spider_ximalaya.rar

from lxml import etree import requests import os from urllib import request,parse import json import execjs def spider_songs(list): '''保存音频（字典）''' for i in list: dir = "ximalaya/{}/".format(i['bookName']) if not os.path.exists(dir): print("创建目录:.%s" % dir) os.makedirs(dir) i['name'] = i['name'].replace("?", "").replace('"', "") # 在目录下创建一个喜马拉雅的文件夹 with open(r'{}/{}.m4a'.format(dir, i['name']), 'ab')as f: r = requests.get(i['src']) print("正在下载:{}...".format(i['name']), end="") f.write(r.content) print("\t下载完成！") # def spider_song(m4a_url,m4a_name): # # 创建down文件夹 # if not os.path.exists('Down'): # os.mkdir('Down') # filename = 'Down/' + m4a_name + '.m4a' # # print(filename) # # 下载 # request.urlretrieve(m4a_url, filename) # print(m4a_url + m4a_name + 'downloading...') # print('---' * 50) def spider_list(albumId): all_list = [] headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36', 'Accept':'text/html,application/xhtml+ xml,application/xml;q = 0.9,image/webp,image/apng,*/*;q=0.8, application/signe-exchange;v = b3', 'Host': 'www.ximalaya.com' } sign = exec_js() #加入xm-sign到header中 headers['xm-sign'] = sign # 音频地址 data_url = 'https://www.ximalaya.com/revision/play/album?albumId={}&pageNum=1&sort=-1&pageSize=30'.format(albumId) # print(data_url) response = requests.get(data_url, headers=headers) py_dict = json.loads(response.content.decode()) # print(py_dict) book_list = py_dict['data']['tracksAudioPlay'] for book in book_list: # 获取每段音频的名称和地址 list = {} list['name'] = book['trackName'] list['bookName'] = book['albumName'] list['src'] = book['src'] # 打印list # print(list) all_list.append(list) # 返回字典 return all_list '''生成xm-sign''' def exec_js(): #获取喜马拉雅系统时间戳 time = getxmtime() #读取同一路径下的js文件 with open('xmSign.js', encoding='utf-8') as f: js = f.read() # 通过compile命令转成一个js对象 docjs = execjs.compile(js) # 调用js的function res = docjs.call('python',time) #res = docjs.call('getnow') return res '''爬取喜马拉雅服务器系统时间戳，用于生成xm-sign''' def getxmtime(): headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36', 'Accept': 'text/html,application/xhtml+ xml,application/xml;q = 0.9,image/webp,image/apng,*/*;q=0.8, application/signe-exchange;v = b3', 'Host': 'www.ximalaya.com' } url="https://www.ximalaya.com/revision/time" response = requests.get(url, headers=headers) # print(response) html = response.text return html def spider_ximalaya(albumId): all_list = spider_list(albumId) spider_songs(all_list) if __name__ =='__main__': spider_ximalaya(12642314)