Python爬虫之批量下载喜马拉雅音频

https://www.ximalaya.com/revision/play/v1/audio?id=348451879&ptype=1

import requests
from fake_useragent import UserAgent as ua
from bs4 import BeautifulSoup as bs

# 专栏地址
music_list_url = 'Https://www.ximalaya.com/ertongjiaoyu/19702607/'
# 获取音频地址的url
get_link_url = "https://www.ximalaya.com/revision/play/v1/audio"

# UA伪装
headers = {
    "User-Agent": ua().random
}

# 参数
params = {
    "id": None,    # id先设为None
    "ptype": "1",
}

# 获取专栏html源码
music_list_r = requests.get(music_list_url, headers=headers)
# 解析 获取所有li标签
soup = bs(music_list_r.text, "lxml")
li = soup.find_all("li", {"class": "lF_"})

# for循序遍历处理
for i in li:
    a = i.find("a")   # 找到a标签
    # 获取href属性
    # split("/")将字符串以"/"作为分隔符 从右往左数第一项是id号
    music_id = a.get("href").split("/")[-1]
    # 获取title属性 和“.m4a”拼接成文件名
    music_name = a.get("title") + ".m4a"

	# 修改请求参数id
    params['id'] = music_id

	# 获得音频源地址
    r = requests.get(get_link_url, headers=headers, params=params)
    link = r.JSON()['data']['src']

	# 获取音频文件并保存
    music_file = requests.get(link).content
    with open(music_name, "wb") as f:
        f.write(music_file)

print("下载完毕！")