "term": {
            "model": {
              "value": "禽蛋肉类"
            }
          }
        }
      ]
    }
  }
}

{
  "size": 0,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "is_valid": 1
        }
      }
    }
  },
  "aggs": {
    "group_by_category_type": {
      "terms": {
        "field": "seo_category_type.keyword",
        "size": 100
      },
      "aggs": {
        "show_category_Id": {
          "terms": {
            "field": "seo_category_Id.keyword",
            "size": 100
          },
          "aggs": {
            "group_by_part_name": {
              "terms": {
                "field": "seo_part_name.keyword",
                "size": 100
              },
              "aggs": {
                "show_part_Id": {
                  "terms": {
                    "field": "seo_part_Id.keyword",
                    "size": 100
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}


DELETE seojoindata/_doc/0cc6e0c5-755d-11ea-a4b5-00cfe03abc06



GET seojoindata/_search
{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "articleId": {
              "value": "5e573a51abe6408d7b0d5036"
            }
          }
        }
      ]
    }
  }
}

GET seojoindata/_search
{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "category_Id.keyword": {
              "value": "c15"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": ["articleId","article_en"]
  }
}


GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 400,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_en"
          }
        },
        {
          "exists": {
            "field": "ar"
          }
        }
      ]
    }
  },
  "_source": {
    "includes": ["article_en"]
  }
}

GET seojoindata/_search
{
  "query": {
    "term": {
      "articleId": {
        "value": "5e7b37f064db6da8125687bb"
      }
    }
  }
}



# DELETE seokeytagsdata

GET seokeytagsdata/_count


GET seojoindata/_search
{
  "track_total_hits": true, 
  "query": {
   "regexp": {
     "pubdate": "201[0-9]{1}年.*"
   }
  },
  "_source": {
    "includes": ["pubdate","article_summery"]
  }
}


GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "is_valid": 1
        }
      }
    }
  }, 
  "aggs": {
    "group_by_category": {
      "terms": {
        "field": "category_type",
        "size": 100
      },
      "aggs": {
        "group_by_category_Id": {
          "terms": {
            "field": "category_Id.keyword",
            "size": 1
          }
        }
      }
    }
  }
}


{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "term": {
            "category_Id.keyword": {
              "value": "c14"
            }
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part_Id": {
      "terms": {
        "field": "part_Id",
        "size": 30
      },
      "aggs": {
        "top_articles": {
          "top_hits": {
            "sort": [
              {
                "pubdate": {
                  "order": "desc"
                }
              }
            ],
            "size": 10,
            "_source": {
              "includes": [
                "title_en",
                "articleId",
                "part_Id",
                "part_name",
                "category_type",
                "category_Id",
                "article_summery",
                "pubdate"
              ]
            }
          }
        }
      }
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "coreKwdCount",
      "model",
      "clickCount"
    ]
  }
}


{
  "size": 1,
  "query": {
    "bool": {
      "should": [
        {
          "term": {
            "category_Id.keyword": {
              "value": "c25"
            }
          }
        },
        {
          "term": {
            "part_Id": {
              "value": "c25"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "category_Id",
      "category_type",
      "part_Id",
      "part_name"
    ]
  }
}


{
  "size": 0,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "is_valid": 1
        }
      }
    }
  },
  "aggs": {
    "group_by_category_type": {
      "terms": {
        "field": "category_type",
        "size": 100
      },
      "aggs": {
        "show_category_Id": {
          "terms": {
            "field": "category_Id.keyword",
            "size": 100
          },
          "aggs": {
            "group_by_part_name": {
              "terms": {
                "field": "part_name",
                "size": 100
              },
              "aggs": {
                "show_part_Id": {
                  "terms": {
                    "field": "part_Id",
                    "size": 100
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}



{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "part_Id"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part": {
      "terms": {
        "field": "part_name",
        "size": 30
      },
      "aggs": {
        "group_by_part_Id": {
          "terms": {
            "field": "part_Id",
            "size": 1
          }
        }
      }
    }
  }
}

GET seokeytagsdata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 0
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_click": {
      "top_hits": {
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ],
        "size": 20
      }
    }
  }
}


{
  "size": 1,
  "query": {
    "bool": {
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        },
        {
          "term": {
            "corekwdId": {
              "value": 996
            }
          }
        }
      ]
    }
  }
}


{
  "size": 10,
  "query": {
    "bool": {
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 0
            }
          }
        },
        {
          "match": {
            "corekwd": {
              "query": "1 2 benzenedithiol",
              "analyzer": "english",
              "minimum_should_match": "70%"
            }
          }
        }
      ]
    }
  }
}








{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "keywords_type": {
              "value": 0
            }
          }
        },
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_click": {
      "top_hits": {
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ],
        "size": 10
      }
    }
  }
}


{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        },
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_click": {
      "top_hits": {
        "size": 20,
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ]
      }
    }
  }
}


{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_click": {
      "top_hits": {
        "size": 10,
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ]
      }
    }
  }
}


{
  "track_total_hits": true,
  "query": {
    "match_all": {}
  }
}


GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "match": {
            "title_en": {
              "query": "1 4 dichlorobenzene",
              "minimum_should_match": "30%"
            }
          }
        }
      ],
      "should": [
        {
          "match_phrase": {
            "title_en": {
              "query": "1 4 dichlorobenzene",
              "slop": 3
            }
          }
        },
        {
          "match": {
            "article_en": {
              "query": "1 4 dichlorobenzene",
              "minimum_should_match": "60%"
            }
          }
        },
        {
          "match_phrase": {
            "article_en": {
              "query": "1 4 dichlorobenzene",
              "slop": 3
            }
          }
        }
      ]
    }
  }
}



{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "category_Id.keyword": {
              "value": "c21"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "top_keyword": {
      "top_hits": {
        "sort": [
          {
            "coreKwdCount": {
              "order": "desc"
            }
          }
        ],
        "size": 15,
        "_source": {
          "includes": [
            "category_type",
            "category_Id",
            "pubdate",
            "coreKeyWord"
          ]
        }
      }
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "model",
      "article_summery",
      "part_Id",
      "part_name",
      "title_en",
      "articleId",
      "category_type",
      "clickCount"
    ]
  }
}


{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "category_Id.keyword": {
              "value": "c21"
            }
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part_Id": {
      "terms": {
        "field": "part_Id",
        "size": 100
      },
      "aggs": {
        "top_articles": {
          "top_hits": {
            "sort": [
              {
                "pubdate": {
                  "order": "desc"
                }
              }
            ],
            "size": 10,
            "_source": {
              "includes": [
                "title_en",
                "articleId",
                "part_Id",
                "part_name",
                "category_type",
                "category_Id",
                "article_summery",
                "pubdate"
              ]
            }
          }
        }
      }
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "coreKwdCount",
      "model",
      "clickCount"
    ]
  }
}

{
  "size": 0,
  "aggs": {
    "group_by_category": {
      "terms": {
        "field": "category_type",
        "size": 100
      },
      "aggs": {
        "group_by_category_Id": {
          "terms": {
            "field": "category_Id.keyword",
            "size": 1
          }
        }
      }
    }
  }
}

GET seokeytagsdata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "keywords_type": {
              "value": 0
            }
          }
        },
        {
          "range": {
            "match_count": {
              "gte": 6
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "top_click": {
      "top_hits": {
        "size": 20,
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          },
          {
            "match_count": {
              "order": "desc"
            }
          }
        ]
      }
    }
  }
}

GET /seojoindata/_search





{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "articleId": {
              "value": "5e572270abe6408d7b0d43cf"
            }
          }
        },
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        }
      ]
    }
  },
  "_source": {
    "excludes": [
      "otherkwdlist",
      "fullurl",
      "model",
      "title",
      "endSource"
    ]
  }
}


