"突破喜马拉雅的 xm-sign 验证，爬取有声读物"

from queue import Queue
import threading
import requests
import hashlib
import random
import time
import re
import os


class XimaLaya(object):
    def __init__(self, page_url):
        self.headers = {'User-Agent': 'Mozilla/5.0', 'Host': 'www.ximalaya.com'}
        self.server_time_url = 'https://www.ximalaya.com/revision/time'
        self.requests_url = 'https://www.ximalaya.com/revision/play/album'
        self.page_url = page_url
        self.queue = Queue()

    def get_md5(self, str_time):
        """
        获取md5字段
        """
        return hashlib.md5('himalaya-{}'.format(str_time).encode()).hexdigest()

    def xm_sign(self):
        """
        获取xm-sign
        """
        # 喜马拉雅服务器时间戳
        server_time = requests.get(self.server_time_url, headers=self.headers).text
        # 现在的时间戳
        now_time = str(int(time.time()*1000))
        # 100内随机数
        random_num = '({})'.format(str(random.randrange(100)))
        # 获取xm-sign
        return self.get_md5(server_time) + random_num + server_time + random_num + now_time

    def get_album_info(self):
        """
        获取专辑id、页码、专辑名称
        """
        html = requests.get(self.page_url, headers=self.headers, timeout=10).text
        return (
            re.findall(r'/(\d{4,})/', self.page_url)[0],
            re.findall(r'min="1" max="(\d+)"', html)[0],
            re.findall(r'<h1 class="title _leU">(.*?)</h1>', html)[0],
        )

    def crawler(self, albumId, page_num):
        """
        爬取音乐数据
        """
        try:
            for n in range(1, int(page_num) + 1):
                self.headers['xm-sign'] = self.xm_sign()
                params = {'albumId': albumId, 'pageNum': str(n), 'sort': '0', 'pageSize': '30'}
                r = requests.get(self.requests_url, params=params, headers=self.headers, timeout=8)
                music_list = r.json()['data']['tracksAudioPlay']
                for music in music_list:
                    music_name = re.sub(r'[\/:*?"<>|]', "", music['trackName'])
                    music_url = music['src'].replace('"', "")
                    print('添加到队列：', (music_url, music_name))
                    self.queue.put_nowait((music_url, music_name))
        except:
            pass

    def download(self):
        """
        下载音乐
        """
        while not self.queue.empty():
            try:
                music_url, music_name = self.queue.get_nowait()
                content = requests.get(music_url, timeout=20).content
                with open(path + '/' + music_name + '.m4a', 'wb') as f:
                    f.write(content)
                    print('已下载：{}.m4a'.format(music_name))
            except:
                pass

    def main(self):
        album_id, page_num, album_name = self.get_album_info()
        # 创建文件夹
        album_name = re.sub(r'[\/:*?"<>|]', "", album_name)
        global path
        path = "ximalaya/{}/".format(album_name)
        if not os.path.exists(path):
            os.makedirs(path)
        # 单线程爬取数据
        self.crawler(album_id, page_num)
        # 多线程下载
        t_l = []
        for x in range(5):
            t = threading.Thread(target=self.download)
            t_l.append(t)
            t.start()

        for t in t_l:
            t.join()


if __name__ == '__main__':
    # url = input('输入链接：')
    url = 'https://www.ximalaya.com/youshengshu/5088879/'
    xm = XimaLaya(url)
    xm.main()