ElasticSearch+Django打造个人爬虫搜索引擎

ElasticSearch+Django打造个人爬虫搜索引擎

学习至慕课课程

利用ElasticSearch数据库，Python的Django框架，配合scrapy爬虫，打造属于自己的搜索引擎。

Windows10本地运行都OK，docker服务器环境配置到一半发现Java运行内存不够了。。留下了贫穷的泪水。。

环境配置

Java和nodejs以及redis安装

安装教程很多，动动手百度一下就有，其中Java要求1.8以上版本。

Elasticsearch-RTF安装

链接：https://github.com/medcl/elasticsearch-rtf：

说明：
什么是Elasticsearch-RTF？ RTF是Ready To Fly的缩写，在航模里面，表示无需自己组装零件即可直接上手即飞的航空模型，Elasticsearch-RTF是针对中文的一个发行版，即使用最新稳定的elasticsearch版本，并且帮你下载测试好对应的插件，如中文分词插件等，目的是让你可以下载下来就可以直接的使用（虽然es已经很简单了，但是很多新手还是需要去花时间去找配置，中间的过程其实很痛苦），当然等你对这些都熟悉了之后，你完全可以自己去diy了，跟linux的众多发行版是一个意思。

当前版本 Elasticsearch 5.1.1

Windows下启动

cd elasticsearch/bin
elasticsearch.bat

浏览器打开127.0.0.1:9200

elasticsearch-head安装

链接：https://github.com/mobz/elasticsearch-head

说明：elasticsearch集群的web前端

Windows下运行：

cd elasticsearch-head
npm install
npm run start

浏览器打开127.0.0.1:9100

Kibana安装

链接：https://www.elastic.co/cn/downloads/past-releases#kibana

说明：Kibana是一个针对Elasticsearch的开源分析及可视化平台，用来搜索、查看交互存储在Elasticsearch索引中的数据。

下载版本：5.1.2（对应elasticsearch版本）

Windows下运行：

cd kibana-5.1.2-windows-x86\bin
kibana.bat

浏览器打开127.0.0.1:5601

scrapy爬虫

需安装相关库：

pip install elasticsearch-dsl

主要model代码，用来创建elasticsearch数据的index和type：

# -*- coding: utf-8 -*-

from elasticsearch_dsl import DocType, Date, 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):
    # 版本问题，需要重新继承CustomAnalyzer，重写get_analysis_definition方法
    def get_analysis_definition(self):
        return {}


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


class ArticleType(DocType):
    """
    # elasticsearch_dsl安装5.4版本
    """
    # 文章类型
    suggest = Completion(analyzer=ik_analyzer)
    title = Text(analyzer="ik_max_word")
    create_date = Date()
    url = Keyword()
    view = Integer()
    tag = Text(analyzer="ik_max_word")
    content = Text(analyzer="ik_max_word")
    url_id = Keyword()

    class Meta:
        index = "pm"  # 数据库名
        doc_type = "article"  # 表名


if __name__ == "__main__":
    data = ArticleType.init()
    print(data)

item数据处理主要代码：

import redis
import scrapy
from articles.model.es_types import ArticleType

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

redis_cli = redis.StrictRedis()


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})

    return suggests


class PmArticlesItem(scrapy.Item):
    # define the fields for your item here like:
    title = scrapy.Field()
    create_date = scrapy.Field()
    url = scrapy.Field()
    content = scrapy.Field()
    view = scrapy.Field()
    tag = scrapy.Field()
    url_id = scrapy.Field()

    def save_to_es(self):
        article = ArticleType()
        article.title = self['title']
        article.create_date = self["create_date"]
        article.content = self["content"]
        article.url = self["url"]
        article.view = self["view"]
        article.tag = self["tag"]
        article.meta.id = self["url_id"]

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

        article.save()

        redis_cli.incr("pm_count")  # redis存储爬虫数量

        return

Pipeline存储主要代码：

class ElasticsearchPipeline(object):
    # 将数据写入到es中
    def process_item(self, item, spider):
        # 将item转换为es的数据
        item.save_to_es()

        return item

Django：

class SearchView(View):
    """
    搜索视图，根据搜索词q和类型s_type返回搜索结果
    """
    def get(self, request):
        key_words = request.GET.get("q", "")
        s_type = request.GET.get("s_type", "article")
        # TODO
        # 根据类型不同，动态取对应的数据库内容

        # 热门搜索设置和排序
        redis_cli.zincrby("search_keywords_set", 1, key_words)  # redis最新版本参数坑
        topn_search = redis_cli.zrevrangebyscore("search_keywords_set", "+inf", "-inf", start=0, num=5)
        
        page = request.GET.get("p", "1")
        try:
            page = int(page)
        except:
            page = 1

        pm_count = redis_cli.get("pm_count")  # 获取爬虫数量
        start_time = datetime.now()
        response = client.search(
            index="pm",
            body={
                "query": {
                    "multi_match": {
                        "query": key_words,
                        "fields": ["tag", "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()  # 搜索计时
        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]  # 取前五百个词
            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,
                                               "pm_count": pm_count,
                                               "topn_search": topn_search})

GitHub：https://github.com/downdawn/eswork