python中requests库基础应用解析

python中requests库基础应用解析，python中requests库的基础应用，网页数据挖掘的常用库之一。也就是说最主要的功能是从网页抓取数据。

python2.7下

#coding:utf-8
#python网络爬虫库requests库应用全解
import requests
import json

print u'================入门================'

r = requests.get('https://cuiqingcai.com')  #返回Response对象
print type(r)
print r.status_code  # 获取返回状态
print r.encoding
print r.cookies
print r.raw #返回原始响应体，也就是 urllib 的 response 对象，使用 r.raw.read() 读取
print r.content #字节方式的响应体，会自动为你解码 gzip 和 deflate 压缩
print r.text #字符串方式的响应体，会自动根据响应头部的字符编码进行解码
r.headers #以字典对象存储服务器响应头，但是这个字典比较特殊，字典键不区分大小写，若键不存在则返回None
#*特殊方法*#
#r.json() #Response中内置的JSON解码器
#r.raise_for_status() #功能：如果失败请求(非200响应)抛出异常


print u'================基本请求================'
r = requests.post("https://httpbin.org/post")
r = requests.put("https://httpbin.org/put")
r = requests.delete("https://httpbin.org/delete")
r = requests.head("https://httpbin.org/get")
r = requests.options("https://httpbin.org/get")

print u'================基本GET请求================'
payload = {'key1': 'value1', 'key2': 'value2'}  #字典数据
headers = {'content-type': 'application/json'}  #header数据
r = requests.get("https://httpbin.org/get", params=payload, headers=headers) #payload可以省略，会在网址中添加
print r.url


print u'================基本POST请求================'

url = 'https://httpbin.org/post'
payload = {'some': 'data'}
r = requests.post(url, data=json.dumps(payload))  #上传json数据
print r.text

url = 'https://httpbin.org/post'
myfiles = {'file': open('test.txt', 'rb')}  #获取文件对象
r = requests.post(url, files=myfiles)  #上传文件
print r.text

#with open('test.txt') as f:  #流式上传
#    requests.post('https://some.url/streamed', data=f)


print u'================Cookies================'

url = 'https://httpbin.org/cookies'
r = requests.get(url)  #响应中会包含cookie
print r.cookies

url = 'https://httpbin.org/cookies'
cookies = dict(cookies_are='working')  #自定义cookie变量
r = requests.get(url, cookies=cookies)  #请求时附带cookie
print r.text

print u'================超时配置================'

requests.get('https://github.com', timeout=1)  #1秒没有响应就报错

print u'================会话对象（持久连接）================'

s = requests.Session()
s.get('https://httpbin.org/cookies/set/sessioncookie/123456789')  #get方式设置cookie
r = s.get("https://httpbin.org/cookies")  #获取cookie
print(r.text)


headers = {'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
           'Accept-Encoding': 'gzip, deflate, compress',
           'Accept-Language': 'en-us;q=0.5,en;q=0.3',
           'Cache-Control': 'max-age=0',
           'Connection': 'keep-alive',
           'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:22.0) Gecko/20100101 Firefox/22.0'}

s = requests.Session()
s.headers.update(headers)  #更新header
r = s.get('https://httpbin.org/headers', headers={'x-test': 'true'})  #get函数中添加的headers会覆盖原有同名，添加不同名的，去除值为None的
print r.text

print u'================SSL证书验证================'

r = requests.get('https://github.com', verify=True)
print r.text

r = requests.get('https://kyfw.12306.cn/otn/', verify=False)  #把 verify 设置为 False即可跳过证书验证
print r.text


print u'================证书================'

proxies = {
  "https": "https://41.118.132.69:4433"
}
r = requests.post("https://httpbin.org/post", proxies=proxies)
print r.text