l线程池抓取lianjia

1. 线程池 的应用

from multiprocessing.dummy import Pool

import requests
from lxml import etree
url="https://sz.lianjia.com/ershoufang/co32/"
# url="https://sz.lianjia.com/ershoufang/pg2co32/"

from multiprocessing.dummy import Pool

headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',

}

import pymongo


res = requests.get(url=url,headers=headers)

class Ljia():

    def __init__(self):

        self.start_url ="https://sz.lianjia.com/ershoufang/co32/"

        self.headers ={
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',

            }
        self.client = pymongo.MongoClient()
        self.collention = self.client.Ljia.lianjia


    def get_content(self,url):

        # 提取数据
        html = requests.get(url,headers=self.headers)

        tree = etree.HTML(html.text)

        li_list=tree.xpath('//ul[@class="sellListContent"]/li')

        for li in li_list:
            item={}
            item['title'] =li.xpath(".//div[@class='title']/a/text()")[0]
            item['detail_url'] = li.xpath(".//div[@class='houseInfo']/a/@href")[0]
            item['houseInfo'] =li.xpath(".//div[@class='houseInfo']//text()")
            item['houseInfo'] =[i.strip() for i in item['houseInfo'] if i.strip()]
            item['houseInfo'] = ''.join(item['houseInfo'])
            item['totalPrice'] = li.xpath(".//div[@class='totalPrice']//text()")
            item['totalPrice'] = [i.strip()for i in item['totalPrice'] if i.strip()]
            item['totalPrice'] = ''.join(item['totalPrice'])
            item['Price'] = li.xpath(".//div[@class='unitPrice']/span/text()")[0]
            item['followInfo'] =li.xpath(".//div[@class='followInfo']//text()")
            item['followInfo'] = [i.strip() for i in item['followInfo'] if i.strip()]
            item['followInfo'] = ''.join( item['followInfo'])

            print(item)


            return item



    def  get_page_url(self):

        # 生成待抓取的url

        yield self.start_url

        for i in range(2,101):

            url = "https://sz.lianjia.com/ershoufang/pg%sco32/"%i

            print('正在抓取:=============%s'%url)


            yield url

    def save_data(self,item):
        # 保存数据
        if item:

            self.collention.insert(item)

        else:
            print('数据不存在===========')



    def run(self):

        pool = Pool(5)
        # 线程池进行抓取数据
        data = pool.map(self.get_content,self.get_page_url())
        # 线程池进行存储
        pool.map(self.save_data,data)




if __name__ == '__main__':


    lian_jia = Ljia()

    lian_jia.run()