爬取《喜马拉雅》音频排行榜

先上图，只爬了20分钟左右。保存了2000个音频

完整代码如下，，，直接拿去就可以用，
报错的话更改一下Cookie

import requests
from bs4 import BeautifulSoup
import re
import time


# 定义一个保存文件的函数
def xiazhai(url, name):
    try:
        req = requests.get(url)
        with open(r'C:\Users\MI\Desktop\python\爬虫测试文件\喜马拉雅\{}.mp3'.format(name), 'wb') as f:
            f.write(req.content)
    except:
        print('-----------保存出现未知错误，已跳过---------')


# 定义一个获取下载链接的函数
def huoqu_url(mulu):
    for pn in range(1, 31):  # 每个书有30页数据
        headers = {
            'Cookie': 'Hm_lvt_4a7d8ec50cfd6af753c4f8aee3425070=1538547574; Hm_lpvt_4a7d8ec50cfd6af753c4f8aee3425070=1538547574',
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:62.0) Gecko/20100101 Firefox/62.0',
            'Host': 'www.ximalaya.com',
            'Referer': 'https: // www.ximalaya.com / xiangsheng / {} /'.format(mulu)
        }
        data = {
            'albumId': mulu,
            'pageNum': pn,
            'sort': ' -1',
            'pageSize': ' 30'
        }
        url1 = 'https://www.ximalaya.com/revision/play/album?albumId={}&pageNum={}&sort=-1&pageSize=30'.format(mulu, pn)
        try:
            r = requests.get(url1, headers=headers, data=data)
            r = r.json()
            for i in range(30):
                r1 = r['data']['tracksAudioPlay'][i]['src']  # 获取到的url
                r2 = r['data']['tracksAudioPlay'][i]['trackName']
                r2 = re.sub(r'《|》|？|！|。|，|：|；|:|;| ', '', r2)  # 正则后的名称
                xiazhai(r1, r2)
                print(r1, r2)
                time.sleep(1)
        except:
            print('----------获取下载链接出现未知错误，已跳过---------')

#定义一个获取排行榜音频ID
def mulu_ID():
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:62.0) Gecko/20100101 Firefox/62.0'
    }
    url1 = 'https://www.ximalaya.com/lishi/top/'
    try:
        r = requests.get(url1, headers=headers)
        soup = BeautifulSoup(r.text, 'lxml')
        r = soup.find_all('div', attrs={'class': 'rankpage-content clearfix', 'class': 'RZ7r right-rank-content',
                                        'class': 'RZ7r rrc-list'})
        soup = BeautifulSoup(str(r), 'lxml')
        r_1 = soup.find_all('a')
        for i in range(50):  # 排行榜第一页有50个数据
            r1 = str(r_1[i])
            r = r1[16:24]
            id = re.sub(r'/|<|>\"|"|>','',r)
            print('-----------------------这是第{}本书--------------------'.format(i+1),'图书ID：',id)
            huoqu_url(id)#调用获取下载链接的函数
    except:
        print('-----------获取书本目录出现出现未知错误，已跳过---------')


mulu_ID()