CZYC_Pachong/utils/GetVideoInfo.py

# -*- coding: utf-8 -*-
# @Author  : ChenZhaoyuchen
# @Time    : 2024/9/13 15:02
# @File    : GetVideoInfo.py

import json
import re
from utils.GetResponse import *
from pprint import pprint

video_json = {
}

def GetVideoInfo() -> str:
    response_video = GetResponse_AV()

    html_video = response_video.text

    info_video = re.findall('<script>window.__playinfo__=(.*?)</script>', html_video)[0]

    json_data_video = json.loads(info_video)

    video_url = json_data_video['data']['dash']['video'][0]['baseUrl']

    return video_url

def GetAudioInfo() -> str:
    response_audio = GetResponse_AV()

    html_audio = response_audio.text

    info_audio = re.findall('<script>window.__playinfo__=(.*?)</script>', html_audio)[0]

    json_data_audio = json.loads(info_audio)

    audio_url = json_data_audio['data']['dash']['audio'][0]['baseUrl']

    return audio_url

def GetTitile():
    response_audio = GetResponse_AV()

    html = response_audio.text

    title = re.findall('<title data-vue-meta="true">(.*?)</title>', html)[0]

    print("原名为：",title)

    video_json[title] = title

    if not title:
        title = '未知'
        if title:
            illegal_chars = fr'<|>\/:"*?'
            def remove_illegal_chars(title_ill):
                for char in illegal_chars:
                    title_ill = title_ill.replace(char, "")
                return title_ill
            title = remove_illegal_chars(title)
        else:
            return None
    elif len(title) > 30:
        # 如果名字过长，就取前20对反爬虫策略有一定的反制手段，如使用代理IP、设置随机访问时间、获取ajax等个字符
        title = title[:30]
    return title

# 仅用作测试
def GetHTML():
    response = GetResponse_AV()
    html = response.text
    return html

# # 测试代码
if __name__ == '__main__':
    A = GetAudioInfo()
    print(A)
    B = GetVideoInfo()
    print(B)
    C = GetTitile()
    print('修饰过后名字为：',C)
    D = GetHTML()
    pprint(D)