crawler_suisuiniannianyoufuqi/main/ssnnyfq_recommend.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2022/11/7
import os
import random
import sys
import time
import ffmpeg
import requests
import urllib3
sys.path.append(os.getcwd())
from main.common import Common
from main.feishu_lib import Feishu
from main.ssnnyfq_publish import Publish


class Recommend:
    page = 0

    @classmethod
    def get_video_info_from_local(cls, video_path):
        probe = ffmpeg.probe(video_path)
        video_stream = next((stream for stream in probe['streams'] if stream['codec_type'] == 'video'), None)
        if video_stream is None:
            print('No video stream found!')
            return
        width = int(video_stream['width'])
        height = int(video_stream['height'])
        duration = float(video_stream['duration'])
        return width, height, duration

    @classmethod
    def get_feeds(cls, log_type, env):
        try:
            while True:
                url = 'https://www.jzkksp.com/index/home/get_home_list.html'
                headers = {
                    'content-type': 'application/x-www-form-urlencoded',
                    'Accept-Encoding': 'gzip,compress,br,deflate',
                    'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 13_3_1 like Mac OS X) '
                                  'AppleWebKit/605.1.15 (KHTML, like Gecko) '
                                  'Mobile/15E148 MicroMessenger/8.0.25(0x1800192b) NetType/WIFI Language/zh_CN',
                    'Referer': 'https://servicewechat.com/wxd4c54f60812f6f36/1/page-frame.html',
                }
                cls.page += 1
                data = {
                    'token': '851ae159fd33f955bf433e7c47a4a298',
                    'time': '1667905857000',
                    'str_data': 'uT551tU8',
                    'page': str(cls.page),
                    'limit': '10',
                    'appid': 'wxd4c54f60812f6f36',
                    'version': '1.4.1',
                    'openid': 'oDAjy5SCFe7Ml3PNgiow3ncozL1o'
                }
                urllib3.disable_warnings()
                response = requests.post(url=url, headers=headers, data=data, verify=False)
                if 'data' not in response.json():
                    Common.logger(log_type).warning('response:{}\n', response.text)
                    cls.page = 0
                    return
                elif len(response.json()['data']['video_list']['data']) == 0:
                    Common.logger(log_type).warning('response:{}', response.json())
                    Common.logger(log_type).info('视频列表返回空，退出\n')
                    cls.page = 0
                    return
                else:
                    feeds = response.json()['data']['video_list']['data']
                    Common.logger(log_type).info('page:{}\n', cls.page)
                    for i in range(len(feeds)):
                        # video_title
                        if 'title' not in feeds[i]:
                            video_title = 0
                        else:
                            video_title = feeds[i]['title']

                        # video_id
                        if 'id' not in feeds[i]:
                            video_id = 0
                        else:
                            video_id = feeds[i]['id']

                        # play_cnt
                        if 'browse' not in feeds[i]:
                            play_cnt = 0
                        else:
                            play_cnt = feeds[i]['browse']

                        # publish_time
                        if 'createtime' not in feeds[i]:
                            publish_time = 0
                        else:
                            publish_time = feeds[i]['createtime']

                        # cover_url
                        if 'thumb' not in feeds[i]:
                            cover_url = 0
                        else:
                            cover_url = feeds[i]['thumb']

                        # video_url
                        if 'url' not in feeds[i]:
                            video_url = 0
                        else:
                            video_url = feeds[i]['url']

                        Common.logger(log_type).info('video_title:{}', video_title)
                        Common.logger(log_type).info('video_id:{}', video_id)
                        Common.logger(log_type).info('play_cnt:{}', play_cnt)
                        Common.logger(log_type).info('publish_time:{}', publish_time)
                        Common.logger(log_type).info('cover_url:{}', cover_url)
                        Common.logger(log_type).info('video_url:{}', video_url)

                        if video_id == 0 or video_title == 0 or cover_url == 0 or video_url == 0:
                            Common.logger(log_type).info('无效视频\n')
                        elif int(video_id) in [x for y in Feishu.get_values_batch(log_type, 'ssnnyfq', '290bae') for x in y]:
                            Common.logger(log_type).info('视频已下载\n')
                        else:
                            Common.download_method(log_type, 'cover', video_title, cover_url)
                            Common.download_method(log_type, 'video', video_title, video_url)
                            # 获取视频时长
                            video_info = cls.get_video_info_from_local(
                                "./videos/" + video_title + "/video.mp4")
                            video_width = str(video_info[0])
                            video_height = str(video_info[1])
                            duration = video_info[2]
                            # 保存视频信息至 "./videos/{download_video_title}/info.txt"
                            with open("./videos/" + video_title
                                      + "/" + "info.txt", "a", encoding="UTF-8") as f_a:
                                f_a.write("ssnnyfq" + str(int(time.time())) + "\n" +
                                          str(video_title) + "\n" +
                                          str(int(duration)) + "\n" +
                                          str(play_cnt) + "\n" +
                                          '0' + "\n" +
                                          '0' + "\n" +
                                          '0' + "\n" +
                                          str(video_width) + '*' + str(video_height) + "\n" +
                                          str(int(time.time())) + "\n" +
                                          '岁岁年年迎福气小程序' + "\n" +
                                          str(cover_url) + "\n" +
                                          str(video_url) + "\n" +
                                          str(cover_url) + "\n" +
                                          "suisuiniannianyingfuqi" + str(int(time.time())))
                            Common.logger(log_type).info("==========视频信息已保存至info.txt==========")

                            # 上传视频
                            Common.logger(log_type).info("开始上传视频:{}".format(video_title))
                            if env == 'dev':
                                our_video_id = Publish.upload_and_publish(log_type, env, "width")
                                our_video_link = "https://testadmin.piaoquantv.com/cms/post-detail/" + str(
                                    our_video_id) + "/info"
                            else:
                                our_video_id = Publish.upload_and_publish(log_type, env, "width")
                                our_video_link = "https://admin.piaoquantv.com/cms/post-detail/" + str(
                                    our_video_id) + "/info"
                            Common.logger(log_type).info("视频上传完成，保存至已下载表")

                            # 视频ID工作表，插入首行
                            Feishu.insert_columns(log_type, "ssnnyfq", "290bae", "ROWS", 1, 2)
                            # 视频ID工作表，首行写入数据
                            upload_time = int(time.time())
                            values = [[time.strftime("%Y/%m/%d %H:%M:%S", time.localtime(upload_time)),
                                       "推荐榜",
                                       video_title,
                                       video_id,
                                       our_video_link,
                                       play_cnt,
                                       int(duration),
                                       str(video_width) + '*' + str(video_height),
                                       cover_url,
                                       video_url]]
                            time.sleep(1)
                            Feishu.update_values(log_type, "ssnnyfq", "290bae", "F2:V2", values)
                            Common.logger(log_type).info("视频:{}，下载/上传成功，随机休眠 10-30 秒\n", video_title)
                            time.sleep(random.randint(10, 30))

        except Exception as e:
            Common.logger(log_type).error('get_feeds异常:{}\n', e)


if __name__ == '__main__':
    Recommend.get_feeds('recommend', 'dev')