Python爬虫实现千千音乐歌曲爬取

1.导入python模板

import requests
import json
from pprint import pprint
import os

2.创建目录及文件夹方法

#创建目录方法
k=os.path.exists('千千音乐')
if k==False:
    # 没有才创建
    os.makedirs('千千音乐')
#创建文件方法
if os.path.exists('千千音乐/{}.mp3'.format(music_url['data']['title'])):
    print('true')
else:
	print('false')

3.获取同一分类下的所有歌曲

在此只展示一个分类，其他分类在千千音乐网页中查看

# url为当前分类下请求歌曲数据的路径
url='https://music.taihe.com/v1/song/info?sign=56cdab3b9092cbdd870e5a79e1a28a01&appid=16073360&TSID=T10049736422%2CT10053603750%2CT10053704552%2CT10055686712%2CT10040725440%2CT10049734100%2CT10056561270%2CT10049556116%2CT10058507148%2CT10038961805%2CT10049729058%2CT10049742477%2CT10054676204%2CT10051577859%2CT10048305736%2CT10054385057%2CT10044389725%2CT10051194799%2CT10053650317%2CT10057519284%2CT10044779449%2CT10038920637%2CT10054113223%2CT10038826793%2CT10054000106%2CT10038626780%2CT10049739231%2CT10049467977%2CT10052929701%2CT10040588896%2CT10049813516%2CT10049813517%2CT10049813518%2CT10049783488%2CT10040594947%2CT10040396162%2CT10052868574%2CT10053091729%2CT10038626778%2CT10044857774%2CT10044812250%2CT10044852766%2CT10044808426%2CT10044820931%2CT10044879237%2CT10044875830%2CT10044818822%2CT10044868541%2CT10044849927%2CT10044861457%2CT10044850274%2CT10044830319%2CT10044874276%2CT10044881722%2CT10044833443&timestamp=1609762305'
# str_url为每一首歌曲的TSID获取所对应的歌曲下载链接
str_url='https://music.taihe.com/v1/song/tracklink?sign=f0de68957c8aa94f2310863d8fbf0bed&appid=16073360&TSID=T10044833443&timestamp=1609762306'
req=requests.get(url=url)
req_str=req.content.decode()
# dict_req为当前分类下的歌曲数据
# 调用json_loads()方法将获取的json字符串转换为字典
dict_req=json.loads(req_str)['data']

#遍历所获取的数据，解析出每一首歌曲的TSID，通过TSID获取对应的歌曲下载链接res1
for i in dict_req:  tricklink=requests.get('https://music.taihe.com/v1/song/tracklink?TSID={}&timestamp=1609762306'.format(i['TSID']))
    music_url=json.loads(tricklink.text)
    # print(tricklink.status_code)
    # pprint(music_url['data'])
    if 'path' in music_url['data']:
        res1 =music_url['data']['path']
    else:
        res1 =music_url['data']['trail_audio_info']['path']
    print(music_url['data']['title'])
    print(res1)
#创建歌曲文件
    if os.path.exists('千千音乐/{}.mp3'.format(music_url['data']['title'])):
        print('true')
        pass
    else:
        print('false')
        #'wb'表示以二进制流下载歌曲
        with open(r'千千音乐/{}.mp3'.format(music_url['data']['title']), 'wb') as file:  # 保存到本地的文件名
            file.write(requests.get(url=res1).content)
            file.flush()

4.知道第3步的歌曲下载思路后，下载所有分类下的歌曲

import requests
import json
from pprint import pprint
import os
num = eval(input('请输入你想下载歌曲的种类数量'))
# 创建存放歌曲的文件夹
if not os.path.exists('千千音乐全爬虫'):
    os.makedirs('千千音乐全爬虫')
# url为获取所有分类的歌曲数据，其中pageSize为想下载的分类数量
url='https://music.taihe.com/v1/tracklist/list?sign=89d9c9b950b010c1d043434e7999d89b&subCateId=2376&pageSize={}'.format(num)
req=requests.get(url=url)
# decode 将类似于\\U8650的数据解码
html=req.text.encode('utf-8').decode("unicode-escape")
# print(type(html))
# json字符串转换，添加strict=False意为在非严格，防止报错
music_url=json.loads(html,strict=False)
url_data=music_url['data']['result']
for items in url_data:
    dirsname=items['title'].replace('|','')
    # print(dirsname)
    # print(i,item['id'],item['desc'])
    # 创建每个分类的目录，如果分类已存在，则不重复下载
    if not os.path.exists('千千音乐全爬虫/{}'.format(dirsname)):
        os.makedirs('千千音乐全爬虫/{}'.format(dirsname))
        print('以创建{}目录，下载中...'.format(dirsname))
 		# https://music.taihe.com/v1/tracklist/info?sign=955b1cf7feb748c62e86089f8f4aebd4&id=271713&pageSize=50           
        get_tsid=requests.get(url='https://music.taihe.com/v1/tracklist/info?sign=955b1cf7feb748c62e86089f8f4aebd4&id={}&pageSize=50'.format(items['id']))
        # print(get_tsid.text)
        list_tsid=json.loads(get_tsid.text,strict=False)
        # print(list_tsid['data']["trackList"])
        for item in list_tsid['data']["trackList"]:
            # print(item['TSID'])
            tricklink = requests.get(
                'https://music.taihe.com/v1/song/tracklink?TSID={}&timestamp=1609762306'.format(item['TSID']))
            print(tricklink.status_code)
            music_url = json.loads(tricklink.text)
            # print(tricklink.status_code)
            # pprint(music_url['data'])
            if 'path' in music_url['data']:
                res1 = music_url['data']['path']
            else:
                res1 = music_url['data']['trail_audio_info']['path']
            # print(music_url['data']['title'])
            # print(res1)
            if os.path.exists('千千音乐全爬虫/{}/{}.mp3'.format(dirsname,music_url['data']['title'])):
                # print('true')
                pass
            else:
                # print('false')
                with open(r'千千音乐全爬虫/{}/{}.mp3'.format(dirsname,music_url['data']['title']), 'wb') as file:  # 保存到本地的文件名
                    file.write(requests.get(url=res1).content)
                    print('已下载{}歌曲'.format(music_url['data']['title']))
                    file.flush()
   
    else:
        print('已存在{}目录，跳过创建'.format(dirsname))

5.运行结果

在此个人只下载了43个分类下的歌曲，共1048首音乐，因为部分音乐是试听歌曲，无法完全下载，可以通过对下载的每首歌曲进行判断，筛选出完整的歌曲。