手把手教你使用Flask搭建ES搜索引擎(预备篇)

pip install elasticsearch

def __init__(self, index_type: str, index_name: str, ip="127.0.0.1"):

    # self.es = Elasticsearch([ip], http_auth=('username', 'password'), port=9200)
    self.es = Elasticsearch("localhost:9200")
    self.index_type = index_type
    self.index_name = index_name

def get_doc(self, uid):
    return self.es.get(index=self.index_name, id=uid)

def insert_one(self, doc: dict):
    self.es.index(index=self.index_name, doc_type=self.index_type, body=doc)

def insert_array(self, docs: list):
    for doc in docs:
        self.es.index(index=self.index_name, doc_type=self.index_type, body=doc)

def search(self, query, count: int = 30):
    dsl = {
        "query": {
            "multi_match": {
                "query": query,
                "fields": ["title", "content", "link"]
            }
        },
        "highlight": {
            "fields": {
                "title": {}
            }
        }
    }
    match_data = self.es.search(index=self.index_name, body=dsl, size=count)
    return match_data

def __search(self, query: dict, count: int = 20): # count: 返回的数据大小
    results = []
    params = {
        'size': count
    }
    match_data = self.es.search(index=self.index_name, body=query, params=params)
    for hit in match_data['hits']['hits']:
        results.append(hit['_source'])

    return results

def delete_index(self):
    try:
        self.es.indices.delete(index=self.index_name)
    except:
        pass

from elasticsearch import Elasticsearch


class elasticSearch():

    def __init__(self, index_type: str, index_name: str, ip="127.0.0.1"):

        # self.es = Elasticsearch([ip], http_auth=('elastic', 'password'), port=9200)
        self.es = Elasticsearch("localhost:9200")
        self.index_type = index_type
        self.index_name = index_name

    def create_index(self):
        if self.es.indices.exists(index=self.index_name) is True:
            self.es.indices.delete(index=self.index_name)
        self.es.indices.create(index=self.index_name, ignore=400)

    def delete_index(self):
        try:
            self.es.indices.delete(index=self.index_name)
        except:
            pass

    def get_doc(self, uid):
        return self.es.get(index=self.index_name, id=uid)

    def insert_one(self, doc: dict):
        self.es.index(index=self.index_name, doc_type=self.index_type, body=doc)

    def insert_array(self, docs: list):
        for doc in docs:
            self.es.index(index=self.index_name, doc_type=self.index_type, body=doc)

    def search(self, query, count: int = 30):
        dsl = {
            "query": {
                "multi_match": {
                    "query": query,
                    "fields": ["title", "content", "link"]
                }
            },
            "highlight": {
                "fields": {
                    "title": {}
                }
            }
        }
        match_data = self.es.search(index=self.index_name, body=dsl, size=count)
        return match_data

import json
from datetime import datetime
import pymongo
from app.elasticsearchClass import elasticSearch

client = pymongo.MongoClient('127.0.0.1', 27017)
db = client['spider']
sheet = db.get_collection('Spider').find({}, {'_id': 0, })

es = elasticSearch(index_type="spider_data",index_name="spider")
es.create_index()

for i in sheet:
    data = {
            'title': i["title"],
            'content':i["data"],
            'link': i["link"],
            'create_time':datetime.now()
        }

    es.insert_one(doc=data)

import requests
import re
import time

exist_urls = []
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.62 Safari/537.36',
}

def get_link(url):
    try:
        response = requests.get(url=url, headers=headers)
        response.encoding = 'UTF-8'
        html = response.text
        link_lists = re.findall(&#39;.*?<a target=_blank href="/item/([^:#=<>]*?)".*?</a>&#39;, html)
        return link_lists
    except Exception as e:
        pass
    finally:
        exist_urls.append(url)


# 当爬取深度小于10层时，递归调用主函数，继续爬取第二层的所有链接
def main(start_url, depth=1):
    link_lists = get_link(start_url)
    if link_lists:
        unique_lists = list(set(link_lists) - set(exist_urls))
        for unique_url in unique_lists:
            unique_url = &#39;https://baike.baidu.com/item/&#39; + unique_url

            with open(&#39;url.txt&#39;, &#39;a+&#39;) as f:
                f.write(unique_url + &#39;\n&#39;)
                f.close()
        if depth < 10:
            main(unique_url, depth + 1)

if __name__ == &#39;__main__&#39;:
    start_url = &#39;https://baike.baidu.com/item/%E7%99%BE%E5%BA%A6%E7%99%BE%E7%A7%91&#39;
    main(start_url)

# parse.py
from celery import Celery
import requests
from lxml import etree
import pymongo
app = Celery('tasks', broker='redis://localhost:6379/2')
client = pymongo.MongoClient('localhost',27017)
db = client['baike']
@app.task
def get_url(link):
    item = {}
    headers = {'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.131 Safari/537.36'}
    res = requests.get(link,headers=headers)
    res.encoding = 'UTF-8'
    doc = etree.HTML(res.text)
    content = doc.xpath("//div[@class='lemma-summary']/div[@class='para']//text()")
    print(res.status_code)
    print(link,'\t','++++++++++++++++++++')
    item['link'] = link
    data = ''.join(content).replace(' ', '').replace('\t', '').replace('\n', '').replace('\r', '')
    item['data'] = data
    if db['Baike'].insert(dict(item)):
        print("is OK ...")
    else:
        print('Fail')

from parse import get_url

def main(url):
    result = get_url.delay(url)
    return result

def run():
    with open('./url.txt', 'r') as f:
        for url in f.readlines():
            main(url.strip('\n'))

if __name__ == '__main__':
    run()

celery -A parse worker -l info -P gevent -c 10