爬取酷狗音乐

1 requests  

2 gevent  

3 sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='gb18030') # 改系统编码 utf-8 不好使

爬取多个歌曲  批量爬取  

import requests

import urllib.request

from requests.exceptions import ReadTimeout,HTTPError,RequestException
from bs4 import BeautifulSoup
import urllib
import gevent
from gevent import Greenlet
import socket
import random
import sys
import os
import json
import io
import re
import math


def main(url):
    print(url)

    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36'
    }
    #
    try:
        get=requests.get(url,headers)


        while get.status_code != 200:
              print("url %s"%url)

        else:
            r = get.text
            datas = json.loads(r[r.index('(') + 1:-2])
            lsits = datas['data']['lists']
            lens= len(lsits)
            print("总数->%d"%lens)
            for i in range(lens):
                 print("下载编号 %s" %str(i)+"---"+lsits[i]['FileName'].replace("<em>","").replace("</em>"," "))
                 print("下载编号 %s" %str(i)+"---"+lsits[i]['FileHash'].replace("<em>","").replace("</em>"," "))
                 gevent.sleep(2)
                 fihash = re.findall('"FileHash":"(.*?)"', r)[i]
                 ps_url = "https://www.kugou.com/yy/html/index.php?r=play/getdata&hash="+fihash
                 print(ps_url)
                 rrr = requests.get(ps_url).text

                 print("ps_url ---------------------------------")
                 play_url =re.findall('"play_url":"(.*?)"',rrr)[0].replace("\\","")
                 print(play_url)
                 print("编号{} >>> ps_url{} >>> play_url{}".format(i,ps_url,play_url))
                 path_name = lsits[i]['FileName'].replace("<em>", "").replace("</em>", " ")
                 path_name.replace(" ","")
                 p = os.getcwd() + "/MP5/"
                 with open(p+path_name+".mp3","wb") as f:
                     f.write(requests.get(play_url).content)



            print(len(lsits))
    except ReadTimeout:
        print('timeout')
    except HTTPError:
        print('httperror')
    except RequestException:
        print('reqerror')




if __name__ == '__main__':

    song_name = input("请输入歌曲名称:").split(",")
    songs = len(song_name)
    #lock = threading.Lock()
    urls=[]
    for  i in range(songs):
            url = "https://songsearch.kugou.com/song_search_v2?callback=jQuery112406438825614322465_1545881092316&keyword=" + str(song_name[i]) + "&page=1&pagesize=30&userid=-1&clientver=&platform=WebFilter&tag=em&filter=2&iscorrection=1&privilege_filter=0&_=1545881092322"

            urls.append(gevent.spawn(main,url))

    gevent.joinall(urls)

 

转载于:https://www.cnblogs.com/wxc1/p/10215662.html