video_rewriting/data_channel/douyin.py

import json
import random
import time

import requests
import urllib3
from requests.adapters import HTTPAdapter
from common import Material, Feishu, AliyunLogger
from common.sql_help import sqlCollect
from data_channel.douyin_help import DouYinHelper


class DY:

    @classmethod
    def get_dy_url(cls, task_mark, url_id, number, mark, feishu_id, cookie_sheet, channel_id, name):
        list = []
        next_cursor = 0
        try:
            for i in range(6):
                cookie = Material.get_cookie_data(feishu_id, cookie_sheet, channel_id)
                time.sleep(random.randint(1, 5))
                url = 'https://www.douyin.com/aweme/v1/web/aweme/post/'
                headers = {
                    'Accept': 'application/json, text/plain, */*',
                    'Accept-Language': 'zh-CN,zh;q=0.9',
                    'Cache-Control': 'no-cache',
                    'Cookie': cookie,
                    'Pragma': 'no-cache',
                    'Referer': f'https://www.douyin.com/user/{url_id}',
                    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) '
                                  'Chrome/118.0.0.0 Safari/537.36',
                }
                query = DouYinHelper.get_full_query(ua=headers['User-Agent'], extra_data={
                    'sec_user_id': url_id,
                    'max_cursor': next_cursor,
                    'locate_query': 'false',
                    'show_live_replay_strategy': '1',
                    'need_time_list': '1',
                    'time_list_query': '0',
                    'whale_cut_token': '',
                    'cut_version': '1',
                    'count': '18',
                    'publish_video_strategy_type': '2',
                })
                urllib3.disable_warnings()
                s = requests.session()
                s.mount('http://', HTTPAdapter(max_retries=3))
                s.mount('https://', HTTPAdapter(max_retries=3))
                response = requests.request(method='GET', url=url, headers=headers, params=query, timeout=30)
                body = response.content.decode()
                obj = json.loads(body)
                has_more = True if obj.get('has_more', 0) == 1 else False
                next_cursor = str(obj.get('max_cursor')) if has_more else None
                data = obj.get('aweme_list', [])
                if data == [] and len(data) == 0:
                    if name == '抖音品类账号' or name == '抖音品类账号-1' or name == 'Top溯源账号':
                        # Feishu.bot("wangxueke", '机器自动改造消息通知', f'抖音-{name}cookie过期，请及时更换', '王雪珂')
                        Feishu.bot("xinxin", '机器自动改造消息通知', f'抖音-{name}cookie过期，请及时更换', '信欣')
                        Feishu.bot("liuzhaoheng", '机器自动改造消息通知', f'抖音-{name}cookie过期，请及时更换', '刘兆恒')

                    else:
                        Feishu.bot(mark, '机器自动改造消息通知', f'抖音-{name}cookie过期，请及时更换', name)
                    return list
                response.close()
                for i in range(len(data)):
                    entity_type = data[i].get('media_type')
                    if entity_type == 4:
                        # is_top = data[i].get('is_top')  # 是否置顶
                        video_id = data[i].get('aweme_id')  # 文章id
                        day_count = Material.get_count_restrict(channel_id)
                        if day_count:
                            status =sqlCollect.is_used_days(video_id, mark, channel_id,day_count)
                        else:
                            status = sqlCollect.is_used(video_id, mark, channel_id)

                        video_uri = data[i].get('video', {}).get('play_addr', {}).get('uri')
                        ratio = f'{data[i].get("video", {}).get("height")}p'
                        video_url = data[i].get('video', {}).get('play_addr', {}).get('url_list', [None])[0]
                        # video_url = f'https://www.iesdouyin.com/aweme/v1/play/?video_id={video_uri}&ratio={ratio}&line=0'  # 视频链接
                        digg_count = int(data[i].get('statistics').get('digg_count'))  # 点赞
                        # comment_count = int(data[i].get('statistics').get('comment_count'))  # 评论
                        share_count = int(data[i].get('statistics').get('share_count'))  # 转发
                        old_title = data[i].get('desc', "").strip().replace("\n", "") \
                            .replace("/", "").replace("\\", "").replace("\r", "") \
                            .replace(":", "").replace("*", "").replace("？", "") \
                            .replace("?", "").replace('"', "").replace("<", "") \
                            .replace(">", "").replace("|", "").replace(" ", "") \
                            .replace("&NBSP", "").replace(".", "。").replace(" ", "") \
                            .replace("'", "").replace("#", "").replace("Merge", "")
                        duration = data[i].get('video', {}).get('duration', {})
                        duration = int(duration) // 1000
                        # duration = dataHelp.video_duration(video_url)

                        log_data = f"user:{url_id},,video_id:{video_id},,video_url:{video_url},,original_title:{old_title},,share_count:{share_count},,digg_count:{digg_count},,duration:{duration}"
                        AliyunLogger.logging(channel_id, name, url_id, video_id, "扫描到一条视频", "2001", log_data)
                        if status:
                            AliyunLogger.logging(channel_id, name, url_id, video_id, "该视频已改造过", "2002", log_data)
                            continue
                        if share_count < 200:
                            AliyunLogger.logging(channel_id, name, url_id, video_id, "不符合规则:分享小于200", "2003", log_data)

                            continue
                        video_percent = '%.2f' % (share_count / digg_count)
                        special = float(0.15)
                        if float(video_percent) < special:
                            AliyunLogger.logging(channel_id, name, url_id, video_id, "不符合规则:分享/点赞小于0.15", "2003", log_data)

                            continue

                        if int(duration) < 30 or int(duration) > 720:
                            AliyunLogger.logging(channel_id, name, url_id, video_id, "不符合规则:时长不符合规则大于720秒/小于30秒", "2003", log_data)
                            continue
                        cover_url = data[i].get('video').get('cover').get('url_list')[0]  # 视频封面
                        all_data = {"video_id": video_id, "cover": cover_url, "video_url": video_url,
                                    "rule": video_percent, "old_title": old_title}
                        list.append(all_data)
                        AliyunLogger.logging(channel_id, name, url_id, video_id, "符合规则等待改造", "2004", log_data)
                        if len(list) == int(number):
                            return list

            return list
        except Exception as exc:
            # Feishu.bot("liuzhaoheng", '机器自动改造消息通知', f'抖音-{name}cookie过期，请及时更换', '刘兆恒')
            # Feishu.bot("wangxueke", '机器自动改造消息通知', f'抖音-{name}cookie过期，请及时更换', '王雪珂')
            # Feishu.bot("xinxin", '机器自动改造消息通知', f'抖音-{name}cookie过期，请及时更换', '信欣')
            return list