转载:https://www.cnblogs.com/c-x-a/p/10001353.html
# coding=utf-8 import asyncio import pyppeteer from collections import namedtuple Response = namedtuple("rs", "title url html cookies headers history status") async def get_html(url, timeout=30): # 默认30s browser = await pyppeteer.launch(headless=True, args=['--no-sandbox']) page = await browser.newPage() res = await page.goto(url, options={'timeout': int(timeout * 1000)}) data = await page.content() title = await page.title() resp_cookies = await page.cookies() resp_headers = res.headers resp_history = None resp_status = res.status response = Response(title=title, url=url, html=data, cookies=resp_cookies, headers=resp_headers, history=resp_history, status=resp_status) return response if __name__ == '__main__': url_list = ["http://www.10086.cn/index/tj/index_220_220.html", "http://www.10010.com/net5/011/", "http://python.jobbole.com/87541/"] task = (get_html(url) for url in url_list) loop = asyncio.get_event_loop() results = loop.run_until_complete(asyncio.gather(*task)) for res in results: print(res.title)