{
  "size": 0,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "part_Id": "c2129"
        }
      },
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_tags": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 20
      },
      "aggs": {
        "group_by_tagId": {
          "terms": {
            "field": "taglist.tagId",
            "size": 1
          }
        }
      }
    }
  }
}





GET /_cat/segments

DELETE /_search/scroll/_all
{
    "aggs" : {
        "t_shirts" : {
            "filter" : { "term": { "type": "t-shirt" } },
            "aggs" : {
                "avg_price" : { "avg" : { "field" : "price" } }
            }
        }
    }
}


GET seojoindata/_search
{
  "size": 0, 
  "query": {
    "bool": {
      "filter": {
        "term": {
          "is_valid": 1
        }
      }
    }
  },
  "aggs": {
    "group_by_ct_type": {
      "terms": {
        "field": "category_Id.keyword",
        "size": 20
      },
      "aggs": {
        "group_by_part": {
          "terms": {
            "field": "part_name",
            "size": 30
          },
          "aggs": {
            "group_by_part_Id": {
              "terms": {
                "field": "part_Id",
                "size": 30
              }
            }
          }
        }
      }
    }
  }
}


GET seojoindata/_search
{
  "size": 15,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "is_valid": 1
        }
      }
    }
  },
  "sort": [
    {
      "clickCount": {
        "order": "desc"
      }
    }
  ],
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "coreKeyWord",
      "originalKeyWord",
      "model",
      "part_Id",
      "part_name"
    ]
  }
}

GET seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "is_valid": 1
        }
      }
    }
  },
  "aggs": {
    "group_by_category_type": {
      "terms": {
        "field": "category_type",
        "size": 100
      },
      "aggs": {
        "show_category_Id": {
          "terms": {
            "field": "category_Id.keyword",
            "size": 100
          },
          "aggs": {
            "group_by_part_name": {
              "terms": {
                "field": "part_name",
                "size": 100
              },
              "aggs": {
                "show_part_Id": {
                  "terms": {
                    "field": "part_Id",
                    "size": 100
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}

{
  "query": {
    "term": {
      "is_valid": {
        "value": 1
      }
    }
  }
}

GET seojoindata/_search
{
  "size": 10, 
  "query": {
    "bool": {
      "filter": {
        "term": {
          "is_valid": 1
        }
      },
      "must": [
        {
          "term": {
            "category_Id.keyword": {
              "value": "c14"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": ["category_Id","category_type","part_Id","part_name"]
  }
}

GET seojoindata/_search
{
  "size": 10,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "term": {
            "category_Id.keyword": {
              "value": "c11"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "coreKeyWord",
      "originalKeyWord",
      "model",
      "part_Id",
      "part_name"
    ]
  }
}

GET seojoindata/_search
{
  "track_total_hits": true, 
  "size": 10, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist"
          }
        },
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": ["taglist","title_en"]
  }
}


GET seojoindata/_search
{
  "size": 200, 
  "query": {
    "bool": {
      "should": [
        {
          "match": {
            "title_en": {
              "query": "1.5 ml eppendorf tubes",
              "analyzer": "english",
              "minimum_should_match": "60%"
            }
          }
        },
        {
          "match_phrase": {
            "title_en": {
              "query": "1.5 ml eppendorf tubes",
              "analyzer": "english", 
              "slop": 5
            }
          }
        },
        {
          "match_phrase": {
            "article_en": {
              "query": "1.5 ml eppendorf tubes",
              "analyzer": "english", 
              "slop": 10
            }
          }
        },
        {
          "match": {
            "article_en": {
              "query": "1.5 ml eppendorf tubes",
              "analyzer": "english",
              "minimum_should_match": "60%"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "excludes": ["article_en","otherkwdlist","coreKeyWord","fullurl","article_keys","article_summery","endSource","model","title",""]
  }
}


GET seokeytagsdata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "range": {
            "match_count": {
              "gte": 5
            }
          }
        },
        {
          "regexp": {
            "corekwd.raw": "f.*"
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        }
      ],
      "must_not": [
        {
          "term": {
            "after_keytag.raw": {
              "value": "fda organizational chart"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_click": {
      "top_hits": {
        "size": 10,
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ],
        "_source": {
          "includes": [
            "corekwdId",
            "corekwd",
            "match_count"
          ]
        }
      }
    }
  }
}

GET seojoindata/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "taglist.tag_after.raw": {
              "value": "fda organizational chart"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "title_en",
      "articleId",
      "part_Id",
      "part_name",
      "category_type",
      "category_Id",
      "seo_part_Id",
      "seo_part_name",
      "seo_category_type",
      "seo_category_Id",
      "article_summery",
      "taglist",
      "pubdate",
      "clickCount"
    ]
  },
  "highlight": {
    "no_match_size": 180,
    "number_of_fragments": 3,
    "pre_tags": [
      "<span>"
    ],
    "post_tags": [
      "</span>"
    ],
    "fields": {
      "article_en": {
        "type": "plain"
      }
    }
  }
}   

GET /seojoindata/_search
{
  "query": {
    "term": {
      "FIELD": {
        "value": "VALUE"
      }
    }
  },
  "highlight": {
    "no_match_size": 180,
    "number_of_fragments": 3,
    "pre_tags": [
      "<span>"
    ],
    "post_tags": [
      "</span>"
    ],
    "fields": {
      "article_en": {
        "type": "plain"
      }
    }
  }
}


# 关键词能够匹配上的文章数量
GET /seojoindata/_search
{
  "track_total_hits": true,
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "match": {
            "title_en": {
              "query": "0 dibromobenzene",
              "minimum_should_match": "60%"
            }
          }
        }
      ],
      "should": [
        {
          "match_phrase": {
            "title_en": {
              "query": "0 dibromobenzene",
              "slop": 3
            }
          }
        },
        {
          "match": {
            "article_en": {
              "query": "0 dibromobenzene",
              "minimum_should_match": "60%"
            }
          }
        },
        {
          "match_phrase": {
            "article_en": {
              "query": "0 dibromobenzene",
              "slop": 3
            }
          }
        }
      ]
    }
  }
}



GET seojoindata/_search
{
  "track_total_hits": true, 
  "size": 0,
  "query": {
    "nested": {
      "path": "coreKeyWord",
      "query": {
        "term": {
          "coreKeyWord.corekwdId": {
            "value": "2057243"
          }
        }
      }
    }
  },
  "_source": {
    "includes": ["coreKeyWord","originalKeyWord"]
  }
}


# 统计每个核心词分配的文章数量
GET seojoindata/_search
{
  "size": 0,
  "aggs": {
    "group_by_kwId": {
      "nested": {
        "path": "coreKeyWord"
      },
      "aggs": {
        "group_by_kId": {
          "terms": {
            "field": "coreKeyWord.corekwdId",
            "size":6000
          }
        }
      }
    }
  }
}


GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 10,
  "query": {
    "nested": {
      "path": "coreKeyWord",
      "query": {
        "bool": {
          "must": [
            {
              "exists": {
                "field": "coreKeyWord.corekwd"
              }
            }
          ]
        }
      }
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist"
    ]
  }
}


# rescore  slop 移动的次数 
GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 10,
  "query": {
    "nested": {
      "path": "coreKeyWord",
      "query": {
        "bool": {
          "must": [
            {
              "exists": {
                "field": "coreKeyWord.corekwd"
              }
            }
          ]
        }
      }
    }
  },
  "rescore": {
    "query": {
      "rescore_query": {
        "match_phrase": {
          "originalKeyWord": {
            "query": "bakery shortening meaning",
            "slop": 20
          }
        }
      }
    },
    "window_size": 50
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist"
    ]
  }
}

GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 25,
  "query": {
    "bool": {
      "should": [
        {
          "match_phrase": {
            "title_en": {
              "query": "citric acid dosage",
              "analyzer": "english"
            }
          }
        },
        {
          "match": {
            "title_en": {
              "query": "citric acid dosage",
              "minimum_should_match": "30%",
              "boost": 2,
              "analyzer": "english"
            }
          }
        },
        {
          "match_phrase": {
            "article_en": {
              "query": "citric acid dosage",
              "analyzer": "english"
            }
          }
        },
        {
          "match": {
            "article_en": {
              "query": "citric acid dosage",
              "minimum_should_match": "50%",
              "boost": 7,
              "analyzer": "english"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "excludes": [
      "article_en"
    ]
  }
}

GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 0, 
  "query": {
   "bool": {
     "must": [
       {
         "exists": {
           "field": "originalKeyWord"
         }
       }
     ]
   }
  },
  "_source": {
    "excludes": [
      "endSource", 
      "model", 
      "category_Id",
      "category_type",
      "part_Id",
      "part_name",
      "article_summery",
      "is_valid"
    ]
  }
}


GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 0, 
  "query": {
   "bool": {
     "must": [
       {
         "exists": {
           "field": "article_summery"
         }
       }
     ]
   }
  },
  "_source": {
    "includes": [
      "endSource", 
      "model", 
      "category_Id",
      "category_type",
      "part_Id",
      "part_name",
      "article_summery",
      "is_valid"
    ]
  }
}

GET seojoindata/_search
{
  "track_total_hits": true,
  "size": 10000, 
  "query": {
   "bool": {
     "must": [
       {
         "term": {
           "endSource": {
             "value": "www.zyzhan.com"
           }
         }
       },
       {
         "term": {
           "part_name": {
             "value": "技术原理"
           }
         }
       }
     ],
     "must_not": [
       {
         "exists": {
           "field": "is_valid"
         }
       }
     ]
   }
  },
  "_source": {
    "includes": [
      "endSource", 
      "model", 
      "category_Id",
      "category_type",
      "part_Id",
      "part_name",
      "is_valid"
    ]
  }
}

# 每个大类下的小类
GET /seojoindata/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_category": {
      "terms": {
        "field": "category_type",
        "size": 50
      },
      "aggs": {
        "group_by_part": {
          "terms": {
            "field": "part_name",
            "size": 20
          },
          "aggs": {
            "group_by_partId": {
              "terms": {
                "field": "part_Id",
                "size": 1
              }
            }
          }
        }
      }
    }
  }
}



GET seokeytags_v4/_search
{
  "query": {
    "term": {
      "articleId": {
        "value": "5e5f0102bdee44a1d6e79f2c"
      }
    }
  }
}

GET /seokeytags_v4/_search
{
  "query": {
    "term": {
      "endSource": {
        "value": "www.chembeango.com"
      }
    }
  },
  "aggs": {
    "filterAge": {
      "filter": {
        
      }
    }
  }, 
  "_source": {
    "includes": [
      "category_Id",
      "category_type",
      "part_Id",
      "part_name"
    ]
  }
}

# 查询关键词少于5篇的文章






GET seojoindata/_search
{
  "size": 0, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "is_valid": {
              "value": 1
            }
          }
        },
        {
          "term": {
            "endSource": {
              "value": "www.bbaqw.com"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part": {
      "terms": {
        "field": "part_name",
        "size": 30
      }
    }
  },
  "_source": {
    "includes": [
      "category_Id",
      "category_type",
      "part_Id",
      "part_name",
      "is_valid"
    ]
  }
}


GET /seokeytags_v4/_search
{
  "track_total_hits": true, 
  "query": {
    "term": {
      "endSource": {
        "value": "www.asiacoat.com"
      }
    }
  }
}


GET /keywordstag/_search
{
  "query": {
    "term": {
      "corekwdId": {
        "value": 1666870
      }
    }
  }
}

# 没有关键词的文章数量
GET /seokeytags_v4/_search
{
  "track_total_hits": true,
  "query": {
    "nested": {
      "path": "coreKeyWord",
      "query": {
        "bool": {
          "must": [
            {
              "exists": {
                "field": "coreKeyWord"
              }
            }
          ]
        }
      }
    }
  }
}


# 关键词深度分页
GET /keywordstag/_search
{
  "track_total_hits": true, 
  "size": 100,
  "query": {
    "bool": {
      "must": [
        {
          "regexp": {
            "corekwd.raw": "a.*"
          }
        }
      ]
    }
  },
  "search_after":[60300],
  "sort": [
    {
      "corekwdId": {
        "order": "asc"
      }
    }
  ], 
  "_source": {
    "includes": ["corekwdId","corekwd","keywords_type"]
  }
}

# 获取关键词最大最小编号

GET /keywordstag/_search
{
  "track_total_hits": true, 
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "regexp": {
            "corekwd.raw": "b.*"
          }
        }
      ]
    }
  },
  "aggs": {
    "min_max_kId": {
      "stats": {
        "field": "corekwdId"
      }
    }
  }
}


GET /keywordstag/_search
{
  "size": 10, 
  "query": {
    "wildcard": {
      "corekwd.raw": {
        "value": "a.*"
      }
    }
  },
  "_source": {
    "includes": ["corekwdId","corekwd","keywords_type"]
  }
}

GET /keywordstag/_search
{
  "size": 10,
  "query": {
    "prefix": {
      "corekwd": {
        "value": "a"
      }
    }
  },
  "_source": {
    "includes": ["corekwdId","corekwd","keywords_type"]
  }
}

GET /keywordstag/_search
{
  "query": {
    "query_string": {
      "default_field": "corekwd",
      "query": {
        "prefix": {
          "corekwd": {
            "value": "a"
          }
        }
      }
    }
  }
}

# 根据分类编号查询级别
GET /seokeytags_v4/_search
{
  "size": 1, 
  "query": {
    "bool": {
      "should": [
        {
          "term": {
            "category_Id.keyword": {
              "value": "c14"
            }
          }
        },
        {
          "term": {
            "part_Id": {
              "value": "c14"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": ["category_Id","category_type","part_Id","part_name"]
  }
}


# 相关关键词
GET /keywordstag/_search
{
  "size": 20,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "keywords_type": {
              "value": 0
            }
          }
        },
        {
          "match": {
            "corekwd": {
              "query": "opical antiviral drugs",
              "analyzer": "english",
              "minimum_should_match": "70%"
            }
          }
        }
      ]
    }
  }
}

# 相关文章
GET /seokeytags_v4/_search
{
  "size":10,
  "query": {
    "bool": {
      "must": [
        {
          "match": {
            "title_en": {
              "query": "State Council announced national price linkage",
              "analyzer": "english", 
              "minimum_should_match": "60%"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": ["articleId","title_en","pubdate","clickCount"]
  }
}

# 文章点击量
GET /seokeytags_v4/_search
{
  "size": 0,
  "aggs": {
    "group_by_click": {
      "top_hits": {
        "size": 20,
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ],
        "_source": {
          "includes": [
            "articleId",
            "category_Id",
            "category_type",
            "title_en",
            "part_Id",
            "part_name",
            "pubdate",
            "clickCount"
          ]
        }
      }
    }
  }
}

GET /keywordstag/_search
{
  "query": {
    "term": {
      "keywords_type": {
        "value": 1
      }
    }
  }
}

POST keywordstag/_update_by_query
{
  "script": {
    "source": "ctx._source.clickCount=2;",
    "lang": "painless"
  },
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "corekwdId": {
              "value": 805
            }
          }
        }
      ]
    }
  }
}

# 文章分配的关键词聚合
GET /seokeytags_v4/_search
{
  "size": 0,
  "aggs": {
    "group_by_tag_name": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 20
      },
      "aggs": {
        "group_by_tag_Id": {
          "terms": {
            "field": "taglist.tagId",
            "size": 1
          }
        }
      }
    }
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ]
}

# 按照tag点击次数聚合
GET /keywordstag/_search
{
  "size": 0,
  "query": {
    "term": {
      "keywords_type": {
        "value": 1
      }
    }
  }, 
  "aggs": {
    "group_by_click":{
      "top_hits": {
        "size": 20,
        "sort": [{
          "clickCount": {
            "order": "desc"
          }
        }]
      }
    }
  }
}

