3. QQ音乐排行榜

• 只用于技术研究，不允许非法用途

地址：https://y.qq.com/n/ryqq/toplist/4

​​

# 地址1: https://y.qq.com/n/ryqq/toplist/4
# 获取QQ音乐排行榜
# 开发时间 2024/07/12

import requests
from lxml import etree

def get_html():
    url = "https://y.qq.com/n/yqq/toplist/4.html/"
    ## 添加请求头
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36'
    }

    resp = requests.get(url=url,headers=headers)
    data = resp.content.decode()
    return data

def parse_data(data):
    tree = etree.HTML(data)
    data_list = tree.xpath("//ul[@class='songlist__list']/li")
    lst = []
    count = 0
    for item in data_list:
        count = count + 1
        song_name = item.xpath(".//div[@class='songlist__songname']/span[@class='songlist__songname_txt']/a")[1].text
        author = item.xpath(".//div[@class='songlist__artist']/a/text()")[0]
        lst.append((count ,song_name,author))
    return lst

if __name__ == '__main__':
    data = parse_data(get_html())
    print(data)