爬虫请求模块-urllib

import urllib.request
import urllib.parse
import urllib.error
import socket

# 发送get请求
# response=urllib.request.urlopen('https://www.baidu.com/')         #默认get方法
# print(type(response))
# print(response.status)       #响应状态码
# print(response.getheaders())   #响应头信息
# print(response.read().decode('utf-8'))              #读取html信息并utf-8解码

# 发送post请求
# url = 'https://www.httpbin.org/post'  # post请求测试
# data = bytes(urllib.parse.urlencode({'hello': 'python'}), encoding='utf-8')  # 将表单数据转换为bytes类型
# response = urllib.request.urlopen(url=url, data=data)
# print(response.read().decode('utf-8'))

# 设置网络超时
# 1
# url = 'https://www.python.org/'
# response = urllib.request.urlopen(url=url, timeout=0.1)
# print(response.read().decode('utf-8'))
# 2
# url = 'https://www.python.org/'
# try:
#     response = urllib.request.urlopen(url=url, timeout=1)
#     print(response.read().decode('utf-8'))
# except urllib.error.URLError as error:
#     if isinstance(error.reason,socket.timeout):     #判断异常是否为超时
#         print('当前任务超时，进入下一个任务')

# 设置请求头
# url = 'https://python.org/'
# headers = {'User-Agent': 'Mozilla/5.0'}
# data = bytes(urllib.parse.urlencode({'hello': 'python'}), encoding='utf-8')
# r = urllib.request.Request(url=url, data=data, headers=headers, method='POST')  #将headers信息添加在request对象中
# response=urllib.request.urlopen(r)
# print(response.read().decode('utf-8'))

#cookies的获取和设置
#设置代理ip
#异常处理
#解析链接