GET /keywordstag/_search
{
  "size": 0,
  "query": {
    "term": {
      "keywords_type": {
        "value": 1
      }
    }
  }, 
  "aggs": {
    "group_by_click": {
      "terms": {
        "field": "corekwd.raw",
        "size": 20
      },
      "aggs": {
        "group_by_Id": {
          "terms": {
            "field": "corekwdId",
            "size": 1
          }
        }
      }
    }
  },
  "sort": [
    {
      "clickCount": {
        "order": "desc"
      }
    }
  ]
}


# 文章详情页
GET /seokeytags_v4/_search
{
  "query": {
    "term": {
      "articleId": {
        "value": "5e5ca575ba25c1e16609cd88"
      }
    }
  },
  "_source": {
    "excludes": ["otherkwdlist","fullurl","model","title","endSource"]
  }
}

#  根据关键词获取摘要
GET /seokeytags_v4/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "match": {
            "article_en": {
              "query": "treatment",
              "minimum_should_match": "60%"
            }
          }
        },
        {
          "term": {
            "articleId": {
              "value": "5e4f9918d515cd7523346441"
            }
          }
        }
      ]
    }
  },
  "highlight": {
    "no_match_size": 150,
    "number_of_fragments":3,
    "pre_tags": [
      "<span>"
    ],
    "post_tags": [
      "</span>"
    ],
    "fields": {
      "article_en": {
        "type": "plain"
      }
    }
  },
  "_source": {
     "excludes": ["otherkwdlist","fullurl","model","title","endSource"]
  }
}


# Tag词列表页下的热点文章 desc
GET /seokeytags_v4/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {"exists": {
          "field": "article_summery"
        }},
        {
          "match": {
            "title_en": {
              "query": "ulpa filter",
              "minimum_should_match": "70%"
            }
          }
        } 
      ]
    }
  }, 
  "aggs": {
    "group_by_clickCount": {
      "top_hits": {
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ],
        "size": 20,
        "_source": {
          "includes": [
            "title_en",
            "articleId",
            "part_Id",
            "part_name",
            "article_summery",
            "category_type",
            "category_Id",
            "pubdate",
            "clickCount"
          ]
        }
      }
    }
  }
}


# 点击量排名前20的关键词
GET /keywordstag/_search
{
  "size": 0,
  "query": {
    "term": {
      "keywords_type": {
        "value": 0
      }
    }
  }, 
  "aggs": {
    "group_by_click": {
      "top_hits": {
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ],
        "size": 20
      }
    }
  }
}

GET /keywordstag/_search
{
  "query": {
    "term": {
      "after_keytag.raw": {
        "value": "mg full form in medical"
      }
    }
  }
}

#  根据tagId获取tag数据
GET /keywordstag/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        },
        {
          "term": {
            "corekwdId": {
              "value": 805
            }
          }
        }
      ]
    }
  }
}

# tags列表页 文章
GET /seokeytags_v4/_search
{
  "track_total_hits": true, 
  "from": 0,
  "size": 20, 
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist"
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        },
        {
          "term": {
            "taglist.tag.raw": {
              "value": "emtricitabine"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "title_en",
      "articleId",
      "part_Id",
      "part_name",
      "category_type",
      "category_Id",
      "article_summery",
      "taglist", 
      "pubdate",
      "clickCount"
    ]
  }
}


GET /seokeytags_v4/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist"
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "title_en",
      "articleId",
      "part_Id",
      "part_name",
      "category_type",
      "category_Id",
      "taglist", 
      "pubdate",
      "clickCount"
    ]
  }
}

# 关键词列表页 topics  按照二级分类文章数量desc 聚合
GET /seokeytags_v4/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {"exists": {
          "field": "part_Id"
        }}
      ]
    }
  }, 
  "aggs": {
    "group_by_part": {
      "terms": {
        "field": "part_name",
        "size": 10
      },
      "aggs": {
        "group_by_part_Id": {
          "terms": {
            "field": "part_Id",
            "size": 1
          }
        }
      }
    }
  }
}

# 关键词类表页下的热点文章 desc
GET /seokeytags_v4/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {"exists": {
          "field": "article_summery"
        }},
        {
          "match": {
            "title_en": {
              "query": "ulpa filter",
              "analyzer": "english",
              "minimum_should_match": "70%"
            }
          }
        }
      ]
    }
  }, 
  "aggs": {
    "group_by_clickCount": {
      "top_hits": {
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ],
        "size": 20,
        "_source": {
          "includes": [
            "title_en",
            "articleId",
            "part_Id",
            "part_name",
            "category_type",
            "category_Id",
            "pubdate",
            "clickCount"
          ]
        }
      }
    }
  }
}

# 关键词列表页 hottag  匹配tag词然后再聚合
GET /seokeytags_v4/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "match": {
            "taglist.tag": {
              "query": "0.22 micron filter",
              "minimum_should_match": "40%"
              
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_tag_name": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 20
      },
      "aggs": {
        "group_by_tag_Id": {
          "terms": {
            "field": "taglist.tagId",
            "size": 1
          }
        }
      }
    }
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ]
}

# 相关tag词匹配
GET keywordstag/_search
{
  "size": 20,
  "query": {
    "bool": {
      "must": [
        {
          "match": {
            "corekwd":{
              "query": "bitterant",
              "minimum_should_match": "60%"
            }
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 1
            }
          }
        }
      ]
    }
  }
}

# 相关关键词匹配
GET keywordstag/_search
{
  "size": 20,
  "query": {
    "bool": {
      "must": [
        {
          "match": {
            "corekwd":{
              "query": "0.1 glycine buffer",
              "minimum_should_match": "75%"
            }
          }
        },
        {
          "term": {
            "keywords_type": {
              "value": 0
            }
          }
        }
      ]
    }
  }
}

GET keywordstag/_search
{
  "query": {
    "term": {
      "corekwdId": {
        "value": 1309905
      }
    }
  }
}


GET /seokeytags_v4/_search
{
  "query": {
    "match_all": {}
  }
}




# 根据关键词ID获取关键词信息
GET seokeytags_v4/_search
{
  "track_total_hits": true,
  "size": 20,
  "query": {
    "bool": {
      "should": [
        {"term": {
          "otherkwdlist.keyId": {
            "value": "1004333"
          }
        }},
        {
          "term": {
            "coreKeyWord.corekwdId": {
              "value": "1004333"
            }
          }
        }
      ]
    }
  }
  
}

# 相关关键词匹配title
GET seokeytags_v4/_search
{
  "track_total_hits": true,
  "from": 0, 
  "size": 20,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_summery"
          }
        },
        {
          "match": {
            "title_en": {
              "query": "0.05 edta solution preparation"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "includes": [
      "articleId",
      "title_en",
      "clickCount",
      "article_summery",
      "pubdate"
    ]
  },
  "highlight": {
    "pre_tags": [
      "<span>"
    ],
    "post_tags": [
      "</span>"
    ],
    "fields": {
      "title_en": {
        "type": "plain"
      }
    }
  }
}


# 相关关键词文章内容
GET seokeytags_v4/_search
{
  "track_total_hits": true,
  "size": 20,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "article_summery"
          }
        }
      ],
      "should": [
        {
          "match_phrase": {
            "title_en": {
              "query": "trichloro propanone",
              "analyzer": "english"
            }
          }
        },
        {
          "match": {
            "title_en": {
              "query": "trichloro propanone",
              "minimum_should_match": "50%",
              "boost": 5
            }
          }
        },
        {
          "match": {
            "article_summery": {
              "query": "trichloro propanone",
              "minimum_should_match": "70%",
              "boost": 5
            }
          }
        },
        {
          "match_phrase": {
            "article_en": {
              "query": "trichloro propanone",
              "analyzer": "english"
            }
          }
        },
        {
          "match": {
            "article_en": {
              "query": "trichloro propanone",
              "minimum_should_match": "70%",
              "boost": 7,
              "analyzer": "english"
            }
          }
        }
        
