python在B站爬糖豆广场舞

先附上代码：

import requests,re
from lxml  import etree

#这是单页面下载，翻页的目前还不会
url = 'https://search.bilibili.com/all?vt=96737335&keyword=%E7%B3%96%E8%B1%86%E5%B9%BF%E5%9C%BA%E8%88%9E'

headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36',
    'referer':'https://www.bilibili.com/'
}

res = requests.get(url,headers=headers)
# print(res.text)

html = etree.HTML(res.text)
links = html.xpath('//*[@id="i_cecream"]/div/div[2]/div[2]/div/div/div/div[2]/div/div[*]/div/div[2]/div/div/a/@href')
# print(links)

for link in links:
    link = 'https:'+ link
    # print(link)

    url_res = requests.get(link,headers=headers)
    url_html = etree.HTML(url_res.text)
    #视频名
    title = url_html.xpath('//*[@id="viewbox_report"]/h1/text()')[0]
    title2 = re.sub('\W','',title)
    # print(title2)

    # 获取音频URL

    get_ad = re.findall(r'"id":30280,"baseUrl":"(.*?)","base_url"',url_res.content.decode())
    get_ad2=[]
    if not  get_ad:
        # print('列表为空')
        continue
    else:
        # print(get_ad[0])
        get_ad2 =  get_ad

    # get_ad = re.findall(r'"id":17,"baseUrl":"(.*?)","base_url"',url_res.content.decode())

    #获取视频url
    get_vd = re.findall(r'"id":32,"baseUrl":"(.*?)","base_url"',url_res.content.decode())
    get_vd2 = []
    if not  get_vd:
        continue
    else:
        get_vd2 =  get_vd
        # print(get_vd2)
        # with open('log2.txt','wb') as f:
        #     f.write(get_vd2)


    headers2 = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36',
        'referer':'https://www.bilibili.com',
    }

    # 第二次发送请求，请求视频
    # print('1111')
    res_ad = requests.get(get_ad2[0],headers=headers2)
    res_vd = requests.get(get_vd2[0],headers=headers2)
    # res2 = res_ad.content
    print('1111')

    with open(f'video/{title2}ad.mp4','wb') as f:
        f.write(res_ad.content)
    with open(f'video/{title2}vd.mp4','wb') as f:
        f.write(res_vd.content)
        print(f'{title2}视频下载完成！')

    from moviepy.editor import *

    vd = VideoFileClip(f"video/{title2}vd.mp4")
    au = AudioFileClip(f"video/{title2}ad.mp4")
    vd2 = vd.set_audio(au)
    vd2.write_videofile(f"video/{title2}.mp4")

下载完以后的成果。