carry_video_rewriting/data_channel/shipinhao.py

import json
import random
import time

import requests

from common import Common, AliyunLogger, Feishu
from common.sql_help import sqlCollect
from data_channel.data_help import dataHelp


class SPH:

    @classmethod
    def find_target_user(cls, name, user_list):
        """
        在搜索到到账号列表中找目标列表
        """
        for obj in user_list:
            if obj['contact']["nickname"] == name:
                return obj
            else:
                continue
        return False

    @classmethod
    def get_account_id(cls, account_name):
        channel = 'shipinhao'
        history_id = sqlCollect.get_history_id(channel, account_name)
        if history_id:
            return history_id
        else:
            url = "http://47.236.68.175:8889/crawler/wei_xin/shi_pin_hao/account_info"
            payload = json.dumps({
                "account_name": account_name
            })
            headers = {
                'Content-Type': 'application/json'
            }

            response = requests.request("POST", url, headers=headers, data=payload)
            response = response.json()
            if response['code'] == 0:
                data = response['data']['data']

                channel_account_id = data['channel_account_id']
                if channel_account_id:
                    sqlCollect.insert_history_id(account_name, channel_account_id, channel)


                    return channel_account_id
                else:
                    return False
            else:
                Feishu.finish_bot("shi_pin_hao/account_info接口获取失败",
                                  "https://open.feishu.cn/open-apis/bot/v2/hook/575ca6a1-84b4-4a2f-983b-1d178e7b16eb",
                                  "【视频号接口异常提示 】")
                return False

    @classmethod
    def get_sph_url(cls, task_mark, url_id, number, mark, channel_id, name):
        account_id = cls.get_account_id(url_id)
        if account_id:
            url = "http://47.236.68.175:8889/crawler/wei_xin/shi_pin_hao/blogger"
            next_cursor = ""
            list = []
            # for i in range(10):
            headers = {
                'Content-Type': 'application/json'
            }
            payload = json.dumps({
                "account_id": account_id,
                "cursor": next_cursor
            })
            try:
                response = requests.request("POST", url, headers=headers, data=payload)
                time.sleep(random.randint(1, 5))
                res_json = response.json()
                if res_json['code'] == 0:
                    # next_cursor = res_json['data']['next_cursor']
                    data_lsit = res_json['data']['data']
                    if data_lsit == None:
                        return list
                    for obj in data_lsit:
                        objectId = obj['id']
                        status = sqlCollect.is_used(task_mark, objectId, mark, "视频号")

                        old_title = obj['objectDesc']['description']
                        url_p = obj['objectDesc']['media'][0]['Url']
                        url_token = obj['objectDesc']['media'][0]['urlToken']
                        video_url = f"{url_p}{url_token}"
                        decode_key = obj['objectDesc']['media'][0]['decodeKey']
                        cover = obj['objectDesc']['media'][0]['coverUrl']

                        share_cnt = int(obj['forwardCount'])  # 分享
                        like_cnt = int(obj['likeCount'])  # 点赞
                        duration = int(obj['objectDesc']['media'][0]['VideoPlayLen'])
                        # duration = int(duration_ms) / 1000

                        log_data = f"user:{url_id},,video_id:{objectId},,video_url:{video_url},,original_title:{old_title},,share_count:{share_cnt},,like_count:{like_cnt},,duration:{duration}"
                        AliyunLogger.logging(channel_id, name, url_id, objectId, "扫描到一条视频", "2001", log_data)
                        Common.logger("sph").info(
                            f"扫描：{task_mark},用户主页id:{url_id},视频id{objectId} ,分享:{share_cnt},点赞:{like_cnt}")
                        if status:
                            AliyunLogger.logging(channel_id, name, url_id, objectId, "该视频已改造过", "2002", log_data)
                            continue
                        video_percent = '%.2f' % (share_cnt / like_cnt)
                        special = float(0.25)
                        if like_cnt >= 30000 or like_cnt >= 50000 or (share_cnt >= 300 and float(video_percent) >= special):
                            if int(duration) < 30 or int(duration) > 720:
                                Common.logger("sph").info(
                                    f"任务：{task_mark},用户主页id:{url_id},视频id{objectId} ,分享:{share_cnt},点赞:{like_cnt} ,时长:{duration} ")
                                AliyunLogger.logging(channel_id, name, url, objectId, "不符合规则:时长不符合规则大于720秒/小于30秒",
                                                     "2003", log_data)

                                continue
                            all_data = {"video_id": objectId, "cover": cover, "video_url": video_url, "rule": video_percent, "old_title": old_title, "decode_key": decode_key}
                            list.append(all_data)
                            AliyunLogger.logging(channel_id, name, url_id, objectId, "符合规则等待改造", "2004", log_data)
                            if len(list) == int(number):
                                Common.logger(mark).info(f"获取视频号视频总数:{len(list)}\n")
                                return list
                        else:
                            AliyunLogger.logging(channel_id, name, url_id, objectId, "不符合规则:点赞小于30000/50000 或 分享/点赞小于0.25和分享小于300", "2003", log_data)

                            Common.logger("sph").info(
                                     f"不符合规则：{task_mark},用户主页id:{url_id},视频id{objectId} ,分享:{share_cnt},点赞:{like_cnt}")
                            continue
                    return list
            except Exception as e:
                print(e)
                return list


if __name__ == '__main__':
    SPH.get_sph_url('1',"人民日报",'10','2',"视频号",'视频号品类账号')