Python 爬取网易云歌手的50首热门作品

import json
import os
import time

from bs4 import BeautifulSoup
import requests


class Music:
    """
    下载网易云歌手排行前50的歌曲
    """

    def __init__(self, init_url, download):
        self.init_url = init_url
        self.download = download

    def mkdir(self, path):
        """
        创建文件夹
        :param path:
        :return:
        """
        path = path.strip()
        if not os.path.exists(path):  # 判断此文件夹存不存在
            print(‘创建 ‘, path, ‘文件夹‘)
            os.makedirs(path)
            return True
        else:
            print(path, ‘文件夹已存在，无需创建‘)
            return False

    def download_video(self, video_url, name):
        """
        下载
        :param video_url: 音乐的链接
        :param name: 歌曲名称
        :return:
        """
        path = self.download + "\\" + name + ‘.mp3‘  # 拼接保存后的文件路径
        # print(path)
        headers = {
            "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.116 Safari/537.36",
        }
        header = {
            "Origin": "http://music.163.com/",
            "Referer": video_url,  # 请求头必须添加referer
        }
        headers.update(header)  # 更新头部信息
        size = 0
        start = time.time()
        try:
            result = requests.get(video_url, headers=headers, stream=True, verify=False)
            # print(‘result‘, result)
            with open(path, "wb") as f:
                for chunk in result.iter_content(1024):
                    f.write(chunk)
                    f.flush()  # 清空缓存
                    size = size + len(chunk)
            print("已下载：%0.2f Mb" % (size / (1024 * 1024)))
        except Exception as e:
            print("url下载错误：%s" % video_url)
            print(e)
        stop = time.time()
        print("下载完成，耗时：%0.2f秒" % (stop - start))

    def spider(self):
        r = requests.get(self.init_url).text
        soupObj = BeautifulSoup(r, ‘lxml‘)
        song_ids = soupObj.find(‘textarea‘).text
        # print(song_ids)
        jobj = json.loads(song_ids)
        list01 = []
        for item in jobj:
            dict01 = {}
            # print(item[‘id‘])  # 歌曲id
            # print(item[‘name‘])  # 歌曲名称
            dict01[‘name‘] = item[‘name‘]
            dict01[‘id‘] = item[‘id‘]
            list01.append(dict01)

        print(list01)
        len_list = len(list01)
        print("一共", len_list, "首歌曲")
        self.mkdir(self.download)
        print(‘开始切换文件夹‘)
        os.chdir(self.download)
        for i in list01:
            name = i[‘name‘]
            id = i[‘id‘]
            song_url = "http://music.163.com/song/media/outer/url?id=" + str(id) + ".mp3"
            print(song_url)  # 最终下载的音乐链接
            self.download_video(song_url, name)  # 下载
            len_list = len_list - 1
            print("还剩", len_list, "首歌曲需要下载")


if __name__ == ‘__main__‘:
    #     init_url = ‘https://music.163.com/artist?id=5781‘  # 薛之谦
    #     download = ‘C:\\Users\\AIERXUAN\\Desktop\\BeautifulPicture\\Music\\xzq‘  # 保存地址
    # init_url = ‘https://music.163.com/artist?id=12429072‘  # 隔壁老樊
    # download = ‘C:\\Users\\AIERXUAN\\Desktop\\BeautifulPicture\\Music\\gblf‘  # 保存地址
    # init_url = ‘https://music.163.com/artist?id=861777‘  # 华晨宇
    # download = ‘C:\\Users\\AIERXUAN\\Desktop\\BeautifulPicture\\Music\\hcy‘  # 保存地址
    # init_url = ‘https://music.163.com/artist?id=6452‘  # 周杰伦
    # download = ‘C:\\Users\\AIERXUAN\\Desktop\\BeautifulPicture\\Music\\zjl‘  # 保存地址
    # init_url = ‘https://music.163.com/artist?id=2116‘  # 陈奕迅
    # download = ‘C:\\Users\\AIERXUAN\\Desktop\\BeautifulPicture\\Music\\cyx‘  # 保存地址
    # init_url = ‘https://music.163.com/artist?id=3684‘  # 林俊杰
    # download = ‘C:\\Users\\AIERXUAN\\Desktop\\BeautifulPicture\\Music\\ljj‘  # 保存地址

    # init_url = ‘https://music.163.com/artist?id=12138269‘  # 毛不易
    # download = ‘C:\\Users\\AIERXUAN\\Desktop\\BeautifulPicture\\Music\\mby‘  # 保存地址

    # init_url = ‘https://music.163.com/artist?id=4292‘  # 李荣浩
    # download = ‘C:\\Users\\AIERXUAN\\Desktop\\BeautifulPicture\\Music\\lrh‘  # 保存地址
    # init_url = ‘https://music.163.com/artist?id=30116848‘  # 阿冗
    # download = ‘C:\\Users\\AIERXUAN\\Desktop\\BeautifulPicture\\Music\\ar‘  # 保存地址
    # init_url = ‘https://music.163.com/artist?id=5771‘  # 许嵩
    # download = ‘C:\\Users\\AIERXUAN\\Desktop\\BeautifulPicture\\Music\\xs‘  # 保存地址
    # init_url = ‘https://music.163.com/artist?id=6472‘  # 张杰
    # download = ‘C:\\Users\\AIERXUAN\\Desktop\\BeautifulPicture\\Music\\zj‘  # 保存地址
    # init_url = ‘https://music.163.com/artist?id=5538‘  # 汪苏泷
    # download = ‘C:\\Users\\AIERXUAN\\Desktop\\BeautifulPicture\\Music\\wsl‘  # 保存地址
    # init_url = ‘https://music.163.com/artist?id=1197168‘  # 徐秉龙
    # download = ‘C:\\Users\\AIERXUAN\\Desktop\\BeautifulPicture\\Music\\xbl‘  # 保存地址
    init_url = ‘https://music.163.com/artist?id=30284835‘  # 枯木逢春
    download = ‘C:\\Users\\AIERXUAN\\Desktop\\BeautifulPicture\\Music\\kmfc‘  # 保存地址

    s = Music(init_url, download)
    s.spider()