爬取网易云音乐飙升榜（100首）

爬取网易云音乐飙升榜（100首）

目的

• 学习request模块的使用
• 练习爬虫的机制
• 仅学习使用，不做非法事情

爬取页面

• 网易云音乐飙升榜不定期会更换

代码

# -*- coding:utf-8 -*-
import os
import requests
from lxml import etree
import threading


class Get_Music:
    def __init__(self):
        self.song_url = 'https://music.163.com/discover/toplist'
        self.headers = {
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64)',
            'referer': 'https://music.163.com/'
        }

        # 定义两个列表分别存储歌曲名称和歌曲的下载链接
        self.song_list = []
        self.download_url = []

    def get_music_url(self):
        response = requests.get(url=self.song_url, headers=self.headers).content.decode()
        html_page = etree.HTML(response)
        # 获取歌曲id和歌名列表
        song_info_list = html_page.xpath('//div/ul[@class="f-hide"]/li')

        # 解析歌曲列表信息
        for item in song_info_list:
            # 获取歌曲名称
            song_name = item.xpath("./a/text()")[0]
            self.song_list.append(song_name)
            # 获取歌名
            song_player_url = item.xpath("./a/@href")[0]
            song_id = song_player_url.split('=')[1]
            # 使用API拼接下载链接
            download_url = 'http://music.163.com/song/media/outer/url?id=' + str(song_id)
            self.download_url.append(download_url)

    def save_file(self, number):
        # 进度条
        try:
            number = int(number)
            if int(number) == 0:
                exit()
            else:
                response = requests.get(url=self.download_url[number - 1], headers=self.headers, stream=True)
                chunk_size = 1024  # 单次下载的数据块大小
                data_count = 0  # 数据已下载的总大小
                content_size = int(response.headers['content-length'])  # 数据需要下载的总大小
                filename = self.song_list[number - 1] + ".mp3"
                with open(f'./musics/{filename}', mode='wb') as f:
                    for data in response.iter_content(chunk_size=chunk_size):
                        f.write(data)
                        done_block = int((data_count / content_size) * 50)
                        data_count = data_count + len(data)
                        now_jd = (data_count / content_size) * 100
                        print("\r %s: [%s%s] %d%% %d/%d" % (filename, done_block * '█', ' ' * (50 - 1 - done_block), now_jd, 1, 1), end="")
        except Exception:
            print("请输入有效数字编号......")

    def main(self):
        # 检测是否创建存放音频文件的目录
        if not os.path.exists('./musics'):
            os.mkdir("./musics")

        self.get_music_url()
        print("----------------------------------------")
        print('编号\t\t', '名称')
        for item in self.song_list:
            print(self.song_list.index(item) + 1, '\t\t', item)
        print('----------------------------------------')
        # 启动多线程下载
        number = input('请输入歌曲编号,回车即可下载(退出请按:0): ')
        threading.Thread(target=self.save_file, args=(number,)).start()


if __name__ == '__main__':
    a = Get_Music()
    a.main()