import requests # 數(shù)據(jù)請求模塊 pip install requests (第三方模塊)
import pprint # 格式化輸出模塊 內(nèi)置模塊 不需要安裝
import re # 正則表達(dá)式
import json

def get_response(html_url):
    # 用python代碼模擬瀏覽器
    # headers 把python代碼進(jìn)行偽裝
    # user-agent 瀏覽器的基本標(biāo)識(shí)
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36'
    }
    # 用代碼直接獲取的 一般大多數(shù)都是直接 cookie
    response = requests.get(url=html_url, headers=headers)
    return response

def get_video_info(video_id):
    html_url = f'https://liveapi.huya.com/moment/getMomentContent?videoId={video_id}&uid=&_=1634127164373'
    response = get_response(html_url)
    title = response.json()['data']['moment']['title'] # 視頻標(biāo)題
    video_url = response.json()['data']['moment']['videoInfo']['definitions'][0]['url']
    video_info = [title, video_url]
    return video_info

def get_video_id(html_url):
    html_data = get_response(html_url).text
    result = re.findall('<script> window.HNF_GLOBAL_INIT = (.*?) </script>', html_data)[0]
    # 需要把獲取的字符串?dāng)?shù)據(jù), 轉(zhuǎn)成json字典數(shù)據(jù)
    json_data = json.loads(result)['videoData']['videoDataList']['value']
    # json_data 列表 里面元素是字典
    # print(json_data)
    video_ids = [i['vid'] for i in json_data]  # 列表推導(dǎo)式
    # lis = []
    # for i in json_data:
    #     lis.append(i['vid'])
    # print(video_ids)
    # print(type(json_data))
    return video_ids

# 目光所至 我皆可爬
def main(html):
    video_ids = get_video_id(html_url=html)
    for video_id in video_ids:
        video_info = get_video_info(video_id)
        save(video_info[0], video_info[1])

def save(title, video_url):
    # 保存數(shù)據(jù), 也是還需要對(duì)于播放地址發(fā)送請求的
    # response.content 獲取響應(yīng)的二進(jìn)制數(shù)據(jù)
    video_content = get_response(html_url=video_url).content
    new_title = re.sub(r'[\/:*?"<>|]', '_', title)
    # 'video\\' + title + '.mp4' 文件夾路徑以及文件名字 mode 保存方式 wb二進(jìn)制保存方式
    with open('video\\' + new_title + '.mp4', mode='wb') as f:
        f.write(video_content)
        print('保存成功: ', title)

if __name__ == '__main__':
    # get_video_info('589462235')
    video_info = get_video_info('589462235')
    save(video_info[0], video_info[1])
    for page in range(1, 6):
        print(f'正在爬取第{page}頁的數(shù)據(jù)內(nèi)容')
        # python基礎(chǔ)入門課程 第一節(jié)課 講解的知識(shí)點(diǎn) 字符串格式化方法
        url = f'https://v.huya.com/g/all?set_id=31&order=hot&page={page}'
        main(url)