网络爬虫（三）爬取B站视频

尝试着用request库去爬取了一些B站视频

参考和抄了一些博主的代码和思路，我略作了修改，目前是不能爬取带分页的视频（只需要略作修改，也可爬取）：

Python爬取B站视频，只需一个B站视频地址，即可任意下载 - 腾讯云开发者社区-腾讯云 (tencent.com)

import requests
import re  # 正则表达式
import pprint
import json
import subprocess
import os


if not os.path.exists("./video"):
    os.mkdir("./video")
ID=r"BV1Vx4y177ew"
fileName="./video/test"
url = f'https://www.bilibili.com/video/{ID}/'
headers = {
            'referer': f'https://www.bilibili.com/video/{ID}?spm_id_from=333.337.search-card.all.click',
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36'
    }


def send_request(url):
    response = requests.get(url=url, headers=headers)
    return response
def get_video_data(html_data):
    """解析视频数据"""

    # 提取视频的标题
    #title = re.findall('<span class="tit">(.*?)</span>', html_data)
    # print(title)

    # 提取视频对应的json数据
    json_data = re.findall('<script>window\.__playinfo__=(.*?)</script>', html_data)[0]
    # print(json_data)  # json_data 字符串
    json_data = json.loads(json_data)
    pprint.pprint(json_data)

    # 提取音频的url地址
    audio_url = json_data['data']['dash']['audio'][0]['backupUrl'][0]
    print('解析到的音频地址:', audio_url)

    # 提取视频画面的url地址
    video_url = json_data['data']['dash']['video'][0]['backupUrl'][0]
    print('解析到的视频地址:', video_url)

    video_data = [audio_url, video_url]
    return video_data
def save_data(file_name, audio_url, video_url):
    # 请求数据
    print('正在请求音频数据')
    audio_data = send_request(audio_url).content
    print('正在请求视频数据')
    video_data = send_request(video_url).content
    with open(file_name + '.mp3', mode='wb') as f:
        f.write(audio_data)
        print('正在保存音频数据')
    with open(file_name + '.mp4', mode='wb') as f:
        f.write(video_data)
        print('正在保存视频数据')

def merge_data(video_name):
    print('视频合成开始:', video_name)
    # ffmpeg -i video.mp4 -i audio.wav -c:v copy -c:a aac -strict experimental output.mp4
    COMMAND = f'ffmpeg -i {video_name}.mp4 -i {video_name}.mp3 -vcodec copy -acodec copy {video_name}_out.mp4'
    subprocess.run(COMMAND, encoding='utf-8',shell=True)
    print('视频合成结束:', video_name)

rep=send_request(url).text
video=get_video_data(rep)
save_data(fileName,*video)
merge_data(fileName)
print("success")