import requests
from lxml import etree
from urllib import parse
url = 'https://www.ximalaya.com/lishi/4164479/'
headers = {
'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}
response = requests.get(url, headers=headers)
# with open('chunqiu.html', 'wb') as f:
# f.write(response.content)
html_str = response.text
# print(html_str)
html_ele = etree.HTML(html_str)
# print(html_ele)
li_list = html_ele.xpath('//ul[@class="dOi2"]/li')
# print(li_list)
for li_ele in li_list:
# print(li_ele)
li_href = li_ele.xpath('./div[2]/a/@href')[0]
# print(li_href)
url_list = parse.urljoin(url, li_href)
# print(url_list)
url_a = url_list.split('/')[-1]
# print(url_a)
url_b = 'https://www.ximalaya.com/revision/play/tracks?trackIds='+ str(url_a)
# print(url_b)
response_a = requests.get(url_b, headers=headers)
json_a_dict = response_a.json()
# print(json_a_dict)
src_a_str = json_a_dict['data']['tracksForAudioPlay'][0]['src']
trackName_a = json_a_dict['data']['tracksForAudioPlay'][0]['trackName']
from urllib import request
request.urlretrieve(src_a_str,trackName_a+'.ma4')