1. import requests
    2. import time
    3. import os
    4. from lxml import etree
    6. for page in range(1, 3):
    7.     print(f'正在抓取第{page}页=================')
    8.     page_url= f'https://www.ximalaya.com/youshengshu/22963309/p{page}/'
    9.     headers = {
    10.         'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36'
    11.     }
    12.     page_text = requests.get(url=page_url, headers=headers).text
    13.     page_tree = etree.HTML(page_text)
    14.     media_dir = page_tree.xpath('////h1[@class="title k_Z"]/text()')[0].split(' | ')[0]
    15.     div_list = page_tree.xpath('//div[@class="text Mi_"]')
    17.     if not os.path.exists(media_dir):
    18.         os.mkdir(media_dir)
    20.     # 这里使用了枚举法--enumerate(squ)已达到给每个小标题加上序列的目的
    21.     for num, div in enumerate(div_list):
    22.         media_title = div.xpath('./a/@title')[0] #  media_title：重生八零：媳妇有点辣 0001 我是破鞋？
    23.         media_index = (page-1) * 30 + num + 1
    24.         # 当序号小于10时，在序号前面加上一个0
    25.         if media_index < 10:
    26.             media_index = '0' + str(media_index)
    27.         media_path = f"{media_index} {media_title.split(' ')[-1]}.mp3"
    28.         media_href = div.xpath('./a/@href')[0] # media_href：/youshengshu/22963309/456562317 
    29.         media_id = media_href.split('/')[-1] # media_id：456562317
    31.         ajax_url = f'https://www.ximalaya.com/revision/play/v1/audio?id={media_id}&ptype=1'
    32.         time.sleep(0.5)
    33.         ajax_data = requests.get(url=ajax_url, headers=headers).json()
    35.         media_url = ajax_data['data']['src']
    36.         print(media_path, '开始下载...')
    37.         time.sleep(0.5)
    38.         media_data = requests.get(url=media_url, headers=headers).content
    39.         with open(f'{media_dir}/{media_path}', 'wb') as fp:
    40.             fp.write(media_data)
    41.         print(media_path, '下载完成!')
    42. print(media_dir,f'所有章节已下载完毕 共{page}页 {media_index}章节！！！')
    45. """
    46. 注意：
    47.     01.if not os.path.exists(path)---判断是否有某个文件夹
    48.     02.os.mkdir(path)---创建文件夹
    49.     03.for in i, path in enumerate(squ)---enumerate()枚举法
    50. """