import asyncio
import time
from functools import wraps
import os

import requests  # aiohttp
from bs4 import BeautifulSoup
import pymongo


url = "http://47.103.13.124:8001/base"
urls = [url] * 10

cookies = {
    'session': '.eJyrViotTi1SsqpWyiyOT0zJzcxTsjLQUcrJTwexSopKU3WUcvOTMnNSlayUDM3gQEkHrDE-M0XJyhjCzkvMBSmKKTVNMjMDkiamFkq1tQDfeR3n.YKXKWQ.QcA_zWfTFZFGlGik_5milrY3gRA'
}

client = pymongo.MongoClient(host='localhost', port=27017)
db = client.crawler
collection = db.demo1


def run_time(func):
    @wraps(func)
    def wrapper(*args, **kwargs):
        start = time.perf_counter()  # 启动时间
        r = func(*args, **kwargs)
        end = time.perf_counter()  # 结束时间
        print(f'PID: {os.getpid()}{func.__module__}.{func.__name__}: {end - start}')
        return r
    return wrapper


async def crawler(_url):
    # 发起网络请求，是阻塞
    # 0.1 + 0.1 + 0.1 = 0.3
    r = requests.get(_url, cookies=cookies)
    soup = BeautifulSoup(r.text, 'lxml')

    movie_list = soup.find('div', class_='movie-list').find_all('a')
    datas = []
    for movie in movie_list:

        img_url = movie.find('img').attrs.get('src')
        title = movie.find('h5').get_text()
        desc = movie.find('p').get_text()
        score = movie.find('small').get_text()

        desc2 = movie.find('small').find_next_sibling('small').get_text()
        datas.append({
            'img_url': img_url,
            'title': title,
            'desc': desc,
            'score': score,
            'desc2': desc2
        })
    # 将执行的权限，交出去，自己被挂起，执行完之后，回到事件循环
    time.sleep(1)
    # await asyncio.sleep(1)
    # 将数据插入 mongo 中
    collection.insert_many(datas)


# async def main():
#     for _url in urls:
#         # 只有自己一个任务，在串行执行
#         await crawler(_url)


async def main():
    tasks = []
    for _url in urls:
        tasks.append(asyncio.create_task(crawler(_url)))
    await asyncio.wait(tasks)


@run_time
def run():
    asyncio.run(main())


run()