Python requests

Table of Contents

get 请求

requests.get()

params 参数

json() 请求的是 json格式的可以调用 json()方法

添加headers 请求头

抓取二进制文件

post 请求

响应

判断请求是否成功

高级

文件上传

cookie 模拟登录

SSL证书验证verfiy参数改为False

会话维持 session

 代理设置

超时设置 timeout

---

get 请求

requests.get()

import requests

r = requests.get('http://www.baidu.com')

print(r.status_code)
print(r.headers)
print(r.cookies)
print(r.content)
print(r.text)

params 参数

import requests

data = {
    'name': 'germey',
    'age': 22
}
r = requests.get("http://httpbin.org/get", params=data)
print(r.text)

r2 = requests.get('http://httpbin.org/get?name=germey&age=22')
print(r2.text)

json() 请求的是 json格式的可以调用 json()方法

import requests

r = requests.get("https://www.lagou.com/lbs/getAllCitySearchLabels.json")
print(r.json())
print(type(r.json()))

添加headers 请求头

import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
}
r = requests.get("https://www.baidu.com",headers=headers)
print(r.text)

抓取二进制文件

import requests

r = requests.get("https://github.com/favicon.ico")
print(r.text)
print(r.content)

with open('1.ico','wb') as f:
    f.write(r.content)

post 请求

import requests

data = {'name': 'test', 'age': '21','sex':'男'}
r = requests.post("http://httpbin.org/post", data=data)
print(r.text)

响应

import requests

r = requests.get('http://www.baidu.com')
# 状态码
print(type(r.status_code), r.status_code)
# 响应头
print(type(r.headers), r.headers)
# Cookies
print(type(r.cookies), r.cookies)
# 请求 url
print(type(r.url), r.url)
# 请求历史
print(type(r.history), r.history)

判断请求是否成功

import requests

r = requests.get('http://www.baidu.com')
# requests.codes.ok得到的是成功的状态码200
exit() if not r.status_code == requests.codes.ok else print('Request Successfully')

---

高级

文件上传

import requests

files = {'file': open('1.ico', 'rb')}
r = requests.post("http://httpbin.org/post", files=files)
print(r.text)

cookie 模拟登录

import requests

url = 'https://weibo.com/u/6539720569/home?topnav=1&wvr=6&pids=plc_main&ajaxpagelet=1&ajaxpagelet_v6=1&__ref=%2Fu%2F6539720569%2Fhome%3Ftopnav%3D1%26wvr%3D6&_t=FM_1542900004053124'
h = {
    'Host': 'weibo.com',
    'Connection': 'keep-alive',
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    # 'Referer': 'https://weibo.com/u/6539720569?is_all=1',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh,zh-CN;q=0.9,en;q=0.8',
    'Cookie': 'SINAGLOBAL=94993410627.1666.1520769274152; _s_tentry=cuiqingcai.com; Apache=5017072227083.262.1542629483779; ULV=1542629483995:36:4:1:5017072227083.262.1542629483779:1542205550567; YF-Page-G0=e44a6a701dd9c412116754ca0e3c82c3; login_sid_t=1a7ba97fe27f566ce119097abd18c565; cross_origin_proto=SSL; Ugrow-G0=56862bac2f6bf97368b95873bc687eef; TC-V5-G0=ac3bb62966dad84dafa780689a4f7fc3; wb_view_log=1920*10801; WBtopGlobal_register_version=18608f873d5d88f2; appkey=; TC-Page-G0=9183dd4bc08eff0c7e422b0d2f4eeaec; wb_view_log_6539720569=1920*10801; un=*******; SUBP=0033WrSXqPxfM725Ws9jqgMF55529P9D9WWEa9ykHUXNGmUlEp4N8evQ5JpX5K2hUgL.Foqfe0.Neo5fSo.2dJLoI7LsUgSuPfxLMNBt; ALF=1574412019; SSOLoginState=1542876019; SCF=AnI7F2A3uDMtu9SYi3j9FdPQsitEYhJntfyXE0_5tz7YOAwXZ7AwlRXenxkj7aWPri2XdxCDtCa9bY0i9InJHI0.; SUB=_2A2528hsjDeRhGeBL6FsW8i7JzTWIHXVVhgvrrDV8PUNbmtAKLWzZkW9NRwIFFJ3DRFJNQh-yiz7GUXwmJX5WcXuB; SUHB=0k1CqncARZEaj7; wvr=6; UOR=,,www.baidu.com',
}
r = requests.get(url,headers=h,verify=False)
print(r.text)

SSL证书验证verfiy参数改为False

import requests

url = 'https://weibo.com'

r = requests.get(url,verify=False)
print(r.text)

会话维持 session

import requests

s = requests.Session()
s.get('http://httpbin.org/cookies/set/number/123456789')
r = s.get('http://httpbin.org/cookies')
print(r.text)

 代理设置

import requests
 
proxies = {
  "http": "http://112.240.176.185:4213",
  "https": "http://112.240.176.185:4213",
}
 
requests.get("https://www.taobao.com", proxies=proxies)

超时设置 timeout

import requests

r = requests.get("https://www.taobao.com", timeout=0.1,verify=False)
print(r.status_code)