爬取酷狗音乐Top500榜单

Posted 2021-08-26 茶·凯碧

import requests
from bs4 import BeautifulSoup
headers = {
    \'User-Agent\': \'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/90.0.4430.93 Safari/537.36\'
}
#需求：爬取酷狗TOP500
#需要的字段 排名、歌名、歌曲时长、歌手
def get_info(url):
    resp = requests.post(url,headers=headers)
    content = resp.content.decode(\'utf-8\')
    soup = BeautifulSoup(content,\'lxml\')
    rankings = soup.select(\'span.pc_temp_num\')                  #获取排名
    songs = soup.select(\'div.pc_temp_songlist > ul > li> a\')    #获取歌名和歌手
    times = soup.select(\'span.pc_temp_tips_r > span\')           #获取时间
    for rank, song, time in zip(rankings, songs, times):
        data = {
            \'排名\' : rank.get_text().strip(),
            \'歌手\' : song.get_text().split(\'-\')[0],
            \'歌名\' : song.get_text().split(\'-\')[1],
            \'时长\' : time.get_text().strip()
        }
        print(data)
if __name__ == \'__main__\':
    urls = [\'https://www.kugou.com/yy/rank/home/{}-8888.html?from=rank\'.format(str(num)) for num in range(1,24)]
    for url in urls:
        get_info(url)