Python爬蟲QQ音樂資料採取,公開資料獲取案例之一
阿新 • • 發佈:2021-09-22
工具準備
資料來源:QQ音樂
開發環境:win10、python3.7
開發工具:pycharm、Chrome
效果展示
專案思路解析
搜尋你需要的歌名或者歌曲
抓取對應的資料包
提取json資料裡的歌曲名字,歌曲的mid,歌手名字
for i in range(1, 10):
url = 'https://c.y.qq.com/soso/fcgi-bin/client_search_cp'
params = {
"ct": " 24",
"qqmusic_ver": " 1298",
"new_json": " 1",
"remoteplace": " txt.yqq.song",
"searchid": " 66595602585102401",
"t": " 0",
"aggr": " 1",
"cr": " 1",
"catZhida": " 1",
"lossless": " 0",
"flag_qc": " 0",
"p": str(i),
"n": " 10",
"w": keyword,
"g_tk_new_20200303": " 1390029147",
"g_tk": " 1390029147",
"loginUin": " 1164153961",
"hostUin": " 0",
"format": " json",
"inCharset": " utf8",
"outCharset": " utf-8",
"notice": " 0",
"platform": " yqq.json",
"needNewCode": " 0"
}
response = requests.get(url, params=params, headers=headers)
# print(re.findall('callback\((.*)\)', response)[0])
search_result = eval(re.findall('callback\((.*)\)', response.text)[0])
song_info_list = search_result['data']['song']['list']
# print()
tplt = "{0:<10}\t{1:<10}\t{2:<20}"
print(tplt.format("序號", "歌手", "歌名"))
for song_info in song_info_list:
# print(song_info)
song_name = song_info['songname']
song_mid = song_info['songmid']
singer = song_info['singer'][0]['name']
找到單個音樂的請求資料介面
音樂的播放地址為purl
動態提交的資料來自與同一個js檔案
除錯js程式碼請求方法為get
get請求的url地址拼接上post對應的表單引數
因為我們獲取的資料只需要資料包含purl的req_1,只需要對應data的req_1的引數,songmid為歌曲的mid
params1 = {
'_': time.time()*1000,
'sign': 'zzakgej75pk8w36d82032784bdb9204d99bf6351acb7d',
"data": '{"req":{"module":"vkey.GetVkeyServer","method":"CgiGetVkey","param":{"guid":"7469768631","songmid":["' + song_mid + '"],"songtype":[0],"uin":"1164153961","loginflag":1,"platform":"20"}}}'
}
response = requests.get(url1, params=params1, headers=headers)
得到對應的req_1的資料,取出purl值拼接成歌曲播放地址
下載對應歌曲
簡易程式碼分享
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Author : BaiChuan
# @File : qq音樂.py
import requests
import re
import time
headers = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36",
}
keyword = input('請輸入你想下載的歌手名:')
for i in range(1, 10):
url = 'https://c.y.qq.com/soso/fcgi-bin/client_search_cp'
params = {
"ct": " 24",
"qqmusic_ver": " 1298",
"new_json": " 1",
"remoteplace": " txt.yqq.song",
"searchid": " 66595602585102401",
"t": " 0",
"aggr": " 1",
"cr": " 1",
"catZhida": " 1",
"lossless": " 0",
"flag_qc": " 0",
"p": str(i),
"n": " 10",
"w": keyword,
"g_tk_new_20200303": " 1390029147",
"g_tk": " 1390029147",
"loginUin": " 1164153961",
"hostUin": " 0",
"format": " json",
"inCharset": " utf8",
"outCharset": " utf-8",
"notice": " 0",
"platform": " yqq.json",
"needNewCode": " 0"
}
response = requests.get(url, params=params, headers=headers)
# print(re.findall('callback\((.*)\)', response)[0])
search_result = eval(re.findall('callback\((.*)\)', response.text)[0])
song_info_list = search_result['data']['song']['list']
# print()
tplt = "{0:<10}\t{1:<10}\t{2:<20}"
print(tplt.format("序號", "歌手", "歌名"))
for song_info in song_info_list:
# print(song_info)
song_name = song_info['songname']
song_mid = song_info['songmid']
singer = song_info['singer'][0]['name']
print(tplt.format(song_mid, singer, song_name))
url1 = 'https://u.y.qq.com/cgi-bin/musicu.fcg'
params1 = {
'_': time.time()*1000,
'sign': 'zzakgej75pk8w36d82032784bdb9204d99bf6351acb7d',
"data": '{"req":{"module":"vkey.GetVkeyServer","method":"CgiGetVkey","param":{"guid":"7469768631","songmid":["' + song_mid + '"],"songtype":[0],"uin":"1164153961","loginflag":1,"platform":"20"}}}'
}
response = requests.get(url1, params=params1, headers=headers)
print(response.json())
songlink = response