python爬虫怎么爬取付费音乐酷狗 (python爬虫批量下载网易云歌曲代码)

本文主要运用了python的requests库爬取QQ音乐全站歌曲（已下架歌曲无法爬取*载下**，其余歌曲均可实现*载下**）。

环境为：python 3.7+pycharm

首先解释下代码中的几个函数，并且分别是什么作用；

1. get_all_singer()主要是按字母A-Z以及特殊字符#来爬取全站歌手
2. get_genre_singer()主要是遍历当前字母下歌手总页数
3. get_singer_songs()主要是获取当前歌手下歌曲总数并获取*载下**歌曲所需的songmid
4. download_song()主要是用来*载下**歌曲文件到本地

下面贴上代码：（第一次发代码，不规范处欢迎指正批评，但代码经本人测试ok，贴上即可使用，谢谢）

①、get_all_singer()

def get_all_singer():
 # 获取字母A-Z和#的全站歌手
 for key in range(1, 28):
 # 获取当前字母分类歌手页数并转换为列表结构
 url = 'https://u.y.qq.com/cgi-bin/musicu.fcg?data={"singerList":{"module":"Music.SingerListServer",' \
 '"method":"get_singer_list","param":{"area":-100,"sex":-100,"genre":-100,"index": ' \
 + str(key)+',"sin":0,"cur_page":1}}}'
 r = session.get(url)
 total = r.json()['singerList']['data']['total']
 page_num = math.ceil(total/80)
 page_list = [x for x in range(page_num)]
 get_genre_singer(key, page_list)

②、get_genre_singer()

def get_genre_singer(key, page_list):
 # 遍历当前字母分类的总页数
 for p in page_list:
 url = 'https://u.y.qq.com/cgi-bin/musicu.fcg?data={"singerList":{"module":"Music.SingerListServer",' \
 '"method":"get_singer_list","param":{"area":-100,"sex":-100,"genre":-100,"index":' \
 + str(key)+',"sin":' + str((p-1)*80)+',"cur_page":' + str(p) + '}}}'
 r = session.get(url)
 # 遍历每一页的每一个歌手
 for k in r.json()['singerList']['data']['singerlist']:
 singermid = k['singer_mid']
 # 将得到的singer_mid值传入get_singer_songs函数
 get_singer_songs(singermid)

③、get_singer_songs()

def get_singer_songs(singermid):
 url = 'https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg?singermid=' + str(singermid)+'&order=listen' \
 '&begin=0&num=30'
 r = session.get(url)
 print(url)
 # 获取歌手姓名
 song_singer = r.json()['data']['singer_name']
 print(song_singer)
 # 获取歌曲总数
 song_count = r.json()['data']['total']
 print(song_count)
 # 根据歌曲总数计算歌曲页数，每页30首
 page_count = math.ceil(int(song_count)/30)
 # 循环页数，获取每一页歌曲信息
 for p in range(page_count):
 url = 'https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg?singermid=' + str(singermid) +\
 '&order=listen&begin=' + str(p*30) + '&num=30'
 r = session.get(url)
 # 得到每一页的歌曲信息
 music_data = r.json()['data']['list']
 # songname：歌名， ablum：专辑， interval：时长， songmid：歌曲id，用于*载下**音频文件
 song_dict = {}
 for i in music_data:
 song_dict['song_name'] = i['musicData']['songname']
 song_dict['song_ablum'] = i['musicData']['albumname']
 song_dict['song_interval'] = i['musicData']['interval']
 song_dict['song_songmid'] = i['musicData']['songmid']
 song_dict['singer_name'] = song_singer
 # *载下**歌曲
 download_song(song_dict['song_songmid'], song_dict['song_name'])
 # 清空处理
 song_dict = {}

④、download_song()

def download_song(songmid, songname):
 # 获取vkey的purl链接
 url = 'https://u.y.qq.com/cgi-bin/musicu.fcg?data={"req_0":{"module":"vkey.GetVkeyServer","method":"CgiGetVkey","param":\
{"guid":"0","songmid":["'+songmid + '"],"uin":"0"}}}'
 # guid:6946840764
 print(url)
 r = session.get(url)
 song_vkey = r.json()['req_0']['data']['midurlinfo'][0]['purl']
 downloadUrl = 'http://183.240.120.15/amobile.music.tc.qq.com/' + song_vkey
 resp = session.get(downloadUrl)
 print(resp.status_code)
 try:
 with open('F:\Desktop\python\QQMusic\song\\' + songname + '.m4a', 'wb')as f:
 f.write(resp.content)
 print('downloadUrl:', downloadUrl)
 except Exception:
 return 'null'

⑤、主函数，即程序入口

if __name__ == '__main__':
 get_all_singer()

