python并发爬虫实用工具tomorrow实用解析

pip install requests_html #网络请求包
pip install fake-useragent #获取useragent包
pip install tomorrow

start=time.time()
for i in url_list:
   print(get_xpath(get_req(i),"//title//text()"))
end=time.time()
print("普通方式花费时间",end-start)

start2 = time.time()
req_list = []
for url in url_list:
  req = async_get_req(url)
  req_list.append(req)

for req in req_list:
  print(get_xpath(req, "//title//text()"))
end2 = time.time()
print("并发后花费时间", end2 - start2)

import time
from requests_html import HTMLSession
from fake_useragent import UserAgent as ua
from tomorrow import threads

headers = {"User-Agent": ua().Chrome}
session = HTMLSession()
url_list = ["https://movie.douban.com",
      "http://www.1905.com/",
      "http://www.mtime.com/",
      "https://www.dy2018.com/",
      "http://dytt8.net",
      "https://www.piaohua.com/",
      "http://maoyan.com",
      "https://www.xigua110.com/",
      "https://www.vmovier.com/",
      "http://movie.kankan.com/",
      "https://107cine.com/",
      "http://movie.youku.com",
      "http://film.qq.com",
      "http://film.spider.com.cn",
      "https://dianying.taobao.com/",
      "http://www.wandafilm.com/",
      "http://www.dygang.net/",
      "http://www.bale.cn/",
      "http://dianying.2345.com/",
      "http://v.x2y4.com/"]


def get_req(url, timeout=10):
  req = session.get(url, headers=headers, timeout=timeout)
  if req.status_code == 200:
    return req


@threads(5)
def async_get_req(url, timeout=10):
  req = session.get(url, headers=headers, timeout=timeout)
  if req.status_code == 200:
    return req


def get_xpath(req, xpath_str):
  return req.html.xpath(xpath_str)[0].strip().replace("\n", "")


start=time.time()
for i in url_list:
   print(get_xpath(get_req(i),"//title//text()"))
end=time.time()
print("普通方式花费时间",end-start)

start2 = time.time()
req_list = []
for url in url_list:
  req = async_get_req(url)
  req_list.append(req)

for req in req_list:
  print(get_xpath(req, "//title//text()"))
end2 = time.time()
print("并发后花费时间", end2 - start2)

第一次：
普通方式花费时间 7.883908271789551
并发后花费时间 2.2888755798339844
第二次:
普通方式花费时间 8.522203207015991
并发后花费时间 2.4674007892608643
第三次:
普通方式花费时间 9.062756061553955
并发后花费时间 2.8703203201293945