video_editor_agc/data_main.py

# -*- coding: utf-8 -*-

from common import Material, Feishu
from extract_data.douyin.douyin_author import douyinAuthor
from extract_data.kuaishou.kuaishou_author import kuaishouAuthor

import schedule
import time
import concurrent.futures
import threading
import os

# 控制读写速度的参数
MAX_BPS = 10 * 1024 * 1024  # 120MB/s
MAX_WORKERS = os.cpu_count() * 2  # 线程池最大工作线程数量
READ_WRITE_CHUNK_SIZE = 1024 * 1024  # 每次读写的块大小 (1MB)
SLEEP_INTERVAL = READ_WRITE_CHUNK_SIZE / MAX_BPS  # 控制每次读写的延迟时间
# 全局锁，用于同步读写操作
lock = threading.Lock()

# 定义读取表格的函数
def douyin_start(user_data):
    print(f"执行抖音数据抓取{user_data}")
    douyinAuthor.get_videoList(user_data)

def kuaishou_start(user_data):
    print(f"执行快手数据抓取{user_data}")
    kuaishouAuthor.get_kuaishou_videoList(user_data)


# 定义定时任务
def douyin_task():
    data = Material.get_all_user("douyin")
    # 创建一个线程池
    with concurrent.futures.ThreadPoolExecutor(max_workers=MAX_WORKERS) as executor:
        futures = {executor.submit(douyin_start, user_data): user_data for user_data in data}
        # 等待所有任务执行完成
        for future in concurrent.futures.as_completed(futures):
            # 获取每个任务的执行结果
            result = future.result()
            print("处理结果:", result)
    print("抖音数据抓取定时任务执行完成")


# 定义定时任务
def kuanshou_task():
    data = Material.get_all_user("kuaishou")
    # 创建一个线程池
    with concurrent.futures.ThreadPoolExecutor(max_workers=MAX_WORKERS) as executor:
        futures = {executor.submit(kuaishou_start, user_data): user_data for user_data in data}
        # 等待所有任务执行完成
        for future in concurrent.futures.as_completed(futures):
            # 获取每个任务的执行结果
            result = future.result()
            print("处理结果:", result)
    print("快手数据抓取定时任务执行完成.")


schedule.every(8).hours.do(douyin_task)

schedule.every(8).hours.do(kuanshou_task)
douyin_task()
kuanshou_task()
# 持续运行，直到手动终止
while True:
    schedule.run_pending()
    time.sleep(1)