程序运行结果及编译输出截图如下：

①、本地*载下**歌曲文件

②、pycharm编译输出结果

③、编译输出结果

最后贴上全部代码：

# get_all_singer()主要是按字母A-Z以及特殊字符#来爬取全站歌手
# get_genre_singer()主要是遍历当前字母下歌手总页数
# get_singer_songs()主要是获取当前歌手下歌曲总数并获取*载下**歌曲所需的songmid
# download_song()主要是用来*载下**歌曲文件到本地
# by eric.luo
# 2018/11/26
import requests
import math
session = requests.session()
def get_all_singer():
 # 获取字母A-Z和#的全站歌手
 for key in range(1, 28):
 # 获取当前字母分类歌手页数并转换为列表结构
 url = 'https://u.y.qq.com/cgi-bin/musicu.fcg?data={"singerList":{"module":"Music.SingerListServer",' \
 '"method":"get_singer_list","param":{"area":-100,"sex":-100,"genre":-100,"index": ' \
 + str(key)+',"sin":0,"cur_page":1}}}'
 r = session.get(url)
 total = r.json()['singerList']['data']['total']
 page_num = math.ceil(total/80)
 page_list = [x for x in range(page_num)]
 get_genre_singer(key, page_list)
def get_genre_singer(key, page_list):
 # 遍历当前字母分类的总页数
 for p in page_list:
 url = 'https://u.y.qq.com/cgi-bin/musicu.fcg?data={"singerList":{"module":"Music.SingerListServer",' \
 '"method":"get_singer_list","param":{"area":-100,"sex":-100,"genre":-100,"index":' \
 + str(key)+',"sin":' + str((p-1)*80)+',"cur_page":' + str(p) + '}}}'
 r = session.get(url)
 # 遍历每一页的每一个歌手
 for k in r.json()['singerList']['data']['singerlist']:
 singermid = k['singer_mid']
 # 将得到的singer_mid值传入get_singer_songs函数
 get_singer_songs(singermid)
# get_singer_songs(singermid)获取歌手的全部歌曲信息
def get_singer_songs(singermid):
 url = 'https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg?singermid=' + str(singermid)+'&order=listen' \
 '&begin=0&num=30'
 r = session.get(url)
 # print(url)
 # 获取歌手姓名
 song_singer = r.json()['data']['singer_name']
 # print(song_singer)
 # 获取歌曲总数
 song_count = r.json()['data']['total']
 # print(song_count)
 # 根据歌曲总数计算歌曲页数，每页30首
 page_count = math.ceil(int(song_count)/30)
 # 循环页数，获取每一页歌曲信息
 for p in range(page_count):
 url = 'https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg?singermid=' + str(singermid) +\
 '&order=listen&begin=' + str(p*30) + '&num=30'
 r = session.get(url)
 # 得到每一页的歌曲信息
 music_data = r.json()['data']['list']
 # songname：歌名， ablum：专辑， interval：时长， songmid：歌曲id，用于*载下**音频文件
 song_dict = {}
 for i in music_data:
 song_dict['song_name'] = i['musicData']['songname']
 song_dict['song_ablum'] = i['musicData']['albumname']
 song_dict['song_interval'] = i['musicData']['interval']
 song_dict['song_songmid'] = i['musicData']['songmid']
 song_dict['singer_name'] = song_singer
 # *载下**歌曲
 download_song(song_dict['song_songmid'], song_dict['song_name'])
 # 清空处理
 song_dict = {}
def download_song(songmid, songname):
 # 获取vkey的purl链接
 url = 'https://u.y.qq.com/cgi-bin/musicu.fcg?data={"req_0":{"module":"vkey.GetVkeyServer","method":"CgiGetVkey","param":\
{"guid":"0","songmid":["'+songmid + '"],"uin":"0"}}}'
 # guid:6946840764
 # print(url)
 r = session.get(url)
 song_vkey = r.json()['req_0']['data']['midurlinfo'][0]['purl']
 downloadUrl = 'http://183.240.120.15/amobile.music.tc.qq.com/' + song_vkey
 resp = session.get(downloadUrl)
 # print(resp.status_code)
 global num
 try:
 with open('F:\Desktop\python\QQMusic\song\\' + songname + '.m4a', 'wb')as f:
 num = num + 1
 print('---------------正在*载下**第' + str(num) + '首歌----------------')
 f.write(resp.content)
 except Exception as err:
 print(err)
if __name__ == '__main__':
 num = 0 # 计算*载下**歌曲的数量
 get_all_singer()
 # myProcess()

