python操作solr从入门到掌握

ゝ一世哀愁。 2023-02-12 15:25 126阅读 0赞

#### 一.安装并创建core ####

##### 1.1安装 #####

cd /usr/local/
    wget http://mirrors.hust.edu.cn/apache/lucene/solr/7.7.3/solr-7.7.3.tgz
    tar -zxvf solr-7.7.3.tgz
    
    # 启动
    cd /usr/local/solr-7.7.3/bin
    ./solr start -force

##### 1.2安装创建core #####

#### 环境添加core
    cd /usr/local/solr-7.7.3/server
    
    # 添加自己的solr core
    mkdir new_core
    
    cd /usr/local/solr-7.7.3/server/solr/configsets/_default
    
    cp -r ./conf /usr/local/solr-7.7.3/server/solr/new_core

界面添加core

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0NvY2t0YWlsX3B5_size_16_color_FFFFFF_t_70]

#### 二.pysolr操作solr ####

# 需要新建一个new_core不然会报错 步骤1.2
    solr = pysolr.Solr('http://127.0.0.1:8983/solr/new_core', always_commit=True, )
    # 查看solr是否能ping得通
    # print(solr.ping())

##### 2.1插入数据 #####

for i in range(1,2000):
        solr.add([
            { 
                "id": "doc_%d"%i,
                "title": "A TeST document",
                "article": "my name is Cocktail_py%d"%i,
                "translation": "Nice to Cocktail_py%d"%i,
            },
    
    
            { 
                "id": "doc_2",
                "title": "The Banana: Tasty or Dangerous?",
                "_doc": [
                    {  "id": "child_doc_1", "title": "peel" },
                    {  "id": "child_doc_2", "title": "seed" },
                ]
            },
        ])
    
    # 搜索new_core中的全部数据
    results = solr.search('*:*')
    print(results.docs)

##### 2.2分页 #####

# 假设一页返回10条数据
    # 返回第一页
    results = solr.search('*:*', start=0 * 10, rows=10)
    
    
    # 返回第二页
    results = solr.search('*:*', start=1 * 10, rows=10)
    print(results.docs)
    
    # 返回第三页
    results = solr.search('*:*', start=2 * 10, rows=10)
    print(results.docs)

##### 2.3深分页 (基于排序进行) #####

# https://blog.csdn.net/weixin_42257250/article/details/97107933
    # https://blog.csdn.net/asdfsadfasdfsa/article/details/80072533
    # results = solr.search(q="""
    # *:*
    # &sort=id desc
    # &cursorMark=*
    # """)
    results = solr.search(q='*:*', sort="id asc", cursorMark="*")
    
    # 获取原始数据
    # raw_rep = results.raw_response
    scroll_size  = len(results.docs)
    data = results.docs
    print(data)
    
    # 获取游标
    nextCursorMark = results.nextCursorMark
    
    
    while (scroll_size > 0):
        results = solr.search(q='*:*', sort="id asc", cursorMark=nextCursorMark)
        nextCursorMark= results.nextCursorMark
        data = results.docs
        scroll_size = len(data)
        print(data)

##### 2.4模糊查询 (最普遍使用的模糊查询就是使用通配符) #####

# https://blog.csdn.net/qq_22929803/article/details/46924487
    # 查询文章中含有cocktail_py的字符 似乎默认忽略大小写
    results = solr.search('article:*cocktail_py*')
    print(results.docs)
    
    
    # # 默认term并且忽略大小写
    results = solr.search(q='title:bAnana', )

##### 2.5完全匹配查询 #####

# https://blog.csdn.net/babydavic/article/details/8657277
    # 将关键字 用 双引号 包起来
    results = solr.search('article:"Cocktail_py1018"')

##### 2.6聚合查询 #####

# https://blog.csdn.net/vtopqx/article/details/76099078
    # http://localhost:8983/solr/solr_select/query?q=*:*&facet=on&facet.field=name
    params = { 
        "facet": "on",
        "facet.field": "id",
    }
    results = solr.search(q="*:*", **params)

更多  
https://blog.csdn.net/li295214001/article/details/46044841  
https://blog.csdn.net/lyf\_ldh/article/details/82733824  
https://blog.csdn.net/opoppinboy/article/details/75907414  
https://blog.csdn.net/sethcss/article/details/84999615  
https://pypi.org/project/pysolr/  
https://blog.csdn.net/u013160017/article/details/81037279

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0NvY2t0YWlsX3B5_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20200526162635824.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0NvY2t0YWlsX3B5,size_16,color_FFFFFF,t_70