Python爬取喜马拉雅有声书

# 导入第三方库

import requests
import parsel

# 模拟浏览器
headers = {
    "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"}


def download_media(media_url, media_name):
　　"""定义下载模块"""
    response = requests.get(media_url, headers=headers)

    with open(f'{media_name}.mp4', mode="wb") as f:
        f.write(response.content)


def media_api(track_id):
    """从网页获取下载地址"""
    api_url = f"https://www.ximalaya.com/revision/play/v1/audio?id={track_id}&ptype=1"
    resepons = requests.get(api_url, headers=headers)
    data = resepons.json()
    src = data["data"]["src"]
    return src


def get_total_page(page_url):
    """请求每页模块"""
    response = requests.get(page_url, headers=headers)
    sel = parsel.Selector(response.text)
    sound_list = sel.css(".sound-list ul li a")
    for sound in sound_list[:30]:
        media_url = sound.css("a::attr(href)").extract_first()
        media_url = media_url.split("/")[-1]
        media_name = sound.css("a::attr(title)").extract_first()
        yield media_url, media_name


if __name__ == '__main__':
　　　"""主程序"""
    # print(media_api(152693861))
    # 循环遍历多页
    for page in range(1, 24):
        medias = get_total_page(f"https://www.ximalaya.com/youshengshu/20642967/p{page}")
        for media_id, media_name in medias:
            media_url = media_api(media_id)
            download_media(media_url, media_name)