video_rewriting/data_channel/ks_ls.py

import random
import time
import requests
import json
from common import Feishu, AliyunLogger
from common.sql_help import sqlCollect

class KSLS:

    @classmethod
    def get_ksls_list(cls, task_mark, url_id, number, mark, channel_id, name):
        #  快手app
        url = "http://8.217.192.46:8889/crawler/kuai_shou/blogger"
        next_cursor = ""
        try:
            for i in range(5):
                payload = json.dumps({
                    "account_id": url_id,
                    "sort_type": "最热",
                    "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()
                list = []
                data_all_list = response["data"]
                if data_all_list == None or len(data_all_list) == 0:
                    try:
                        if int(response["cdoe"]) == 27006:
                            Feishu.finish_bot("kuai_shou/blogger接口"+response["msg"],
                                              "https://open.feishu.cn/open-apis/bot/v2/hook/575ca6a1-84b4-4a2f-983b-1d178e7b16eb", "【快手 Token 使用提示 】")
                    except Exception as exc:
                        return list

                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"]
                    status = sqlCollect.is_used(task_mark, photo_id, mark, "快手历史")

                    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(0.0005)
                    log_data = f"user:{url_id},,video_id:{photo_id},,video_url:'',original_title:{old_title},,share_count:{share_count},,view_count:{view_count},,duration:{duration}"

                    AliyunLogger.logging(channel_id, name, url_id, photo_id, "扫描到一条视频", "2001", log_data)
                    # if status:
                    #     AliyunLogger.logging(channel_id, name, url_id, photo_id, "该视频已改造过", "2002", log_data)
                    #     continue
                    if float(video_percent) < special:
                        AliyunLogger.logging(channel_id, name, url_id, photo_id, "不符合规则:分享/浏览小于0.0005", "2003", log_data)
                        continue
                    if int(share_count) < 100:
                        AliyunLogger.logging(channel_id, name, url_id, photo_id, "不符合规则:分享小于100", "2003", log_data)
                        continue
                    if int(duration) < 30 or (duration) > 720:
                        AliyunLogger.logging(channel_id, name, url_id, 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:{url_id},,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(channel_id, name, url_id, photo_id, "符合规则等待改造", "2004", log_data)

                        if len(list) == int(number):
                            return list
                    else:
                        AliyunLogger.logging(channel_id, name, url_id, 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



if __name__ == '__main__':
    # Feishu.finish_bot('测试',
    #                   "https://open.feishu.cn/open-apis/bot/v2/hook/575ca6a1-84b4-4a2f-983b-1d178e7b16eb", "【 Token 使用提示 】")
    # DYLS.get_video("7314923922602954022")
    KSLS.get_ksls_list("1","3xzicxg2nandemc",1,"1",'','')