python爬虫基础教程：requests库（二）代码实例

get请求

简单使用

import requests
'''
想要学习python？python学习交流群：973783996满足你的需求，资料都已经上传群文件，可以自行下载！
'''
response = requests.get("https://www.baidu.com/")
#text返回的是unicode的字符串，可能会出现乱码情况
# print(response.text)
 
#content返回的是字节，需要解码
print(response.content.decode('utf-8'))
 
 
# print(response.url)       #https://www.baidu.com/
# print(response.status_code)   #200
# print(response.encoding)    #iso-8859-1

添加headers和params

import requests
 
params = {
  'wd':'python'
}
headers = {
  'user-agent':'mozilla/5.0 (windows nt 6.1; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/64.0.3282.140 safari/537.36'
}
 
response = requests.get("https://www.baidu.com/s",params=params,headers=headers)
 
#content返回的是字节，需要解码
with open('baidu.html','w',encoding='utf-8') as f:
  f.write(response.content.decode('utf-8'))

post请求

爬去拉钩网职位信息

import requests
 
url = "https://www.lagou.com/jobs/positionajax.json?city=%e5%8c%97%e4%ba%ac&needaddtionalresult=false"
 
data = {
  'first':'true',
  'pn':1,
  'kd':'python'
}
 
headers = {
  "user-agent":"mozilla/5.0 (windows nt 6.1; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/64.0.3282.140 safari/537.36",
  "referer":"https://www.lagou.com/jobs/list_python?city=%e5%8c%97%e4%ba%ac&cl=false&fromsearch=true&labelwords=&suginput="
}
 
response = requests.post(url,data=data,headers=headers)
# print(response.text)
print(type(response.text))    #<class 'str'>
print(type(response.json()))   #<class 'dict'>
 
print(response.json())      #获取为字典的形式

使用代理

import requests
 
proxy = {'http':'115.210.31.236.55:9000'}
 
response = requests.get("https://www.baidu.com/",proxies=proxy)
 
print(response.content.decode('utf-8'))

session登录

# _*_ coding:utf-8 _*_
 
import requests
 
# 1. 创建session对象，可以保存cookie值
ssion = requests.session()
 
# 2. 处理 headers
headers = {'user-agent':'mozilla/5.0 (windows nt 6.1; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/60.0.3112.101 safari/537.36'}
 
# 3. 需要登录的用户名和密码
data = {"email":"158xxxxxxxx", "password":"pythonxxxxxxx"}
 
# 4. 发送附带用户名和密码的请求，并获取登录后的cookie值，保存在ssion里
ssion.post("http://www.renren.com/plogin.do", data = data)
 
# 5. ssion包含用户登录后的cookie值，可以直接访问那些登录后才可以访问的页面
response = ssion.get("http://zhibo.renren.com/news/108")
 
# 6. 打印响应内容
print(response.text)
 

以上所述是小编给大家介绍的python爬虫基础教程：requests库（二）详解整合，希望对大家有所帮助