[Python知识库]酷狗top100 -python

import requests
import random
import time
from bs4 import BeautifulSoup

datas = []
headers = [
    {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.92 Safari/537.36 Edg/81.0.416.45"},  #微软
    {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.4094.1 Safari/537.36"}, #UC
    {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; rv,2.0.1) Gecko/20100101 Firefox/4.0.1"},  #火狐
    {"User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)"},   #搜狗
    {"User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)"},   #360
    {"User-Agent": "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0"}  #IE9
]
header = random.choice(headers)

def get_info(url):
    res = requests.get(url, header)
    print(res.status_code)
    soup = BeautifulSoup(res.text,'lxml')
    links = soup.select('span.pc_temp_num')
    singers = soup.select('div.pc_temp_songlist>ul>li>a')
    times = soup.select('span.pc_temp_tips_r')

    for link, singer, sing, time in zip(links, singers,singers,times):
        datas.append(
            {
                "lniks" : link.get_text().strip(),
                "singer" : singer.get_text().split('-')[0],
                "sing" : singer.get_text().split('-')[1],
                "time" : time.get_text().strip().split('\t')[-1]
            }
        )
    for i in datas:
        print(i)

if __name__ == "__main__":
    urls = ['https://www.kugou.com/yy/rank/home/{}-8888.html'.format(str(i)) for i in range(1,24)]
    for i in urls:
        get_info(i)
        print('-' *100)
        time.sleep(1)

# https://search.douban.com/movie/subject_search?search_text=%E8%80%81%E5%B8%88&cat=1002
# https://search.douban.com/movie/subject_search?search_text=&cat=1002.