comprehensive_video_rewriting/channel/ks_keyword.py

import random
import time

import requests
import json

from utils.aliyun_log import AliyunLogger
from utils.feishu_form import Material
from utils.sql_help import sqlCollect


class KsKeyword:
    @classmethod
    def get_key_word(cls, task, fs_channel_name):
        combo = task['combo']
        sort_type = combo[0]
        publish_time = combo[1]
        duration = combo[2]
        share_count_rule = 0
        special = 0
        short_duration_rule = 0

        url = "http://8.217.192.46:8889/crawler/kuai_shou/keyword"
        list = []
        if not task["channel_url"] or not task["channel_url"].strip():
            return list
        payload = json.dumps({
            "keyword": task["channel_url"],
            "content_type": "视频",
            "sort_type": sort_type,
            "publish_time": publish_time,
            "duration": duration,
            "cursor": ""
        })
        headers = {
            'Content-Type': 'application/json'
        }
        if " 不限" == publish_time:
            share_count_rule = 100
            special = 0.0005
            short_duration_rule = 25
        elif "近1日" == publish_time:
            share_count_rule = 0
            special = 0.0003
            short_duration_rule = 25
        elif "近7日" == publish_time:
            share_count_rule = 50
            special = 0.0005
            short_duration_rule = 25
        elif "近1月" == publish_time:
            share_count_rule = 100
            special = 0.0005
            short_duration_rule = 25
        try:
            time.sleep(3)
            response = requests.request("POST", url, headers=headers, data=payload, timeout=30)
            response = response.json()
            code = response['code']
            if code != 0:
                return list
            data_list = response['data']['data']
            for data in data_list:
                data = data['feed']
                photo_id =  data['photo_id']
                day_count = Material.get_count_restrict(task["channel"])
                if day_count:
                    status = sqlCollect.is_used_days(photo_id, task['channel'], day_count)
                else:
                    status = sqlCollect.is_used(photo_id, task['channel'])

                image_url = data['cover_thumbnail_urls'][0]['url']
                video_url = data['main_mv_urls'][0]['url']
                if ".mp4" not in video_url:
                    continue
                view_count = data.get('view_count', 0)
                share_count = data.get('share_count', 0)
                old_title = data['caption']  # 标题

                video_percent = '%.4f' % (int(share_count) / int(view_count))
                duration = int(int(data["duration"]) / 1000)
                log_data = f"user:{task['channel_url']},,video_id:{photo_id},,video_url:'',original_title:{old_title},,share_count:{share_count},,view_count:{view_count},,duration:{duration}"

                AliyunLogger.logging(task['channel'], fs_channel_name, task['channel_url'], photo_id, "扫描到一条视频", "2001", log_data)
                if status:
                    AliyunLogger.logging(task['channel'], fs_channel_name, task['channel_url'], photo_id, "该视频已改造过", "2002", log_data)
                    continue
                if float(video_percent) < special:
                    AliyunLogger.logging(task['channel'], fs_channel_name, task['channel_url'], photo_id, f"不符合规则:分享/浏览{special}", "2003", log_data)

                    continue
                if int(share_count) < share_count_rule:
                    AliyunLogger.logging(task['channel'], fs_channel_name, task['channel_url'], photo_id, f"不符合规则:分享小于{share_count_rule}", "2003", log_data)
                    continue
                if int(duration) < short_duration_rule or int(duration) > 720:
                    AliyunLogger.logging(task['channel'], fs_channel_name, task['channel_url'], photo_id, f"不符合规则:时长不符合规则大于720秒/小于{short_duration_rule}", "2003",
                                         log_data)
                    continue

                log_data = f"user:{task['channel_url']},,video_id:{photo_id},,video_url:{video_url},,original_title:{old_title},,share_count:{share_count},,view_count:{view_count},,duration:{duration}"
                all_data = {"video_id": photo_id, "cover": image_url, "video_url": video_url,
                            "rule": video_percent,
                            "old_title": old_title}
                list.append(all_data)
                AliyunLogger.logging(task['channel'], fs_channel_name, task['channel_url'], photo_id, "符合规则等待改造", "2004", log_data)
            return list
        except Exception as exc:
            return list

    @classmethod
    def get_video(cls, video_id):
        url = "http://8.217.192.46:8889/crawler/kuai_shou/detail"

        payload = json.dumps({
            "content_id": str(video_id)
        })
        headers = {
            'Content-Type': 'application/json'
        }
        time.sleep(random.uniform(1, 10))

        response = requests.request("POST", url, headers=headers, data=payload, timeout=30)
        response = response.json()
        data = response["data"]["data"]
        video_url = data["video_url_list"][0]["video_url"]
        image_url = data["image_url_list"][0]["image_url"]
        return video_url, image_url