酷狗top500的爬虫

 

import requests
from bs4 import BeautifulSoup
import time         #导入相应的库文件

headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36'
                 '(KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'#加入请求头
}

def get_info(url):#④定义获取信息的函数
    wb_data = requests.get(url, headers=headers)
    soup = BeautifulSoup(wb_data.text, "html.parser")

    ranks = soup.select('span.pc_temp_num')
    titles = soup.select('div.pc_temp_songlist > ul > li > a')
    times = soup.select('span.pc_temp_tips_r > span')
    for rank,title,time in zip(ranks, titles, times):#⑤
        data = {
            'rank':rank.get_text().strip(),
            'singer':title.get_text().split('-')[0],
            'song':title.get_text().split('-')[1],#通过split获取歌手和歌曲信息
            'time':time.get_text().strip()
        }
        print(data)#获取爬虫信息并按字典格式打印
if __name__ == '__main__': #程序主入口
    urls = ["http://www.kugou.com/yy/rank/home/{}-8888.html".format(number) for number in range(1, 24)]#构造多页URL,①此处会把urls够造出来一共24条网址
    for url in urls:#②
        get_info(url)#③循环调用，此处会带着第一条url地址，跳转到get_info函数体，执行④和⑤，⑤执行完了之后，会再次跳转到这里
        time.sleep(1)#⑥然后执行这个延时函数，这里延时函数执行完了之后，会跳转到②处进行再次循环