      ]
    }
  },
  "_source": {
    "includes": [
      "articleId",
      "title_en",
      "clickCount",
      "article_summery",
      "pubdate"
    ]
  }
}

GET /seokeytags_v4/_search
{
  "track_total_hits": true, 
  "query": {
    "nested": {
      "path": "coreKeyWord",
      "query": {
        "match": {
          "coreKeyWord.corekwd": {
            "query": "polarised state meaning",
            "minimum_should_match": "60%"
          }
        }
      }
    }
  },
  "_source": {
    "includes": [
      "part_Id",
      "coreKeyWord",
      "pubdate",
      "article_summery",
      "articleId",
      "title_en",
      "clickCount"
    ]
  }
}

GET seokeytags_v4/_search
{
  "track_total_hits": true,
  "size": 20,
  "query": {
    "nested": {
      "path": "coreKeyWord",
      "query": {
        "bool": {
          "must": [
            {
              "exists": {
                "field": "article_summery"
              }
            }
          ],
          "should": [
            {
              "term": {
                "coreKeyWord.corekwd": {
                  "value": "polarised state meaning"
                }
              }
            },
            {
              "match_phrase": {
                "coreKeyWord.corekwd": {
                  "query": "polarised state meaning"
                }
              }
            },
            {
              "match": {
                "coreKeyWord.corekwd": {
                  "query": "polarised state meaning"

                }
              }
            }
          ]
        }
      }
    }
  },
  "_source": {
    "includes": [
      "part_Id",
      "coreKeyWord",
      "pubdate",
      "article_summery",
      "articleId",
      "title_en",
      "clickCount"
    ]
  }
}

# 二级分类页的大类导航
GET /seokeytags_v4/_search
{
  "size": 0,
  "aggs": {
    "group_by_category": {
      "terms": {
        "field": "category_type",
        "size": 100
      },
      "aggs": {
        "group_by_category_Id": {
          "terms": {
            "field": "category_Id.keyword",
            "size": 1
          }
        }
      }
    }
  }
}


# 二级分类页下的点击量前20的关键词
GET /seokeytags_v4/_search
{
  "size": 0,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "part_Id": "c2113"
        }
      }
    }
  },
  "aggs": {
    "group_by_clickCount": {
      "top_hits": {
        "size": 20,
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ],
        "_source": {
          "includes": [
            "part_Id", 
            "coreKeyWord",
            "pubdate",
            "clickCount"
          ]
        }
      }
    }
  }
}

# 二级分类页下的点击量前20的文章
GET /seokeytags_v4/_search
{
  "size": 0,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "part_Id": "c2113"
        }
      },
      "must": [
        {
          "exists": {
            "field": "article_summery"
          }
        }
      ]
    }
  },
  "aggs": {
    "top_articles": {
      "top_hits": {
        "size": 20,
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ],
         "_source": {
          "includes": [
            "title_en",
            "articleId",
            "part_Id",
            "part_name",
            "category_type",
            "category_Id",
            "pubdate",
            "clickCount"
          ]
        }
      }
    }
  }
}
# 二级分类页下的按照标签对应的文章数量desc top20标签
GET /seokeytags_v4/_search
{
  "size": 0,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "part_Id": "c2113"
        }
      }
    }
  },
  "aggs": {
    "group_by_tags": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 20
      },
      "aggs": {
        "group_by_tagId": {
          "terms": {
            "field": "taglist.tagId",
            "size": 1
          }
        }
      }
    }
  }
}



# 二级分类页
GET /seokeytags_v4/_search
{
  "track_total_hits": true, 
  "from": 0, 
  "size": 20,
  "query": {
    "bool": {
      "filter": {
        "term": {
          "part_Id": "c2113"
        }
      },
      "must": [
        {"exists": {
          "field": "article_summery"
        }},
        {
          "exists": {
            "field": "taglist"
          }
        }
      ]
    }
  },
  "sort": [
    {
      "pubdate": {
        "order": "desc"
      }
    }
  ], 
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "model",
      "coreKeyWord",
      "clickCount"
    ]
  }
}


# 一级分类项下的top 20关键词
GET /seokeytags_v4/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "category_Id.keyword": {
              "value": "c14"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "top_keyword": {
      "top_hits": {
        "sort": [
          {
            "coreKwdCount": {
              "order": "desc"
            }
          }
        ],
        "size": 20,
        "_source": {
          "includes": [
            "category_type",
            "category_Id",
            "pubdate",
            "coreKeyWord",
            "coreKwdCount"
          ]
        }
      }
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "model",
      "article_summery",
      "part_Id",
      "part_name",
      "title_en",
      "articleId",
      "category_type",
      "clickCount"
    ]
  }
}

# 一级分类下的热点文章 desc
GET /seokeytags_v4/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "category_Id.keyword": {
              "value": "c21"
            }
          }
        },
        {
          "exists": {
            "field": "article_summery"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_clickCount": {
      "top_hits": {
        "sort": [
          {
            "clickCount": {
              "order": "desc"
            }
          }
        ],
        "size": 20,
        "_source": {
          "includes": [
            "title_en",
            "articleId",
            "part_Id",
            "part_name",
            "category_type",
            "category_Id",
            "pubdate",
            "clickCount"
          ]
        }
      }
    }
  }
}

# 一级分类名称下的标签聚合 排名前10的
GET /seokeytags_v4/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "category_Id.keyword": {
              "value": "c21"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_tag_name": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 20
      },
      "aggs": {
        "group_by_tag_Id": {
          "terms": {
            "sort": [
              {
                "pubdate": {
                  "order": "desc"
                }
              }
            ],
            "field": "taglist.tagId",
            "size": 1
          }
        }
      }
    }
  }
}


# 一级分类页和对应子类的文章
GET /seokeytags_v4/_search
{
  "size": 0,
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "category_Id.keyword": {
              "value": "c21"
            }
          }
        },
        {
          "exists": {
             "field": "article_summery"
          }
        }
      ]
    }
  },
  "aggs": {
    "group_by_part_Id": {
      "terms": {
        "field": "part_Id",
        "size": 20
      },
      "aggs": {
        "top_articles": {
          "top_hits": {
            "sort": [
              {
                "pubdate": {
                  "order": "desc"
                }
              }
            ],
            "size": 20,
            "_source": {
              "includes": [
                "title_en",
                "articleId",
                "part_Id",
                "part_name",
                "category_type",
                "category_Id",
                "article_summery",
                "pubdate"
              ]
            }
          }
        }
      }
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "coreKwdCount",
      "model",
      "clickCount"
    ]
  }
}

# 点击量排名靠前的关键词 top 20
GET /seokeytags_v4/_search
{
  "size": 20, 
  "query": {
    "match_all": {}
  },
  "sort": [
    {
      "coreKwdCount": {
        "order": "desc"
      }
    }
  ],
   "_source": {
     "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "originalKeyWord",
      "model",
      "part_Id",
      "part_name",
      "title_en",
      "articleId",
      "category_type",
      "category_Id",
      "clickCount"
    ]
  }
}



# hotArticals  按照文章点击量倒叙排序
GET /seokeytags_v4/_search
{
  "size": 20, 
  "query": {
    "match_all": {}
  },
  "sort": [
    {
      "clickCount": {
        "order": "desc"
      }
    }
  ],
   "_source": {
     "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "coreKeyWord",
      "originalKeyWord",
      "model",
      "part_Id",
      "part_name"
    ]
  }
}


# 获取每个大类对应的top15文章
GET /seokeytags_v4/_search
{
  "size": 20, 
  "query": {
    "term": {
      "category_Id.keyword": {
        "value": "c15"
      }
    }
  },
  "_source": {
     "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist",
      "title",
      "article_keys",
      "fullurl",
      "endSource",
      "coreKeyWord",
      "originalKeyWord",
      "model",
      "part_Id",
      "part_name"
    ]
  }
}


