import requests
import re
import random


class BLBL(object):
    def __init__(self, url, cookie, referer):
        # 需要爬取的網頁字首 例如:https://www.bilibili.com/video/av49035382       ?from=search&seid=1058195128616882249
        self.base_url = url
        # cookie內容
        self.cookie = cookie
        #
 
 referer內容
        self.referer = referer
        # 請求頭資訊
        self.accept = 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3'
        self.accept_Encoding = 'gzip, deflate, br'
        self.accept_Language = 'zh-CN,zh;q=0.9,en;q=0.8'
        self.user_agent 
 
= "User-Agent:Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) "

    def html(self):
        # 訪問起始網頁需新增的請求頭，不加的話，得不到完整的原始碼（反爬）
        base_headers = {
            'Accept': self.accept,
            'Accept-Encoding': self.accept_Encoding,
            'Accept-Language
 
': self.accept_Language,
            'Cache-Control': 'max-age=0',
            'Connection': 'keep-alive',
            'Cookie': self.cookie,
            'Host': 'www.bilibili.com',
            'Referer': self.referer,
            'Upgrade-Insecure-Requests': '1',
            'User-Agent': self.user_agent
        }
        # 請求網頁
        base_response = requests.get(self.base_url, headers=base_headers)
        print(base_headers)
        # 獲取網頁html程式碼
        html = base_response.text
        # print(html.headers)
        return html

    def xin_xi(self, html):
        print(html)
        try:
            # 獲取視訊名稱
            video_name = re.search('<title>(.+)</title>', html, re.S).group(1) + '.flv'
        except:
            # 如果獲取失敗,就隨機一個名字
            video_name = str(random.randint(100000,1000000))+'.flv'
        print(video_name)
        # 獲取視訊連結
        download_url = re.search(r'("url":"|"baseUrl":"|"backupUrl":\[")(.+?)("|"])', html, re.S).group(2)
        print(download_url,111)
        # 獲取主機資訊
        host = re.search(r'//(.+\.com)', download_url, re.S).group(1)
        print(host)
        return video_name, download_url, host

    def video(self, html):
        # 獲取視訊名稱,視訊網址,主機
        video_name, download_url, host = self.xin_xi(html)
        # 請求視訊下載地址時需要新增的請求頭
        download_headers = {
            'User-Agent': self.user_agent,
            'Referer': self.referer,
            'Origin': 'https://www.bilibili.com',
            'Host': host,
            'Accept': self.accept,
            'Accept-Encoding': self.accept_Encoding,
            'Accept-Language': self.accept_Language
        }
        # 獲取視訊資源,並寫入檔案
        with open(video_name, 'wb') as f:
            f.write(requests.get(download_url, headers=download_headers, stream=True, verify=False).content)

    def run(self):
        html = self.html()
        self.video(html)
        print('爬取成功')


if __name__ == '__main__':
    url=input("請輸入網址:")
    cookie = "" //這裡要自己登入b站後得到開啟控制檯得到自己的cookie
    blbl = BLBL(url, cookie, referer)
    blbl.run()