Python爬虫练习

import re
import requests
import os
import time

# 根据歌手的网易云ID爬取其网易云上的歌曲

headers = {
    'User-Agent': 'Chrome/10'
}


def main():
    print('例如：华晨宇的网址是：https://music.163.com/#/artist?id=861777', '\n', 'ID就是：861777。')
    ID = input("请输入歌手ID：")
    url = 'https://music.163.com/artist?id=' + ID
    html = requests.get(url, headers).text
    get_id(html)


def get_id(html):
    finding = re.compile(r'<a href="/song\?id=(\d*)">(.*?)</a></li><li>')
    filename = re.compile(r'<h2 id="artist-name" data-rid=\d* class="sname f-thide sname-max" title=".*?">(.*?)</h2>')
    singers = re.findall(filename, html)[0]
    creat(singers)
    ll = re.findall(finding, html)
    for i in ll:
        savemusic(i[1], i[0])
        time.sleep(0.5)


def creat(singers):  # 创建文件夹
    if not os.path.exists(singers):
        os.mkdir(singers)  # 如果该目录不存在就创建它
    os.chdir(singers)


def savemusic(name, id):  # 保存文件
    url = 'https://music.163.com/song/media/outer/url?id=' + id + '.mp3'
    with open(name + '.m4a', 'wb') as f:
        print('歌曲《', name, '》 下载中***************')
        f.write(requests.get(url=url, headers=headers).content)
        f.close()
        print("《", name, "》下载完成")
        print('')


if __name__ == '__main__':
    main()