【Python爬虫】“每天一遍，防止早恋”？B站高颜值美女视频采集

import requests  # 数据请求模块  pip install requests
import re  # re正则表达式 提取数据
import subprocess # 子进程
import os # 文件操作的模块

headers = {
    'referer': 'https://www.bilibili.com/',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36'
}


def get_response(html_url):
    response = requests.get(url=html_url, headers=headers)
    return response

def get_video_info(html_url):
    html_data = get_response(html_url).text
    title = re.findall('<h1 title="(.*?)" class="video-title">', html_data)[0]
    cid = re.findall('"cid":(\d+),', html_data)[0]
    session = re.findall('"session":"(.*?)"', html_data)[0]
    video_info = [cid, session, title]
    return video_info

def get_video_content(bv_id, cid, session):
    index_url = 'https://api.bilibili.com/x/player/playurl'
    data = {
        'cid': cid,
        'qn': '32',
        'type': '',
        'otype': 'json',
        'fourk': '1',
        'bvid': bv_id,
        'fnver': '0',
        'fnval': '976',
        'session': session,
    }
    json_data = requests.get(url=index_url, params=data, headers=headers).json()
    # 通过字典键值对方法 取内容, 就根据冒号左边内容 提取冒号右边的内容
    audio_url = json_data['data']['dash']['audio'][0]['baseUrl']
    video_url = json_data['data']['dash']['video'][0]['baseUrl']
    video_content = [audio_url, video_url]
    return video_content

def save(title, audio_url, video_url):
    # response.text 获取响应体的文本数据 (一般网页源代码) 返回数据类型 字符串
    # response.content 获取响应体的二进制数据 (保存图片/音频/视频/特定格式文件) 二进制数据内容
    # response.json() 获取响应体的json字典数据 字典数据类型
    audio_content = get_response(audio_url).content
    video_content = get_response(video_url).content
    with open(title + '.mp3', mode='wb') as f:
        f.write(audio_content)
    with open(title + '.mp4', mode='wb') as f:
        f.write(video_content)
    print(title, '视频保存完成')

def merge_data(video_name):
    print('视频合成开始:', video_name)
    cmd = f"ffmpeg -i {video_name}.mp4 -i {video_name}.mp3 -c:v copy -c:a aac -strict experimental {video_name}output.mp4"
    # print(cmd)
    subprocess.run(cmd, shell=True)
    print('视频合成结束:', video_name)
    os.remove(f'{video_name}.mp4')
    os.remove(f'{video_name}.mp3')