Python 爬取网易云音乐

import requests
from bs4 import BeautifulSoup
import urllib.request
import re
import os

headers = {
    'Referer': 'http://music.163.com/',
    'Host': 'music.163.com',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.75 Safari/537.36',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
}

url = 'https://music.163.com/discover/playlist/'

base_url = 'https://music.163.com'

save_path = 'D:\\Download\\music\\wangyiyun\\'



def get_song(music,saveurl):
    try:
        musicUrl = 'http://music.163.com/song/media/outer/url' + music[0][5:] + '.mp3'
        name = music[1]
        if(not os.path.exists(saveurl+"\\"+music[1] + '%s.mp3')):
            urllib.request.urlretrieve(musicUrl, saveurl+"\\"+music[1] + '%s.mp3' % name)
        else:
            print('%s 歌曲已存在',name)
    except Exception as e:
        pass

def get_song_url(url):
    playurl = base_url + url[1]
    s=requests.session()
    response = s.get(playurl, headers=headers).text
    # <li><a href="/song?id=210049">布拉格广场</a></li>
    ex = r'<li><a.*? href="(.*?)">(.*?)</a></li>'
    playurllist = re.findall(ex, response, re.I | re.M)
    return playurllist

def get_url_list():
    # 获取页面内容`
    s = requests.session()
    response = s.get(url, headers=headers).text
    # <a title="朋友请听好 我会陪你笑看风雨" href="/playlist?id=4899739055" class="msk"></a>
    ex = r'<a\s+title="(.*?)"\s+href="(.*?)"\s+class="msk"></a>'
    url_list = re.findall(ex, response, re.I | re.M)
    # ('朋友请听好 我会陪你笑看风雨', '/playlist?id=4899739055')
    return url_list

if __name__ == '__main__':

    if not os.path.isdir(save_path):  # 目录不存在就创建
        os.makedirs(save_path, exist_ok=True)
    page = 1
    count = 1
    urllist = get_url_list()
    for url in urllist:
       save_url = save_path + url[0]
       if not os.path.isdir(save_url):  # 目录不存在就创建
           os.makedirs(save_url, exist_ok=True)
       playlist = get_song_url(url)
       for music in playlist:
           get_song(music,save_url)
           print('本次成功下载 第%d页 第%d个歌曲! %s' % (page,count,music[1]))
           count+=1
       page += 1