下载B站视频（多视频版）

import requests
import re
import json
import requests
from moviepy.audio.io.AudioFileClip import AudioFileClip
from moviepy.video.io.VideoFileClip import VideoFileClip


def getAllTitles():
    url = "https://www.bilibili.com/video/BV18P4y1Y7WD"
    resp = requests.get(url=url, headers='').text
    # 跳过识别不了的gbk字符
    resp = resp.encode("gbk", "ignore").decode("gbk", "ignore")
    all_pages = resp.split('volume')[1].split('subtitle')[0]
    pages = all_pages.split('part')
    titles = []
    for i in pages:
        titles.append(i.split('.mp4')[0].split('\":\"')[1].replace(' ',''))
    del (titles[0])
    return titles

def downVideos(titles,Primary_url):
    # url = 'https://www.bilibili.com/video/BV18D4y1c7BM?spm_id_from=333.999.0.0'
    headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/\
             537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36 Edg/\
            96.0.1054.62',
               "referer": "https://message.bilibili.com/"}
    page=1
    for i in titles:
        url=Primary_url+'?p='+str(page)
        print('下载第' + str(page) + '个视频,地址为：' + url)
        # print(tt)
        html = requests.get(url, headers=headers)  # 请求原始网页
        # 视频下载链接在script标签内
        k = r'<script>window.__playinfo__=(.*?)</script>'
        # print(k)
        script = re.findall(k, html.text)[0]
        # print(script)
        # 转成字典
        script_dic = json.loads(script)
        url_video = script_dic['data']['dash']['video'][0]['baseUrl']
        print('获取到第'+str(page)+'个视频地址')
        url_audio = script_dic['data']['dash']['audio'][0]['baseUrl']
        print('获取到第'+str(page)+'个音频地址')
        # # 提取标题
        # k2 = r'<title data-vue-meta="true">(.*?)</title>'
        #
        # title = re.findall(k2, html.text)[0]
        # # 去掉标题空格，否则ffmpeg出错
        # title = title.replace(' ', '')
        # 命名
        video_name = i + '.mp4'
        audio_name = i + '.mp3'
        output_name = i + '_merge.mp4'
        # 请求资源
        html_video = requests.get(url_video, headers=headers)
        html_audio = requests.get(url_audio, headers=headers)

        # 写入文件
        with open('video/' + video_name, 'wb') as f:
            f.write(html_video.content)
        with open('video/' + audio_name, 'wb') as f:
            f.write(html_audio.content)

        audio = AudioFileClip('video/' + audio_name)
        # 读入视频
        video = VideoFileClip('video/' + video_name)
        # 将音轨合并到视频中
        print('下载完成，开始合并视频和音频')
        video = video.set_audio(audio)
        # 输出
        video.write_videofile(f"result/{i}.mp4")
        print('第'+str(page)+'合并完成')
        page = page+1

    #

if __name__ == '__main__':
    titles=getAllTitles()
    # for i in titles:
    #     print(i)
    downVideos(titles,'https://www.bilibili.com/video/BV18P4y1Y7WD')
# titles ?p=16

标签：视频,url,titles,video,print,audio,page,下载
来源： https://www.cnblogs.com/yangxuyang/p/16453928.html