video_rewriting/data_channel/sph_keyword.py

import re
import time

import requests
import json

from common import Feishu, AliyunLogger, Material
from common.sql_help import sqlCollect


class SphKeyword:

    @classmethod
    def time_str_to_seconds(cls, time_str):
        # 分钟和秒用 ":" 分隔
        minutes, seconds = map(int, time_str.split(":"))
        # 转换为秒
        total_seconds = minutes * 60 + seconds
        return total_seconds

    @classmethod
    def get_key_word(cls, keyword, task_mark, mark, channel_id, name):
        url = "http://8.217.192.46:8889/crawler/wei_xin/shi_pin_hao/keyword"
        list = []
        payload = json.dumps({
            "keyword": keyword,
            "sort": "不限",
            "cursor": ""
        })
        headers = {
            'Content-Type': 'application/json'
        }
        try:
            time.sleep(1)
            response = requests.request("POST", url, headers=headers, data=payload, timeout=30)
            response = response.json()
            code = response['code']
            if code != 0:
                Feishu.finish_bot(f"shi_pin_hao/keyword {response['msg']}",
                                  "https://open.feishu.cn/open-apis/bot/v2/hook/575ca6a1-84b4-4a2f-983b-1d178e7b16eb",
                                  "【视频号搜索接口使用提示】")
                return list
            data_list = response['data']['data']
            for data in data_list:
                items = data['items'][0]
                video_id = data["boxID"]
                duration = items["duration"]
                if duration == '' or duration == None:
                    duration = "00:01"
                duration = cls.time_str_to_seconds(duration)
                digg_count = items.get('likeNum', "0")
                if digg_count == '10万+':
                    digg_count = '100000'
                old_title =items.get('title', "")
                old_title = re.sub(r'<em.*?>.*?</em>', '', old_title)
                cover_url = items["image"]
                video_url = items["videoUrl"]
                log_data = f"user:{keyword},,video_id:{video_id},,video_url:{video_url},,original_title:{old_title},,digg_count:{digg_count},,duration:{duration}"
                AliyunLogger.logging(channel_id, name, keyword, video_id, "扫描到一条视频", "2001", log_data)
                day_count = Material.get_count_restrict(channel_id)
                if day_count:
                    status = sqlCollect.is_used_days(task_mark, video_id, mark, channel_id, day_count)
                else:
                    status = sqlCollect.is_used(task_mark, video_id, mark, channel_id)
                if status:
                    AliyunLogger.logging(channel_id, name, keyword, video_id, "该视频已改造过", "2002", log_data)
                    continue
                if int(digg_count) < 2000:
                    AliyunLogger.logging(channel_id, name, keyword, video_id, f"不符合规则:点赞小于2000", "2003",
                                         log_data)
                    continue
                if int(duration) < 30 or int(duration) > 900:
                    AliyunLogger.logging(channel_id, name, keyword, video_id, f"不符合规则:时长不符合规则大于900秒/小于30秒", "2003", log_data)
                    continue
                all_data = {"video_id": video_id, "cover": cover_url, "video_url": video_url, "rule": '',
                            "old_title": old_title}
                list.append(all_data)
                AliyunLogger.logging(channel_id, name, keyword, video_id, "符合规则等待改造", "2004", log_data)
            return list
        except Exception as exc:
            return list


if __name__ == '__main__':
    SphKeyword.get_key_word('最有钱的地方', '', '', '', '')