多线程Beatiful Soup爬取斗鱼所有在线主播的信息

#-*- coding:utf-8 -*-
from bs4 import BeautifulSoup
import requests, time ,datetime
import json
import pymongo

class douyu_host_info():
    def __init__(self):
        self.date_time = datetime.datetime.now().strftime(‘%Y-%m-%d_%H-%M‘)
        self.host_url = ‘https://www.douyu.com‘
        self.list_data = []
        self.urls_list = []
        self.headers = {
        ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36‘,
        }
    def get_url(self):
        #获取所有类别的网站地址
        urls = ‘https://www.douyu.com/directory‘
        data = requests.get(urls)
        Soup = BeautifulSoup(data.text, ‘lxml‘)
        list = Soup.select(‘.r-cont.column-cont  dl  dd  ul  li  a‘)
        for i in list:
            urls = i.get(‘href‘)
            self.urls_list.append(urls)
        print (self.urls_list)
        return self.urls_list

    def get_info(self, url):
        #查询所需信息并写调用写入数据库及本地磁盘的函数
        time.sleep(1) #避免服务器承压过大，每个网站爬取设置1s间隔
        url = self.host_url + url
        print (‘Now start open {}‘.format(url))
        get_data = requests.get(url, headers=self.headers)
        Soup = BeautifulSoup(get_data.text, ‘lxml‘)
        names = Soup.select(‘.ellipsis.fl‘)
        nums = Soup.select(‘.dy-num.fr‘)
        titles = Soup.select(‘.mes h3‘)
        hrefs = Soup.select(‘#live-list-contentbox  li  a‘)
        #网站中带directory时只是一个分类页面没有主播信息
        if ‘directory‘ in url:
            pass
        #异常处理，有少数类别的HTML元素有差别，这里就舍弃了
        try:
            category = Soup.select(‘.listcustomize-topcon-msg h1‘)[0].get_text()
        except:
            category = ‘秩名类别‘
        for name, num, href, title in zip(names, nums, hrefs, titles):
            data = {
                ‘类别‘: category,
                ‘主播‘: name.get_text(),
                ‘标题‘: title.get_text().split(‘\n‘)[-1].strip(),
                ‘链接‘: ‘https://www.douyu.com‘ + href.get(‘href‘),
                #把人气指数转换成以万为单位的浮点型，方便后面计算查找
                ‘人气指数‘: float(num.get_text()[:-1]) if ‘万‘in num.get_text() else float(num.get_text())/10000,
            }
            if data[‘人气指数‘] > 2:
                print (data)
                self.w_to_local(data)
                self.w_to_db(data)


    def open_data(self, date_time):
        #需要用到时可以输入指定时间点读取本地保存的数据
        with open(‘D:\douyu_host{}.csv‘.format(date_time), ‘r‘) as r_data:
            r_data = json.load(r_data)
            for i in r_data:
                print (i)

    def w_to_local(self,data):
        #在将数据写入数据库的同时在本地磁盘保存一份
        with open(‘D:\douyu_host{}.csv‘.format(self.date_time), ‘a‘) as w_data:
            json.dump(data, w_data)

    def w_to_db(self, data):
        #将数据写入一个以时间为后缀的数据库表， data需要是字典格式
        client = pymongo.MongoClient(‘localhost‘, 27017)
        walden = client[‘walden_{}‘.format(self.date_time)]
        sheet_tab = walden[‘sheet_tab‘]
        if data is not None:
            sheet_tab.insert_one(data)

    def check_from_db(self, date_time):
        #输入时间从数据库查询相关人气信息
        client = pymongo.MongoClient(‘localhost‘, 27017)
        walden = client[‘walden_{}‘.format(date_time)]
        sheet_tab = walden[‘sheet_tab‘]
        for data in sheet_tab.find({‘人气指数‘:{‘$gte‘:40}}):
            print (data)

#-*- coding:utf-8 -*-
import time
from multiprocessing import Pool
from test0822 import douyu_host_info

douyu = douyu_host_info()


if __name__ == ‘__main__‘:
    #多线程爬取数据
    urls_list = douyu.get_url()
    pool = Pool()
    pool.map(douyu.get_info, urls_list)