Python爬虫headers处理及网络超时问题解决方案

import requests
# 创建需要爬取网页的地址
url = 'https://www.baidu.com/'   
# 创建头部信息
headers = {'User-Agent':'OW64; rv:59.0) Gecko/20100101 Firefox/59.0'}
# 发送网络请求
respOnse= requests.get(url, headers=headers)  
# 以字节流形式打印网页源码
print(response.content)

b'\n\n\n  \n  \n              

import requests
# 循环发送请求50次
for a in range(1, 50):
  # 捕获异常
  try:
    # 设置超时为0.5秒
    respOnse= requests.get('https://www.baidu.com/', timeout=0.5)
    # 打印状态码
    print(response.status_code)
  # 捕获异常
  except Exception as e:
    # 打印异常信息
    print('异常'+str(e))

200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200

import requests
# 导入requests.exceptions模块中的三种异常类
from requests.exceptions import ReadTimeout,HTTPError,RequestException
# 循环发送请求50次
for a in range(1, 50):
  # 捕获异常
  try:
    # 设置超时为0.5秒
    respOnse= requests.get('https://www.baidu.com/', timeout=0.5)
    # 打印状态码
    print(response.status_code)
  # 超时异常
  except ReadTimeout:
    print('timeout')
  # HTTP异常
  except HTTPError:
    print('httperror')
  # 请求异常
  except RequestException:
    print('reqerror')

200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200
200