Python——request模块

1.Requsets模块的安装

进入cmd

cd C:Python27Scripts
pip install requests

2.Requests模块的简单使用

#HTTP请求类型
#无参数的get类型
r = requests.get('http://httpbin.org/get')
#有参的get类型
payload = {'key1':'vaule1','key2':'value2'}
r = requests.get(url,params=payload)
#无参的post类型
r = requests.post("http://httpbin.org/post")
#有参的post类型
r = requests.post(url,data=payload)
#data不光可以接受字典类型的数据，还可以接受json等格式
import json
payload = {'a':'杨','b':'hello'}
r = requests.post('http://httpbin.org/post', data=json.dumps(payload))
#发送文件的post类型，这个相当于向网站上传一张图片，文档等操作，这时要使用files参数
files = {'file': open('touxiang.png', 'rb')}
r = requests.post('http://httpbin.org/post', files=files)
#put类型
r = requests.put("http://m.ctrip.com/put")
#delete类型
r = requests.delete("http://m.ctrip.com/delete")
#head类型
r = requests.head("http://m.ctrip.com/head")
#options类型
r = requests.options("http://m.ctrip.com/get")

#获取响应内容
print r.content #以字节的方式去显示，中文显示为字符
print r.text #以文本的方式去显示

#URL传递参数
payload = {'keyword': '日本', 'salecityid': '2'}
r = requests.get("http://m.ctrip.com/webapp/tourvisa/visa_list", params=payload) 
print r.url #示例为http://m.ctrip.com/webapp/tourvisa/visa_list?salecityid=2&keyword=日本

#获取/修改网页编码
r = requests.get('https://github.com/timeline.json')
print r.encoding
r.encoding = 'utf-8'

#json处理
r = requests.get('https://github.com/timeline.json')
print r.json() #需要先import json    

#定制请求头
url = 'http://m.ctrip.com'
headers = {'User-Agent' : 'Mozilla/5.0 (Linux; Android 4.2.1; en-us; Nexus 4 Build/JOP40D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166 Mobile Safari/535.19'}
r = requests.post(url, headers=headers)
print r.request.headers

#复杂post请求
url = 'http://m.ctrip.com'
payload = {'some': 'data'}
r = requests.post(url, data=json.dumps(payload)) #如果传递的payload是string而不是dict，需要先调用dumps方法格式化一下

#post多部分编码文件
url = 'http://m.ctrip.com'
files = {'file': open('report.xls', 'rb')}
r = requests.post(url, files=files)

#响应状态码
r = requests.get('http://m.ctrip.com')
print r.status_code
    
#响应头
r = requests.get('http://m.ctrip.com')
print r.headers
print r.headers['Content-Type']
print r.headers.get('content-type') #访问响应头部分内容的两种方式
    
#Cookies
r = requests.get('http://www.baidu.com')
r.cookies['BAIDUID']  #读取cookies
    
url = 'http://m.ctrip.com/cookies'
cookies = dict(cookies_are='working')
r = requests.get(url, cookies=cookies) #发送cookies

#设置超时时间
r = requests.get('http://m.ctrip.com', timeout=0.001)
#访问中使用session
s = requests.Session() #先初始化一个session对象
r = s.post(url,data = user) #然后使用这个session对象来进行访问
#设置访问代理
proxies = {
           "http": "http://10.10.10.10:8888",
           "https": "http://10.10.10.100:4444",
          }
r = requests.get('http://m.ctrip.com', proxies=proxies)

3.json请求

#!/user/bin/env python
#coding=utf-8
import requests
import json

class url_request():
    def __init__(self):
            """ init """    

if __name__=='__main__':
    headers = {'Content-Type' : 'application/json'}
    payload = {'CountryName':'中国',
               'ProvinceName':'陕西省',
               'L1CityName':'汉中',
               'L2CityName':'城固',
               'TownName':'',
               'Longitude':'107.33393',
               'Latitude':'33.157131',
               'Language':'CN'
               }
    r = requests.post("http://www.xxxxxx.com/CityLocation/json/LBSLocateCity",headers=headers,data=payload)
    #r.encoding = 'utf-8'
    data=r.json()
    if r.status_code!=200:
        print "LBSLocateCity API Error " + str(r.status_code)
    print data['CityEntities'][0]['CityID'] #打印返回json中的某个key的value
    print data['ResponseStatus']['Ack']
    print json.dumps(data,indent=4,sort_keys=True,ensure_ascii=False) #树形打印json，ensure_ascii必须设为False否则中文会显示为unicode

4.xml请求

#!/user/bin/env python
#coding=utf-8
import requests

class url_request():
    def __init__(self):
            """ init """    

if __name__=='__main__':
    
    headers = {'Content-type': 'text/xml'}
    XML = '<?xml version="1.0" encoding="utf-8"?><soap:Envelope xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:soap="http://schemas.xmlsoap.org/soap/envelope/"><soap:Body><Request xmlns="http://tempuri.org/"><jme><JobClassFullName>WeChatJSTicket.JobWS.Job.JobRefreshTicket,WeChatJSTicket.JobWS</JobClassFullName><Action>RUN</Action><Param>1</Param><HostIP>127.0.0.1</HostIP><JobInfo>1</JobInfo><NeedParallel>false</NeedParallel></jme></Request></soap:Body></soap:Envelope>'
    url = 'http://jobws.push.mobile.xxxxxxxx.com/RefreshWeiXInTokenJob/RefreshService.asmx'
    r = requests.post(url,headers=headers,data=XML)
    #r.encoding = 'utf-8'
    data = r.text
    print data

5.Requests模拟登入实例

import requests

payload = {'action:login':'','uid':'08133248','domain':'cumt.edu.cn','nodetect':'false','password':'wattcswh','locale':'zh_CN'}
header = {
"Host": "mail.cumt.edu.cn",
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:49.0) Gecko/20100101 Firefox/49.0",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3",
"Accept-Encoding": "gzip, deflate",
"Referer": "http://acm.hdu.edu.cn/",
"Cookie": "uid=08133248",
"Connection": "keep-alive"
}

s = requests.Session()
r = s.post('http://mail.cumt.edu.cn/coremail/index.jsp',data=payload,headers=header)
print r.status_code

6.快速口算 分值: 350

小明要参加一个高技能比赛，要求每个人都要能够快速口算四则运算，2秒钟之内就能够得到结果，但是小明就是一个小学生没有经过特殊的培训，那小明能否通过快速口算测验呢？

import re
try:
    import requests
except ImportError:
    raise SystemExit('cuole')
s = requests.Session()
url='http://lab1.xseclab.com/xss2_0d557e6d2a4ac08b749b61473a075be1/index.php'
r = s.get(url)
res = unicode(r.content,'utf-8').encode('gbk')
num = re.findall(re.compile(r'<br/>s+(.*?)='),res)[0]
r = s.post(url,data={'v':eval(num)})
key = re.findall(re.compile(r'<body>(.*?)</body>'), r.content)[0]
open('d:/ans.txt','w').write(str(key))