comprehensive_video_rewriting/channel/ks.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 KS:

    @classmethod
    def get_ks_list(cls, task, fs_channel_name):
        #  快手app
        list = []
        url = "http://8.217.192.46:8889/crawler/kuai_shou/blogger"

        try:
            if not task["channel_url"] or not task["channel_url"].strip():
                return []
            if "历史" in task['channel']:
                sort_type = "最热"
            else:
                sort_type = "最新"
            next_cursor = ""
            for i in range(5):
                payload = json.dumps({
                    "account_id": task["channel_url"],
                    "sort_type": sort_type,
                    "cursor": next_cursor
                })
                headers = {
                    'Content-Type': 'application/json'
                }
                time.sleep(random.randint(1, 5))
                response = requests.request("POST", url, headers=headers, data=payload, timeout=30)
                response = response.json()

                data_all_list = response["data"]

                has_more = data_all_list["has_more"]
                next_cursor = str(data_all_list["next_cursor"])

                data_list = data_all_list["data"]
                for data in data_list:
                    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'])

                    view_count = data["view_count"]
                    share_count = data["share_count"]
                    old_title = data["caption"]  # 标题

                    video_percent = '%.4f' % (int(share_count) / (view_count))
                    duration = data["duration"]
                    duration = int(duration)/1000
                    special = float(0.0001)
                    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, "不符合规则:分享/浏览小于0.0001", "2003", log_data)
                        continue
                    if int(share_count) < 500:
                        AliyunLogger.logging(task['channel'], fs_channel_name, task['channel_url'], photo_id, "不符合规则:分享小于500", "2003", log_data)
                        continue
                    if int(duration) < 30 or (duration) > 720:
                        AliyunLogger.logging(task['channel'], fs_channel_name, task['channel_url'], photo_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
                    video_url, image_url = cls.get_video(photo_id)
                    if video_url:
                        log_data = f"user:{task['channel']},,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)

                        if len(list) == int(task['count']):
                            return list
                    else:
                        AliyunLogger.logging(task['channel'], fs_channel_name, task['channel_url'], photo_id, "无法获取到视频链接", "2003", log_data)
                        continue
                if has_more == False:
                    return list
                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