Elasticsearch之pythonAPI简单使用

elasticsearch自动补全建议功能

数据入库操作

ESmapping要求

PUT music
{
    "mappings": {
        "_doc" : {
            "properties" : {
                "suggest" : {
                    "type" : "completion"
                },
                "title" : {
                    "type": "keyword"
                }
            }
        }
    }
}

DocType类

from elasticsearch_dsl import DocType, Date, Nested, Boolean, \
    analyzer, InnerObjectWrapper, Completion, Keyword, Text, Integer

from elasticsearch_dsl.analysis import CustomAnalyzer as _CustomAnalyzer

from elasticsearch_dsl.connections import connections
connections.create_connection(hosts=["localhost"])

class CustomAnalyzer(_CustomAnalyzer):
    """
        避免ik_analyzer参数传递时会报错的问题
    """

    def get_analysis_definition(self):
        return {}

ik_analyzer = CustomAnalyzer("ik_max_word", filter=["lowercase"])

class ArticleType(DocType):

    suggest = Completion(analyzer=ik_analyzer)

    ... 

Items类

from models.es_types import ArticleType
from elasticsearch_dsl.connections import connections
es = connections.create_connection(ArticleType._doc_type.using)

def gen_suggests(index, info_tuple):
    # 根据字符串生成搜索建议数组
    used_words = set()
    suggests = []
    for text, weight in info_tuple:
        if text:
            # 调用es的analyze接口分析字符串
            words = es.indices.analyze(index=index, analyzer="ik_max_word", params={'filter':["lowercase"]}, body=text)
            anylyzed_words = set([r["token"] for r in words["tokens"] if len(r["token"])>1])
            new_words = anylyzed_words - used_words
        else:
            new_words = set()

        if new_words:
            suggests.append({"input":list(new_words), "weight":weight})

class JobBoleArticleItem(scrapy.Item):

    ...

    def save_to_es(self):

        ...

        article.suggest = gen_suggests(ArticleType._doc_type.index, ((article.title,10),(article.tags, 7)))

        article.save()

        redis_cli.incr("jobbole_count")

        return

ES搜索语法

POST myindex/_search?pretty
{
    "suggest": {
        "my-suggest": {
            "text": "linux",
            "completion": {
                "field": "suggest",
                "fuzzy": {
                    "fuzziness": 2
                }
            }
        }
    },
    "_source": ["title"]
}

自动补全建议核心代码

# django_views中的写法

from search.models import ArticleType

class SearchSuggest(View):
    def get(self, request):
        key_words = request.GET.get('s','')
        re_datas = []
        if key_words:
            s = ArticleType.search()
            s = s.suggest('my_suggest', key_words, completion={
                "field":"suggest", "fuzzy":{
                    "fuzziness":2
                },
                "size": 10
            })
            suggestions = s.execute_suggest()
            for match in suggestions.my_suggest[0].options:
                source = match._source
                re_datas.append(source["title"])
        return HttpResponse(json.dumps(re_datas), content_type="application/json")

elasticsearch内容搜索功能

数据入库操作

　　和上面一样

 

搜索核心代码

# django_views中的写法

from elasticsearch import Elasticsearch

client = Elasticsearch(hosts=["127.0.0.1"])

class SearchView(View):

    def get(self, request):
        key_words = request.GET.get("q","")
        s_type = request.GET.get("s_type", "article")
        page = request.GET.get("p", "")
        try:
            page = int(page)
        except:
            page = 1

        start_time = datetime.now()
        response = client.search(
            index= "jobbole",
            body={
                "query":{
                    "multi_match":{
                        "query":key_words,
                        "fields":["tags", "title", "content"]
                    }
                },
                "from":(page-1)*10,
                "size":10,
                "highlight": {
                    "pre_tags": ['<span class="keyWord">'],
                    "post_tags": ['</span>'],
                    "fields": {
                        "title": {},
                        "content": {},
                    }
                }
            }
        )

        end_time = datetime.now()
        last_seconds = (end_time-start_time).total_seconds()
        total_nums = response["hits"]["total"]
        if (page%10) > 0:
            page_nums = int(total_nums/10) +1
        else:
            page_nums = int(total_nums/10)
        hit_list = []
        for hit in response["hits"]["hits"]:
            hit_dict = {}
            if "title" in hit["highlight"]:
                hit_dict["title"] = "".join(hit["highlight"]["title"])
            else:
                hit_dict["title"] = hit["_source"]["title"]
            if "content" in hit["highlight"]:
                hit_dict["content"] = "".join(hit["highlight"]["content"])[:500]
            else:
                hit_dict["content"] = hit["_source"]["content"][:500]

            hit_dict["create_date"] = hit["_source"]["create_date"]
            hit_dict["url"] = hit["_source"]["url"]
            hit_dict["score"] = hit["_score"]

            hit_list.append(hit_dict)

        return render(request, "result.html", {"page":page,
                                            "all_hits":hit_list,
                                            "key_words":key_words,
                                            "total_nums":total_nums,
                                            "page_nums":page_nums,
                                            "last_seconds":last_seconds
                                            })

scrapy框架+django框架组合使用

github项目参考

 https://github.com/holgerd77/django-dynamic-scraper