获取哔哩哔哩(Bilibili)视频目录

由于想学习视频, 一直很中意哔哩哔哩
个人习惯每看个视频都要做笔记嘛, 所以想获取一下视频的目录信息

之前有查到一个获取视频目录的方式
	是在控制台进行操作的
但是嘛, 现在控制台不让复制了, 没办法, 只好写一个小功能了
今天是 2023/11/14 15:15
功能代码如下:

import requests
import json
import os
from datetime import datetime

from bs4 import BeautifulSoup

# 参考链接:
#   https://zhuanlan.zhihu.com/p/117569614
#   https://blog.csdn.net/weixin_42914706/article/details/129112667


def print_directory(data):
    soup = BeautifulSoup(data, 'html.parser')
    # print(bs)
    target = 'window.__INITIAL_STATE__='
    script_tags = soup.find_all('script')
    count = 1
    for script in script_tags:
        if target in script.text:
            data = script.text.replace(target, "").split('};')[0] + '}'
            data = json.loads(data)
            for index in data.get('videoData').get('pages'):
                print('P{0} {1}'.format(count, index.get('part')))
                count += 1
            break


if __name__ == '__main__':
    current_time = datetime.now().strftime("%Y%m%d%H%M%S")
    file_name = 'Bilibili视频目录_{0}.txt'.format(current_time)
    if not os.path.exists(file_name):
        with open(file_name, 'w') as file:
            print("文件创建成功")
    file_size = os.path.getsize(file_name)
    if file_size == 0:
        url = input("请输入网址:")
        print("网址: ", url)
        print("访问网址获取数据")
        res = requests.get(url)
        if os.path.exists(file_name):
            os.remove(file_name)
        with open(file_name, 'w', encoding='utf-8') as f:
            f.write(res.text)
        print_directory(res.text)
    else:
        print("不用访问网址")
        with open(file_name, 'r', encoding='utf-8') as f:
            read = f.read()
        print_directory(read)