爬取酷狗网络红歌榜 基于python--BeautifulSoup库

爬取酷狗网络红歌榜 基于python–BeautifulSoup库，我们要爬取酷狗网络红歌榜里的排名、歌手、歌曲名、播放时间信息。
代码如下：

import requests
from bs4 import BeautifulSoup
from time import sleep
#使用header是用于伪装为浏览器，让爬虫更稳定
Headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.67 Safari/537.36'
}
#定义获取信息的函数
def get_info(url):
    wd_data = requests.get(url,headers=Headers)
    soup = BeautifulSoup(wd_data.text,'lxml')
    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):
        data = {
            'rank':rank.get_text().strip(),
            'singer':title.get_text().split('-')[0],     #通过split获取歌手和歌曲的信息
            'song':title.get_text().split('-')[1],
            'time':time.get_text().strip()
        }
        print(data)
if __name__ == '__main__':
    try:
        urls = ['http://www.kugou.com/yy/rank/home/{}-23784.html?from=rank'.format(number) for number in range(1,11)]
        for url in urls:
            get_info(url)
    except ConnectionError:
        print('连接失败，请重新再运行一次')

我们只爬虫10页的数据，运行结果部分数据截图如下：