# 获取去重后的一级分类名称和Id

GET /seokeytags_v4/_search
{
  "size": 0,
  "aggs": {
    "group_by_category_type": {
      "terms": {
        "field": "category_type"
      },
      "aggs": {
        "show_category_Id": {
          "terms": {
            "field": "category_Id.keyword"
          }
        }
      }
    } 
  }
}

GET /seokeytags_v4/_search
{
  "size": 0,
  "aggs": {
    "group_by_category_type": {
      "terms": {
        "field": "category_type"
      },
      "aggs": {
        "show_category_Id": {
          "terms": {
            "field": "category_Id.keyword"
          },
          "aggs": {
            "group_by_part_name": {
              "terms": {
                "field": "part_name",
                "size": 200
              },
              "aggs": {
                "show_part_Id": {
                  "terms": {
                    "field": "part_Id",
                    "size": 10
                  }
                }
              }
            }
          }
        }
      }
    } 
  }
}


# 二级分类聚合
GET /seokeytags_v4/_search
{
  "size": 0,
  "aggs": {
    "group_by_part_name": {
      "terms": {
        "field": "part_name",
        "size":100
      },
      "aggs": {
        "show_part_Id": {
          "terms": {
            "field": "part_Id"
          }
        }
      }
    } 
  }
}



GET /seokeytags_v4/_mapping



GET /seokeytags_v4/_count
# 67505
GET /seokeytags_v2/_count

GET /seokeytags_v2/_search
{
  "track_total_hits": true, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "endSource": {
              "value": "www.youjc.com"
            }
          }
        } 
      ]
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist"
    ]
  }
}

GET /seokeytags_v4/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "endSource": {
              "value": "Pharmaceutical Intermediates"
            }
          }
        },
        {
          "term": {
            "model": {
              "value": "药物疗效"
            }
          }
        }
      ]
    }
  },
  "_source": {
    "excludes": [
      "article_en",
      "otherkwdlist",
      "taglist"
    ]
  }
}

# 批量修改文章点击数
POST seokeytags_v4/_update_by_query
{
  "script": {
    "source": "ctx._source.clickCount=0;",
    "lang": "painless"
  },
  "query": {
    "match_all":{}
  }
}


POST seokeytags_v4/_update_by_query
{
  "script": {
    "source": "ctx._source.category_type='Industrial Coatings';ctx._source.category_Id='c25';ctx._source.part_name='nan';ctx._source.part_Id='nan';",
    "lang": "painless"
  },
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "endSource": {
              "value": "www.asiacoat.com"
            }
          }
        }
      ]
    }
  }
}



GET /seokeytags_v2/_search
{
  "query": {
    "term": {
      "articleId": {
        "value": "5e5498fed515cd75583c0571"
      }
    }
  },
   "_source": {
    "excludes": [
      "article_en","otherkwdlist","taglist"
    ]
  }
}

GET /seokeytags_v4/_search
{
  "query": {
    "match_all": {}
  },
   "_source": {
    "excludes": [
      "article_en","otherkwdlist","taglist"
    ]
  }
}


GET /seokeytags_v2/_search
{
  "track_total_hits":true, 
  "size": 100, 
  "query": {
    "bool": {
      "filter": {
        "exists": {
          "field": "article_summery"
        }
      }
    }
  }
}


# 排名前20个的tag词聚合
GET /seokeytags_v4/_search
{
  "track_total_hits": true,
  "size": 0,
  "aggs": {
    "group_by_taglist_tag": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 20
      },
      "aggs": {
        "group_by_tag_Id": {
          "terms": {
            "field": "taglist.tagId",
            "size": 1
          }
        }
      }
    }
  }
}


# 每个tag词都分配了多少次
GET /seokeytags_v4/_search
{
  "track_total_hits": true,
  "size": 0,
  "aggs": {
    "group_by_taglist_tag": {
      "terms": {
        "field": "taglist.tag.raw",
        "size": 20
      }
    },
    "group_by_endSource": {
      "terms": {
        "field": "title_en.raw",
        "size": 20
      }
    }
  }
}

GET /seokeytags_v2/_search
{
  "query": {
    "term": {
      "title_en.raw": {
        "value": "A brief report on the international soybean market"
      }
    }
  }
}

GET /seokeytags_v2/_search
{
  "size": 0,
  "aggs": {
    "total_count": {
      "terms": {
        "field": "title_en.raw",
        "size": 10
      }
    }
  }
}


# 匹配taglist

GET /seokeytags_v2/_search
{
  "track_total_hits": true,
  "size": 200,
  "query": {
    "bool": {
      "should": [
        {
          "term": {
            "taglist.tag.raw": {
              "value": "flavorant"
            }
          }
        },
        {
          "match_phrase": {
            "taglist.tag": "flavorant"
          }
        },
        {
          "match": {
            "taglist.tag": "flavorant"
          }
        }
      ]
    }
  },
  "highlight": {
    "pre_tags": [
      "<strong>"
    ],
    "post_tags": [
      "</strong>"
    ],
    "fields": [
      {
        "article_en": {
          "type": "plain"
        }
      },
      {
        "title_en": {
          "type": "plain"
        }
      }
    ]
  }
}

GET /seokeytags_v2/_search
{
  "track_total_hits": true,
  "query": {
    "bool": {
      "must": [
        {
          "exists": {
            "field": "taglist"
          }
        }
      ]
    }
  },
  "sort": [
    {
      "taglist.tagId": {
        "order": "desc"
      }
    }
  ], 
  "_source": {
    "excludes": [
      "article_en","otherkwdlist"
    ]
  }
}

# 67288
GET seokeytags_v2/_search
{
  "track_total_hits": true, 
  "size": 200, 
  "query": {
    "nested": {
      "path": "coreKeyWord",
      "query": {
        "bool": {
          "must": [
            {"exists": {"field": "coreKeyWord"
            }}
          ]
        }
      }
    }
  },
  "_source":  ["title_en","coreKeyWord","otherkwdlist"]
}





# 聚合分析案例  家电卖场案例背景
# 以一个家电卖场中的电视销售数据为背景，对各种品牌 颜色的电视的销量和销售额 进行各种角度的分析
PUT /tvs
{
  "mappings": {
    "properties": {
      "price":{
        "type": "long"
      },
      "color":{
        "type": "keyword"
      },
      "brand":{
        "type": "keyword"
      },
      "sold_date":{
        "type": "date"
      }
    }
  }
}

# 批量导入数据
POST /tvs/_bulk
{"index":{"_index":"tvs"}}
{"price":1000,"color":"红色","brand":"长虹","sold_date":"2016-10-28"}
{"index":{"_index":"tvs"}}
{"price":2000,"color":"红色","brand":"长虹","sold_date":"2016-11-05"}
{"index":{"_index":"tvs"}}
{"price":3000,"color":"绿色","brand":"小米","sold_date":"2016-05-18"}
{"index":{"_index":"tvs"}}
{"price":1500,"color":"蓝色","brand":"TCL","sold_date":"2016-07-02"}
{"index":{"_index":"tvs"}}
{"price":1200,"color":"绿色","brand":"TCL","sold_date":"2016-08-19"}
{"index":{"_index":"tvs"}}
{"price":2000,"color":"红色","brand":"长虹","sold_date":"2016-11-05"}
{"index":{"_index":"tvs"}}
{"price":8000,"color":"红色","brand":"三星","sold_date":"2017-01-01"}
{"index":{"_index":"tvs"}}
{"price":2500,"color":"蓝色","brand":"小米","sold_date":"2017-02-12"}

