python3-asyncio异步爬虫测试(无注释demo)
#!/usr/bin/python3 "this is a spider" import re import asyncio import urllib.request, urllib.parse, urllib.error import http.cookiejar async def html(urlAddr): req = urllib.request.Request(urlAddr) """<http.client.HTTPResponse object at 0x7f517e1a2c50>""" response = urllib.request.urlopen(req) html_image = response.read().decode("utf-8") return html_image def re_html(html_image): print(html_image) html_images = html_image.result() li = re.findall(r'data-sa.*\d"', html_images) for temp in li: print(temp) print("------------------") def main(): html_image = html("http://www.lagou.com/zhaopin/Python/1") html_image1 = html("http://www.lagou.com/zhaopin/Python/3") task = asyncio.ensure_future(html_image) task.add_done_callback(re_html) task1 = asyncio.ensure_future(html_image1) task1.add_done_callback(re_html) tasks = [task, task1] loop = asyncio.get_event_loop() loop.run_until_complete(asyncio.wait(tasks)) main()