时间：2018/11/26 晚，目前测试*载下**将近400首暂未发现问题；如果使用过程中出现问题欢迎联系我讨论；<初学python爬虫>

2018年12月3日：修改为多线程多进程同时*载下**，下面附上源代码，需要自取。

# get_all_singer()主要是按字母A-Z以及特殊字符#来爬取全站歌手
# get_genre_singer()主要是遍历当前字母下歌手总页数
# get_singer_songs()主要是获取当前歌手下歌曲总数并获取*载下**歌曲所需的songmid
# download_song()主要是用来*载下**歌曲文件到本地
# by eric.luo
# 2018/11/26
import requests
import math
from concurrent.futures import ThreadPoolExecutor, ProcessPoolExecutor
num = 0 # 计算*载下**歌曲的数量
session = requests.session()
def get_all_singer(): # 单线程单进程
 # 获取字母A-Z和#的全站歌手
 for key in range(1, 28):
 # 获取当前字母分类歌手页数并转换为列表结构
 url = 'https://u.y.qq.com/cgi-bin/musicu.fcg?data={"singerList":{"module":"Music.SingerListServer",' \
 '"method":"get_singer_list","param":{"area":-100,"sex":-100,"genre":-100,"index": ' \
 + str(key)+',"sin":0,"cur_page":1}}}'
 r = session.get(url)
 total = r.json()['singerList']['data']['total']
 page_num = math.ceil(total/80)
 page_list = [x for x in range(page_num)]
 get_genre_singer(key, page_list)
def get_genre_singer(key, page_list):
 # 遍历当前字母分类的总页数
 for p in page_list:
 url = 'https://u.y.qq.com/cgi-bin/musicu.fcg?data={"singerList":{"module":"Music.SingerListServer",' \
 '"method":"get_singer_list","param":{"area":-100,"sex":-100,"genre":-100,"index":' \
 + str(key)+',"sin":' + str((p-1)*80)+',"cur_page":' + str(p) + '}}}'
 r = session.get(url)
 # 遍历每一页的每一个歌手
 for k in r.json()['singerList']['data']['singerlist']:
 singermid = k['singer_mid']
 # 将得到的singer_mid值传入get_singer_songs函数
 get_singer_songs(singermid)
# get_singer_songs(singermid)获取歌手的全部歌曲信息
def get_singer_songs(singermid):
 url = 'https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg?singermid=' + str(singermid)+'&order=listen' \
 '&begin=0&num=30'
 r = session.get(url)
 # print(url)
 # 获取歌手姓名
 song_singer = r.json()['data']['singer_name']
 # print(song_singer)
 # 获取歌曲总数
 song_count = r.json()['data']['total']
 # print(song_count)
 # 根据歌曲总数计算歌曲页数，每页30首
 page_count = math.ceil(int(song_count)/30)
 # 循环页数，获取每一页歌曲信息
 for p in range(page_count):
 url = 'https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg?singermid=' + str(singermid) +\
 '&order=listen&begin=' + str(p*30) + '&num=30'
 r = session.get(url)
 # 得到每一页的歌曲信息
 music_data = r.json()['data']['list']
 # songname：歌名， ablum：专辑， interval：时长， songmid：歌曲id，用于*载下**音频文件
 song_dict = {}
 for i in music_data:
 song_dict['song_name'] = i['musicData']['songname']
 song_dict['song_ablum'] = i['musicData']['albumname']
 song_dict['song_interval'] = i['musicData']['interval']
 song_dict['song_songmid'] = i['musicData']['songmid']
 song_dict['singer_name'] = song_singer
 # *载下**歌曲
 download_song(song_dict['song_songmid'], song_dict['song_name'])
 # 清空处理
 song_dict = {}
def download_song(songmid, songname):
 # 获取vkey的purl链接
 url = 'https://u.y.qq.com/cgi-bin/musicu.fcg?data={"req_0":{"module":"vkey.GetVkeyServer","method":"CgiGetVkey","param":\
{"guid":"0","songmid":["'+songmid + '"],"uin":"0"}}}'
 # guid:6946840764
 # print(url)
 r = session.get(url)
 song_vkey = r.json()['req_0']['data']['midurlinfo'][0]['purl']
 downloadUrl = 'http://183.240.120.15/amobile.music.tc.qq.com/' + song_vkey
 resp = session.get(downloadUrl)
 # print(resp.status_code)
 global num
 try:
 with open('F:\Desktop\python\QQMusic\song\\' + songname + '.m4a', 'wb')as f:
 num = num + 1
 print('---------------正在*载下**第' + str(num) + '首歌----------------')
 f.write(resp.content)
 except Exception as err:
 print(err)
# 多线程
def myThread(genre):
 # 获取当前字母分类歌手页数并转换为列表结构
 url = 'https://u.y.qq.com/cgi-bin/musicu.fcg?data={"singerList":{"module":"Music.SingerListServer",' \
 '"method":"get_singer_list","param":{"area":-100,"sex":-100,"genre":-100,"index":' + str(genre) + \
 ',"sin":0,"cur_page":1}}}'
 # print(url)
 r = session.get(url)
 # print(r.status_code)
 total = r.json()['singerList']['data']['total']
 # print(total)
 page_num = math.ceil(total / 80)
 page_list = [x for x in range(page_num)]
 thread_number = 10
 list_interval = math.ceil(len(page_list)/thread_number)
 # 设置线程对象
 Thread = ThreadPoolExecutor(max_workers=thread_number)
 for index in range(thread_number):
 # 计算每条线程应执行的页数
 start_num = list_interval*index
 if list_interval*(index+1) <= len(page_list):
 end_num = list_interval*(index+1)
 else:
 end_num = len(page_list)
 # 每个线程各自执行不同歌手列表页数
 Thread.submit(get_genre_singer, genre, page_list[start_num:end_num])
# 多进程
def myProcess():
 with ProcessPoolExecutor(max_workers=27) as executor:
 for i in range(1, 3): # 设置进程数
 executor.submit(myThread, i)
if __name__ == '__main__':
 # get_all_singer()
 # myProcess()
 myProcess()