# 统计哪种颜色的电视销量最高
# agg  固定语法 要对一份数据执行分组聚合操作
# popular_color 就是对每个agg 都要起一个名字 名字可以自定义
# terms 根据字段的值进行分组
# field 根据指定的字段的值进行分组
GET /tvs/_search
{
  "size": 0,
  "aggs": {
    "popular_color": {
      "terms": {
        "field": "color"
      }
    }
  }
}

# 嵌套agg metric聚合分析buket
# 对颜色聚合后再计算每种颜色的平均价
GET /tvs/_search
{
  "size": 0,
  "aggs": {
    "group_by_color": {
      "terms": {
        "field": "color"
      },
      "aggs": {
        "avg_price": {
          "avg": {
            "field": "price"
          }
        }
      }
    }
  }
}

# 从颜色到品牌商进行下钻分析
# 每种颜色的平均价格 以及找到的每种颜色每个品牌的平均价格 我们可以进行多层次的下钻 比如说 现在有红的电视4台 同时这4台电视中有3台属于长虹 1台属于小米
# 红色电视中的3台长虹的平均价是多少
# 红色电视中的1台小米的平均价是多少

# 下钻的意思是 已经分了一个组，比如说颜色的分组，然后还要继续对这个分组内的数据再分组，比如一个颜色内，还可以分成多个不同的品牌的组，最后对每个最小粒度的分组执行聚合分析操作，这就叫下钻分析
GET /tvs/_search
{
  "size": 0,
  "aggs": {
    "group_by_color": {
      "terms": {
        "field": "color"
      },
      "aggs": {
        "color_avg_price": {
          "avg": {
            "field": "price"
          }
        },
        "group_by_brand":{
          "terms": {
            "field": "brand"
          },
          "aggs": {
            "brand_avg_price": {
              "avg": {
                "field": "price"
              }
            }
          }
        }
      }
    }
  }
}

# 更多的metric 
# count avg
# count bucket terms 自动会有一个doc_count 相当于count

GET /tvs/_search
{
  "size": 0,
  "aggs": {
    "group_by_color": {
      "terms": {
        "field": "color"
      },
      "aggs": {
        "avg_price": {
          "avg": {
            "field": "price"
          }
        },
        "max_price":{
          "max": {
            "field": "price"
          }
        },
        "min_price":{
          "min": {
            "field": "price"
          }
        },
        "sum_price":{
          "sum": {
            "field": "price"
          }
        }
      }
    }
  }
}


# histogram 类似terms 也是进行bucket分组操作,接收一个field 按照这个field的值个各个范围区间进行bucket分组操作
# "histogram":{"filed":"price","interval":2000}
# interval:2000  划分范围 0-2000 2000-4000 4000-6000，。。。。。 buckets
GET /tvs/_search
{
  "size": 0,
  "aggs": {
    "group_by_price": {
      "histogram": {
        "field": "price",
        "interval": 2000
      },
      "aggs": {
        "sum_price": {
          "sum": {
            "field": "price"
          }
        }
      }
    }
  }
}

# date_histogram 按照指定的某个date类型的日期field 以及interval
# min_doc_count 即使某个日期的Interval 一条数据没有，那么这个区间也是返回的
# extended_bounds min max  划分bucket的时候会限定在一个具体的范围之内
# 按照月份划分
GET /tvs/_search
{
  "size": 0,
  "aggs": {
    "group_by_sold_date": {
      "date_histogram": {
        "field": "sold_date",
        "interval": "month",
        "format": "yyyy-MM-dd",
        "min_doc_count": 0,
        "extended_bounds": {
          "min": "2016-01-01",
          "max": "2017-01-31"
        }
      }
    }
  }
}




# 每个季度每个品牌的销售额
GET /tvs/_search
{
  "size": 0,
  "aggs": {
    "group_by_sold_date": {
      "date_histogram": {
        "field": "sold_date",
        "interval": "quarter",
        "min_doc_count": 0,
        "extended_bounds": {
         "min": "2016-01-01",
          "max": "2017-12-31"
        }
      },
      "aggs": {
        "group_by_brand": {
          "terms": {
            "field": "brand"
          },
          "aggs": {
            "sum_price": {
              "sum": {
                "field": "price"
              }
            }
          }
        },
        "total_sum_price":{
          "sum": {
            "field": "price"
          }
        }
      }
    },
    "toal_brand_sum_price":{
      "sum": {
        "field": "price"
      }
    }
  }
}

# 查询nested coreKeyWord
GET seokeytags_v2/_search
{
  "track_total_hits": true,
  "query": {
    "nested": {
      "path": "coreKeyWord",
      "query": {
        "bool": {
          "should": [
            {"term": {
              "coreKeyWord.corekwd": {
                "value": "citric acid uses  cosmetics"
              }
            }},
            {
              "match_phrase": {
                "coreKeyWord.corekwd": {
                  "query": "citric acid uses  cosmetics"
                }
              }
            },
            {
              "match": {
                "coreKeyWord.corekwd": {
                  "query": "citric acid uses  cosmetics",
                  "minimum_should_match":"50%"
                }
              }
            }
          ]
        }
      }
    }
  }
}



# 查询含有中文的核心词
GET seokeytags_v2/_search
{
  "track_total_hits": true,
  "query": {
    "nested": {
      "path": "coreKeyWord",
      "query": {
        "bool": {
          "should": [
            {
              "term": {
                "coreKeyWord.corekwd": {
                  "value": "中文"
                }
              }
            },
            {
              "match_phrase": {
                "coreKeyWord.corekwd": {
                  "query": "中文"
                }
              }
            },
            {
              "match": {
                "coreKeyWord.corekwd": {
                  "query": "中文",
                  "minimum_should_match": "50%"
                }
              }
            }
          ]
        }
      }
    }
  },
  "_source": {
    "excludes": [
      "article_en"
    ]
  }
}



GET seokeytags/_search
{
  "track_total_hits": true, 
  "size": 200, 
  "query": {
    "nested": {
      "path": "coreKeyWord",
      "query": {
        "bool": {
          "must": [
            {
              "exists": {
                "field": "coreKeyWord"
              }
            }
          ]
        }
      }
    }
  },
  "_source":  ["title_en","coreKeyWord","otherkwdlist","taglist"]
}


GET seokeytags/_search
{
  "track_total_hits": true, 
  "size": 200, 
  "query": {
   "bool": {
     "must_not": [
       {"exists": {
         "field": "originalKeyWord"
       }}
     ]
   }
  },
  "_source":  ["title_en","coreKeyWord","otherkwdlist"]
}

# 去重

GET seokeytags/_search
{
  "track_total_hits": true, 
  "size": 0,
  "aggs": {
    "distict_title": {
      "cardinality": {
        "field": "fullurl"
      }
    }
  }
}


GET seokeytags/_search
{
  "query": {
    "match_all": {}
  }
}



GET /seokeytags/_mapping

GET /_cat/health

GET /seokeytags_v2/_count

GET /seokeytags/_count

PUT seokeytags_v3
{
  "mappings": {
    "properties": {
      "articleId":{
        "type":"keyword"
      },
      "title": {
        "type": "text"
      },
      "title_en": {
        "type": "text",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        },
        "analyzer": "english"
      },
      "article_en": {
        "type": "text",
        "analyzer": "english"
      },
      "article_keys": {
        "type": "text",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        }
      },
      "article_summery": {
        "type": "text",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        }
      },
      "clickCount": {
        "type": "long"
      },
      "originalKeyWord": {
        "type": "text",
        "analyzer": "english"
      },
      "coreKeyWord": {
        "type": "nested",
        "properties": {
          "corekwd":{
            "type":"text",
            "analyzer": "english"
          },
          "corekwdId":{
            "type":"long"
          }
        }
      },
      "otherkwdlist":{
        "type": "nested",
        "properties": {
          "keyname":{
            "type":"text",
            "analyzer": "english"
          },
          "keyId":{
            "type":"long"
          }
        }
      },
      "endSource": {
        "type": "keyword"
      },
      "fullurl": {
        "type": "keyword"
      },
      "model": {
        "type": "keyword"
      },
      "part_name": {
        "type": "keyword"
      },
      "part_type": {
        "type": "keyword"
      },
      "relatedKeyWords": {
        "type": "nested",
        "properties": {
          "rtdkwd": {
            "type": "text",
            "analyzer": "english"
          },
          "rtdkwdId":{
            "type":"long"
          }
        }
      },
      "relatedTags": {
        "type": "nested",
        "properties": {
          "tag": {
            "type": "keyword"
          },
          "tagId":{
            "type":"long"
          }
        }
      },
      "taglist": {
        "properties": {
          "tag": {
            "type": "text",
            "fields": {
              "raw": {
                "type": "keyword"
              }
            }
          },
          "tagId":{
            "type":"long"
          }
        }
      },
      "category_type": {
        "type": "keyword"
      }
    }
  }
}

