Python下载酷狗Top500

import requests, json, threading, queue, os, random, time, re
import urllib.request
import pandas as pd

class ThreadDown(threading.Thread):
    def __init__(self, urlQueue, path, lock):
        super(ThreadDown, self).__init__()
        self.urlQueue = urlQueue
        self.path = path
        self.lock = lock

    def run(self):
        while not self.urlQueue.empty():
            song_data = self.urlQueue.get()
            songName = re.sub(r'[\/:*?"<>|]', '-', song_data['fileName'])
            fileName = os.path.join(self.path, songName + '.mp3')
            url = song_data['downloadUrl']
            try:
                urllib.request.urlretrieve(url, fileName)
            except:
                print('%s 下载失败！' % songName)
                with self.lock:
                    txtFile = os.path.join(self.path, 'aNote.txt')
                    with open(txtFile, 'a') as f:
                        f.write(songName + '-' + url + '\n')
            time.sleep(random.randint(3, 10))

headers={
        'UserAgent' : 'Mozilla/5.0 (iPhone; CPU iPhone OS 5_0 like Mac OS X) AppleWebKit/534.46 (KHTML, like Gecko) Version/5.1 Mobile/9A334 Safari/7534.48.3',
        'Referer' : 'http://m.kugou.com/rank/info/8888',
        'Cookie' : 'UM_distinctid=161d629254c6fd-0b48b34076df63-6b1b1279-1fa400-161d629255b64c; kg_mid=cb9402e79b3c2b7d4fc13cbc85423190; Hm_lvt_aedee6983d4cfc62f509129360d6bb3d=1523818922; Hm_lpvt_aedee6983d4cfc62f509129360d6bb3d=1523819865; Hm_lvt_c0eb0e71efad9184bda4158ff5385e91=1523819798; Hm_lpvt_c0eb0e71efad9184bda4158ff5385e91=1523820047; musicwo17=kugou'
        }

def get_songs(url):
    res=requests.get(url,headers=headers)
    return res.text

def get_song_download_url(url):
    res=requests.get(url,headers=headers)
    res_tmp_list = json.loads(res.text)
    return res_tmp_list['data']['play_url']

def get_song_page_data(url):
    Song_Json = json.loads(get_songs(URL))
    Song_List_Json = Song_Json['data']['info']
    total = []
    for i in range(len(Song_List_Json)):
        song_download_url = "http://www.kugou.com/yy/index.php?r=play/getdata&hash=%s&album_id=%s&_=1523819864065" % (Song_List_Json[i]['hash'], Song_List_Json[i]['album_id'])
        song_data_dict = {'downloadUrl':get_song_download_url(song_download_url),'fileName':Song_List_Json[i]['filename']}
        total.append(song_data_dict)
    return total

if __name__ == '__main__':
    if not os.path.exists('KuGou'):
        os.mkdir('KuGou')
    path = os.path.join(os.getcwd(), 'KuGou')
    thread_num = 30
    lock = threading.Lock()
    urlQueue = queue.Queue()
    for i in range(1, 11):
        URL='http://mobilecdngz.kugou.com/api/v3/rank/song?rankid=8888&ranktype=2&page=%s&pagesize=50&volid=&plat=2&version=8955&area_code=1' % i
        page_list_data = get_song_page_data(URL)

        for page_data in page_list_data:
            urlQueue.put(page_data)
            # print("%s   %s" % (page_list_data[j]['fileName'],page_list_data[j]['downloadUrl']))

    threadList = []
    for i in range(thread_num):
        thread = ThreadDown(urlQueue, path, lock)
        thread.start()
        threadList.append(thread)

    for thread in threadList:
        thread.join()

    print('全部下载完成！')