from asyncio import tasks
from aiohttp.client import ClientSession
from lxml import etree
from time import sleep
import time
import asyncio
import aiohttp

async def read_page_list(page_num,sem):
    params = {
        'page':page_num,
    }
    #通過連接池控制并發(fā)數量 limit 默認為100  0 為無限制
    async with sem:
        try:
            async with aiohttp.ClientSession() as session:
                async with session.get(url=url,params=params,headers=headers) as response:
                    text = await response.text()
        except Exception as e:
            print('exception:',e)
        
        tree = etree.HTML(text)
        page_list = tree.xpath('//*[@id="thumbs"]/section[1]/ul/li')
        # break
        for li in page_list:
            pic_small_url = li.xpath('.//img/@data-src')[0]
            # print(pic_small_url,type(pic_small_url))
            # pic_small_url = str(pic_small_url)
            if 'small' in pic_small_url:
                temp_url = pic_small_url.replace('small','full')
                a = temp_url.rfind('/')
                temp_url1= temp_url[:a]
                pic_full_url = temp_url1+'/wallhaven-'+temp_url.split('/')[-1]
                pic_full_url = pic_full_url.replace('th','w')
                # print(page_num,pic_full_url)
                pic_list.append(pic_full_url)
            else:
                print(page_num,'find small error',pic_small_url)
            
        print(page_num,len(page_list),response.status)
        # await asyncio.sleep(1)
        #這里可以用硬延時來控制程序的訪問速度，進而控制單位時間內并發(fā)的數量
        # sleep(0.5)

#定義信號量
sem = asyncio.Semaphore(2)

start = time.time()
#建立任務列表
tasks = [loop.create_task(read_page_list(i,sem)) for i in range(1,20)]
loop.run_until_complete(asyncio.wait(tasks))
print('get page list use time:',time.time()-start)