import asyncio import aiohttp from lxml import etree import re from collections import namedtuple Args = namedtuple(‘Args‘,[‘city‘,‘year‘,‘month‘]) async def work(args): url = "/lishi/%s/month/%d%02d.html" % (args.city, args.year, args.month) headers = {‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36‘} async with aiohttp.ClientSession() as session: async with session.get(url, headers=headers, timeout=1000, verify_ssl=False) as response: html = await response.text() ethtml = etree.HTML(html) result = [re.sub("\r\n *","",item.text) for item in ethtml.xpath("//table[@class=‘b‘]/tr/td") if not re.fullmatch("\r\n *",item.text)] return result loop = asyncio.get_event_loop() tasks = [asyncio.ensure_future(work(Args(‘wuhan‘, , month))) for month in range(1,6)] loop.run_until_complete(asyncio.wait(tasks)) for task in tasks: print(task.result())
