- requests.get(url,headers = headers,timeout = 3) #设置超时参数，若url在三秒内未得到响应，报错
from retrying import retry
@retry(stop_max_attempt_number = 3）
示例(访问百度)import requests
from retrying import retry
#专门请求url的方法
@retry(stop_max_attempt_number = 3) #让被装饰的函数反复执行三次，三次都报错才会报错，一次成功即为成长
def aparse_url(url):
print("此处计入装饰器"+"*"*100)
response = requests.get(url,headers = headers,timeout = 5)
print("此处获取url反馈")
return response.content.decode()
def parse_url(url):
try:
html_str = aparse_url(url)
except:
html_str = None
return html_str
if __name__ == '__main__':
headers = {"User-Agent":"Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1",
"Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language":"zh-CN,zh;q=0.9",
"Connection":"keep-alive"}
url = "https://www.baidu.com"
print("程序的起点")
print(parse_url(url)[:100])程序的起点
此处计入装饰器****************************************************************************************************
此处获取url反馈
<!DOCTYPE html>
<html class=""><!--STATUS OK--><head><meta name="referrer" content="always" /><metaPython3 headers = { “User-agent”:”…”,”Cookie”:”cookie” }2.cookie字典传给cookies参数
requests.get(url,cookies = cookie_dict)
3.先发送post请求，获取cookie，带上cookie请求登陆后的页面
