Python爬虫之Requests库基本使用详解

# 导入模块
import urllib.request
import requests
url = "https://www.baidu.com"
# requests 和 urllib.request 响应对象类型对比
# equests 发送get请求
response_s = requests.get(url=url)
# 打印响应对象：Response
print(type(response_s))
# urllib.request发送get请求
response = urllib.request.urlopen(url=url)
# 打印响应对象：HTTPResponse
print(type(response))

import urllib.request
import requests
url = "https://www.baidu.com"
response_s = requests.get(url=url)
# 打印响应对象字符编码
print(response_s.encoding)
# 指定响应对象字符编码为utf-8
response_s.encoding="utf-8"
# 打印状态码
print(response_s.status_code)
# 打印请求url
print(response_s.url)
# 打印头信息
print(response_s.headers)
# 打印cookie信息
print(response_s.cookies)
# 以字符串形式打印网页源码
print(response_s.text)
# 以二进制数据形式打印网页源码
print(response_s.content)

# 响应对象字符编码
ISO-8859-1
# 状态码
200
# url 地址
https://www.baidu.com/
# 响应头信息
{'Cache-Control': 'private, no-cache, no-store, proxy-revalidate, no-transform', 'Connection': 'keep-alive', 'Content-Encoding': 'gzip', 'Content-Type': 'text/html', 'Date': 'Fri, 19 Aug 2022 01:27:47 GMT', 'Last-Modified': 'Mon, 23 Jan 2017 13:23:55 GMT', 'Pragma': 'no-cache', 'Server': 'bfe/1.0.8.18', 'Set-Cookie': 'BDORZ=27315; max-age=86400; domain=.baidu.com; path=/', 'Transfer-Encoding': 'chunked'}
# cookie信息
<RequestsCookieJar[<Cookie BDORZ=27315 for .baidu.com/>]>