python爬虫下载网抑云歌单音乐

最近开车总感觉车里的车载音乐非常的老土，现在都玩网抑云了，抽空看了一下它的页面，发现音乐好听，还可以下载，闲来无趣，写了个爬虫将榜单上所有的歌曲信息提取并分类下载了一下，效果还不错，比原来的车载音乐丰富多了！ 

import requests
from bs4 import BeautifulSoup
import os


class DownloadMusic(object):
    """
    此程序用来爬取某云音乐所有排行榜音乐，学习使用，严禁商业用途
    """
    def __init__(self):
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0'
        }
        self.url = "https://music.163.com/discover/toplist"  # 框架源代码网址
        self.title_url = {}  # 存放排行榜标题和对应网址

    def parse_html(self):
        """
        解析网页
        :return:
        """
        response = requests.get(url=self.url, headers=self.headers)
        html = BeautifulSoup(response.text, "html.parser")  # 解析框架源码
        a_list = html.select("a")  # 提取所有a标签
        # print(a_list)
        for res_url in a_list:
            if res_url.has_attr("href"):
                url = res_url.attrs["href"]
                if str(url).startswith("/discover/toplist?id="):  # 提取所有排行榜的网址
                    self.title_url[res_url.string] = url  # 将网址和排行榜标题关联成字典的键值对
        del self.title_url[None]  # 添加后出现一个重复网址，键名为None，需要删除

    def ranking_list(self):
        """
        排行榜信息提取
        :return:
        """
        for title_dir, url in self.title_url.items():  # 每次循环下载一个榜单音乐
            song_url = {}  # 用来存放歌曲名和网址，每次循环音乐网址字典都要刷新一次
            # if not os.path.isdir(title_dir):
            #     os.makedirs(title_dir)  # 创建文件夹
            dirct = 'E:\\{}'.format(title_dir)
            if not os.path.isdir(dirct):
                os.makedirs('E:\\{}'.format(title_dir))  # 创建文件夹

            ranking_url = "https://music.163.com" + url  # 拼接单个排行榜网址
            response = requests.get(url=ranking_url, headers=self.headers)
            html = BeautifulSoup(response.text, "html.parser")  # 解析框架源码
            a_list = html.select("a")  # 提取所有a标签
            for res_url in a_list:
                if res_url.has_attr("href"):
                    url = res_url.attrs["href"]
                    if str(url).startswith("/song?id"):  # 提取单个排行榜下面的单个歌曲网址
                        if res_url.string == None or res_url.string.startswith("$"):  # 筛除不合格网址信息
                            continue
                        # http://music.163.com/song/media/outer/url?id=1491137515.mp3 完整的下载地址格式
                        download_url = "http://music.163.com/song/media/outer/url" + url[5:] + ".mp3"  # 拼接单个歌曲下载地址
                        song_url[res_url.string] = download_url  # 将歌曲名和歌曲下载地址关联成字典的键值对
            # print(song_url)
            self.download(title_dir, song_url)  # 调用下载歌曲函数，每次下载一个分类
            # break

    def download(self, title_dir, song_url):
        """
        下载歌曲
        :return:
        """
        long = len(song_url)
        print("{}共有{}首音乐,开始下载！".format(title_dir, long))
        count = 0
        for url_name, url in song_url.items():
            # print(url_name, url)
            # if os.path.isfile(title_dir + "/" + url_name + ".mp3"):
            #     print(url_name + "，本地已存在！")
            #     continue  # 若歌曲已经存在，则无需重新下载
            count += 1
            response = requests.get(url, headers=self.headers, allow_redirects=False)
            try:
                r = requests.get(response.headers['Location'], stream=True)
                size = int(r.headers['content-length'])
                print('\033[0;31m' + str(count) + "/" + str(long) + "  正在下载-" + url_name + "  文件大小:" + str(
                    size) + "字节" + "\033[0m")
                schedule = 0  # 下载进度
                with open('E:\\{}'.format(title_dir) + "/" + url_name + ".mp3", "wb") as f:
                # with open(title_dir + "/" + url_name + ".mp3", "wb") as f:
                    for chunk in r.iter_content(chunk_size=512 * 1024):
                        if chunk:
                            f.write(chunk)
                            schedule += len(chunk)
                            print("\r" + url_name + "--下载进度:" + '%3s' % (str(schedule * 100 // size)) + "%", end='')

                print("\n第{}首音乐《{}》下载成功！".format(count, url_name))
                r.close()
            except Exception as e:
                print(url_name + " 下载出错!" + " 错误信息" + str(e.args))

    def run(self):
        """
        运行主程序
        :return:
        """
        self.parse_html()
        self.ranking_list()


down_music = DownloadMusic()
down_music.run()

效果如下，网速太慢了 ，每个榜单会单独生成一个文件夹，上一个榜单下载完成之后下个榜单才会生成文件夹并下载。