python爬虫三

爬取酷狗音乐排行榜

import requests
from bs4 import BeautifulSoup
import re
import time
import lxml
class Spider():
    url='https://www.kugou.com/yy/rank/home/%7B%20%7D-8888.html'
    headers = {
    
    'User-Agent': 'Mozilla/5.0 ' \
                 '(Windows NT 10.0; Win64; x64' \
                 ') AppleWebKit/537.36 (KHTML,' \
                 ' like Gecko) Chrome/79.0.3' \
                 '945.88 Safari/537.36'
                  }
    def __init__(self):
        htmls=requests.get(Spider.url,headers=Spider.headers)
        soup=BeautifulSoup(htmls.text,'lxml')
        self.ranks=soup.select('span.pc_temp_num')
        self.titles=soup.select('div.pc_temp_songlist > ul > li > a')
        self.times=soup.select('span.pc_tem'
                          'p_tips_r > span')

    def __analyse(self):
        self.datas=[]
        for rank,title,time in zip(self.ranks,self.titles,self.times):
            data={
    
    
                'rank':rank.get_text().strip(),
                'title':title.get_text().split('-')[0],
                'time': time.get_text().strip()
            }
            self.datas.append(data)
        return self.datas

    def __refine(self,datas):
        for data in datas:
            print(
                data['rank']+
                '~~~'+
                data['title']+
                '~~~'+
                data['time']
            )
            
    def go(self):
        datas=self.__analyse()
        self.__refine(datas)
        
spider=Spider()
spider.go()