# DELETE seokeytagsdata

# 带文章匹配数的关键词模型 0408
PUT seokeytagsdata
{
  "mappings": {
    "properties": {
      "corekwd": {
        "type": "text",
        "analyzer": "english",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        }
      },
      "corekwdId": {
        "type": "long"
      },
      "keywords_type": {
        "type": "long"
      },
      "clickCount":{
        "type": "long"
      },
      "del_flag":{
        "type": "long"
      },
      "match_count":{
        "type": "long"
      },
      "after_keytag": {
        "type": "text",
        "analyzer": "english",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        }
      }
    }
  }
}


# 关键词名称 编号 类型  处理后名称
PUT keywordstag
{
  "mappings": {
    "properties": {
      "corekwd": {
        "type": "text",
        "analyzer": "english",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        }
      },
      "corekwdId": {
        "type": "long"
      },
      "keywords_type": {
        "type": "long"
      },
      "clickCount":{
        "type": "long"
      },
      "after_keytag": {
        "type": "text",
        "analyzer": "english",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        }
      }
    }
  }
}

DELETE seojoindata

# 带编号和发布日期的模型
# PUT seokeytags_v4

PUT seojoindata
{
  "mappings": {
    "properties": {
      "articleId":{
        "type":"keyword"
      },
      "pubdate":{
        "type": "keyword"
      },
      "title": {
        "type": "text"
      },
      "title_en": {
        "type": "text",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        },
        "analyzer": "english"
      },
      "article_hot_flag":{
        "type": "long"
      },
      "article_en": {
        "type": "text",
        "analyzer": "english"
      },
      "article_keys": {
        "type": "text",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        }
      },
      "article_summery": {
        "type": "text",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        }
      },
      "clickCount": {
        "type": "long"
      },
      "originalKeyWord": {
        "type": "text",
        "analyzer": "english"
      },
      "coreKwdCount":{
        "type": "long"
      },
      "coreKeyWord": {
        "type": "nested",
        "properties": {
          "corekwd":{
            "type":"text",
            "analyzer": "english"
          },
          "corekwdId":{
            "type":"long"
          }
        }
      },
      "otherkwdlist":{
        "type": "nested",
        "properties": {
          "keyname":{
            "type":"text",
            "analyzer": "english"
          },
          "keyId":{
            "type":"long"
          }
        }
      },
      "endSource": {
        "type": "keyword"
      },
      "fullurl": {
        "type": "keyword"
      },
      "model": {
        "type": "keyword"
      },
      "part_name": {
        "type": "keyword"
      },
      "part_Id": {
        "type": "keyword"
      },
      "part_type": {
        "type": "keyword"
      },
      "relatedKeyWords": {
        "type": "nested",
        "properties": {
          "rtdkwd": {
            "type": "text",
            "analyzer": "english"
          },
          "rtdkwdId":{
            "type":"long"
          }
        }
      },
      "relatedTags": {
        "type": "nested",
        "properties": {
          "tag": {
            "type": "keyword"
          },
          "tagId":{
            "type":"long"
          }
        }
      },
      "taglist": {
        "properties": {
          "tag": {
            "type": "text",
            "fields": {
              "raw": {
                "type": "keyword"
              }
            }
          },
          "tagId":{
            "type":"long"
          }
        }
      },
      "category_type": {
        "type": "keyword"
      },
      "category_Id ":{
        "type": "text"
      },
      "is_valid":{
        "type": "long"
      },
      "del_flag":{
        "type":"long"
      }
    }
  }
}

# 创建一个备份索引 添加了未清洗前的词 tag词
PUT seojoindata_back/

PUT seojoindata
{
  "mappings": {
    "properties": {
      "articleId": { 
        "type": "keyword"
      },
      "article_en": {
        "type": "text",
        "analyzer": "english"
      },
      "article_hot_flag": {
        "type": "long"
      },
      "article_keys": {
        "type": "text",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        }
      },
      "article_summery": {
        "type": "text",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        }
      },
      "category_Id": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      },
      "category_type": {
        "type": "keyword"
      },
      "clickCount": {
        "type": "long"
      },
      "coreKeyWord": {
        "type": "nested",
        "properties": {
          "corekwd": {
            "type": "text",
            "analyzer": "english"
          },
          "corekwd_after": {
            "type": "text",
            "fields": {
              "raw": {
                "type": "keyword",
                "ignore_above": 256
              }
            },
            "analyzer": "english"
          },
          "corekwdId": {
            "type": "long"
          }
        }
      },
      "coreKwdCount": {
        "type": "long"
      },
      "del_flag": {
        "type": "long"
      },
      "endSource": {
        "type": "keyword"
      },
      "fullurl": {
        "type": "keyword"
      },
      "is_valid": {
        "type": "long"
      },
      "model": {
        "type": "keyword"
      },
      "originalKeyWord": {
        "type": "text",
        "analyzer": "english"
      },
      "otherkwdlist": {
        "type": "nested",
        "properties": {
          "keyId": {
            "type": "long"
          },
          "keyname_after": {
            "type": "text",
            "analyzer": "english",
            "fields": {
              "raw": {
                "type": "keyword",
                "ignore_above": 256
              }
            }
          },
          "keyname": {
            "type": "text",
            "analyzer": "english"
          }
        }
      },
      "part_Id": {
        "type": "keyword"
      },
      "part_name": {
        "type": "keyword"
      },
      "part_type": {
        "type": "keyword"
      },
      "pubdate": {
        "type": "keyword"
      },
      "relatedKeyWords": {
        "type": "nested",
        "properties": {
          "rtdkwd": {
            "type": "text",
            "analyzer": "english"
          },
          "rtdkwd_after": {
            "type": "text",
            "fields": {
              "raw": {
                "type": "keyword",
                "ignore_above": 256
              }
            },
            "analyzer": "english"
          },
          "rtdkwdId": {
            "type": "long"
          }
        }
      },
      "relatedTags": {
        "type": "nested",
        "properties": {
          "tag": {
            "type": "keyword"
          },
          "tag_after": {
            "type": "text",
            "fields": {
              "raw": {
                "type": "keyword",
                "ignore_above": 256
              }
            },
            "analyzer": "english"
          },
          "tagId": {
            "type": "long"
          }
        }
      },
      "seo_category_Id": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      },
      "seo_category_type": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      },
      "seo_part_Id": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      },
      "seo_part_name": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      },
      "taglist": {
        "properties": {
          "tag": {
            "type": "text",
            "fields": {
              "raw": {
                "type": "keyword"
              }
            }
          },
          "tag_after": {
            "type": "text",
            "fields": {
              "raw": {
                "type": "keyword",
                "ignore_above": 256
              }
            }
          },
          "tagId": {
            "type": "long"
          }
        }
      },
      "title": {
        "type": "text"
      },
      "title_en": {
        "type": "text",
        "fields": {
          "raw": {
            "type": "keyword"
          }
        },
        "analyzer": "english"
      }
    }
  }
}