python实现千千音乐下载

1.目的

对于千千音乐的首页的歌单进行爬取,创建以歌单为名字的文件夹并且下载歌单内的所有歌曲保存至本地

2.介绍功能介绍

不要加多进程与多线程进去增加千千音乐的负担,只做类人爬取,对于技术的练习
爬取内容请不要用做商业用途

import os
import time
import json
import requests
from lxml import etree


class QianQianMusic(object):
    def __init__(self, name):
        self.url = 'http://music.taihe.com/search?key={name}'.format(name=name)
        self.api_url_temp = 'http://musicapi.taihe.com/v1/restserver/ting?method=baidu.ting.song.playAAC&format=jsonp\
        &songid={song_id}&_={t}'
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) \
            Chrome/77.0.3865.90 Safari/537.36',
        }
        self.t = int(time.time() * 1000)

    def get_music_info(self):
        response = requests.get(self.url, headers=self.headers)
        html_text = response.content.decode()
        html = etree.HTML(html_text)
        lis = html.xpath('//div[@class="search-song-list song-list song-list-hook"]/ul/li')
        music_infos = []
        for li in lis:
            href = li.xpath('.//span[@class="music-icon-hook"]/a/@href')
            if href:
                musicicon = li.xpath('.//span[@class="music-icon-hook"]/@data-musicicon')[0]
                song_id = json.loads(musicicon)['id']
                title = li.xpath('.//span[@class="song-title"]/a//text()')
                title = ''.join(title)
                author = li.xpath('.//span[@class="author_list"]/a/text()')[0]
                item = (song_id, title, author)
                music_infos.append(item)
        return music_infos

    def choose_music(self, music_infos):
        for music_info in music_infos:
            print(f'歌曲序号: {music_infos.index(music_info) + 1}\t歌曲: {music_info[1]}\t歌手: {music_info[2]}')

        choose_number = input('请输入你要下载歌曲序号:')
        if choose_number.isdigit():
            choose_number = int(choose_number)
            if choose_number <= len(music_infos) and choose_number > 0:
                choose_music = music_infos[choose_number - 1]
                return choose_music
            else:
                exit('输入歌曲序号不存在')
        else:
            exit('输入歌曲序号有误')

    def mkdir(self, music_name):
        music_dir = os.path.join(os.curdir, 'music')
        if not os.path.isdir(music_dir):
            os.mkdir(music_dir)
        file_name = music_name + '.mp3'
        file_path = os.path.join(music_dir, file_name)
        return file_path

    def get_music_url(self, music_song_id, ):
        data = requests.get(self.api_url_temp.format(song_id=music_song_id, t=self.t), headers=self.headers).json()
        return data['bitrate']['file_link']

    def download(self, music_url, music_name, file_path):
        response = requests.get(music_url, headers=self.headers)
        with open(file_path, 'wb') as f:
            print(f'正在下载歌曲:{music_name}')
            for ret in response.iter_content(1024):
                f.write(ret)
            print(f'歌曲下载完成:{music_name}')

    def main(self):
        music_infos = self.get_music_info()
        choose_music = self.choose_music(music_infos)
        music_song_id = choose_music[0]
        music_name = choose_music[1]
        music_url = self.get_music_url(music_song_id)
        file_path = self.mkdir(music_name)
        self.download(music_url, music_name, file_path)


if __name__ == "__main__":
    music_name = input('请输入你要下载的歌曲:')
    qianqian = QianQianMusic(music_name)
    qianqian.main()

以上就是全部的代码