crawler_haokan/main/demo.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2022/11/23
import time
import requests
from main.common import Common
from main.feishu_lib import Feishu


class Demo:
    @classmethod
    def get_sheet(cls, log_type, crawler, sheetid):
        sheet = Feishu.get_values_batch(log_type, crawler, sheetid)
        print(sheet)

    @classmethod
    def publish_time(cls):
        time1 = '发布时间：2022年11月20日'
        time2 = time1.replace('发布时间：', '').replace('年', '/').replace('月', '/').replace('日', '')
        print(time2)
        time3 = int(time.mktime(time.strptime(time2, "%Y/%m/%d")))
        print(time3)

    @classmethod
    def get_video_url(cls, log_type, video_id):
        url = 'https://haokan.hao123.com/v?'
        params = {
            'vid': video_id,
            '_format': 'json',
        }
        headers = {
            'Accept': '*/*',
            'Accept-Encoding': 'gzip, deflate, br',
            'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
            'Cache-Control': 'no-cache',
            'Connection': 'keep-alive',
            'Content-Type': 'application/x-www-form-urlencoded',
            'Cookie': 'PC_TAB_LOG=video_details_page; COMMON_LID=b0be69dd9fcae328d06935bd40f615cd; Hm_lvt_4aadd610dfd2f5972f1efee2653a2bc5=1669029953; hkpcvideolandquery=%u82CF%u5DDE%u6700%u5927%u7684%u4E8C%u624B%u8F66%u8D85%u5E02%uFF0C%u8F6C%u4E00%u8F6C%u91CC%u8FB9%u8C6A%u8F66%u592A%u591A%u4E86%uFF0C%u4EF7%u683C%u66F4%u8BA9%u6211%u5403%u60CA%uFF01; Hm_lpvt_4aadd610dfd2f5972f1efee2653a2bc5=1669875695; ariaDefaultTheme=undefined; reptileData=%7B%22data%22%3A%22636c55e0319da5169a60acec4a264a35c10862f8abfe2f2cc32c55eb6b0ab4de0efdfa115ea522d6d4d361dea07feae2831d3e2c16ed6b051c611ffe5aded6c9f852501759497b9fbd2132a2160e1e40e5845b41f78121ddcc3288bd077ae4e8%22%2C%22key_id%22%3A%2230%22%2C%22sign%22%3A%22f6752aac%22%7D; RT="z=1&dm=hao123.com&si=uc0q7wnm4w&ss=lb4otu71&sl=j&tt=av0&bcn=https%3A%2F%2Ffclog.baidu.com%2Flog%2Fweirwood%3Ftype%3Dperf&ld=1rdw&cl=7v6c"',
            'Pragma': 'no-cache',
            'Referer': 'https://haokan.hao123.com/v?vid=10623278258033022286&pd=pc&context=',
            'sec-ch-ua': '"Microsoft Edge";v="107", "Chromium";v="107", "Not=A?Brand";v="24"',
            'sec-ch-ua-mobile': '?0',
            'sec-ch-ua-platform': '"macOS"',
            'Sec-Fetch-Dest': 'empty',
            'Sec-Fetch-Mode': 'cors',
            'Sec-Fetch-Site': 'same-origin',
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 Edg/107.0.1418.62',
        }
        r = requests.get(url=url, headers=headers, params=params)
        if r.status_code != 200:
            Common.logger(log_type).info(f'get_video_url_response:{r.text}')
        elif r.json()['errno'] != 0 or len(r.json()['data']) == 0:
            Common.logger(log_type).info(f'get_video_url_response:{r.json()}')
        else:
            clarityUrl = r.json()['data']['apiData']['curVideoMeta']['clarityUrl']
            video_url = r.json()['data']['apiData']['curVideoMeta']['clarityUrl'][len(clarityUrl)-1]['url']

            return video_url


if __name__ == '__main__':
    # Demo.get_sheet('demo', 'haokan', '7f05d8')
    # Demo.publish_time()
    Demo.get_video_url('demo', '10377041690614321392')
    pass