HTTP request python官方文档:http://cn.python-requests.org/zh_CN/latest/
1. 环境
基于环境,需要安装requests 模块,安装方法 pip install requests
想学习requests,就通过help吧
import requests
help(requests)
返回结果如下:
C:\Python27\python.exe E:/test/interface/g_3.py
Help on package requests: NAME
requests FILE
c:\python27\lib\site-packages\requests\__init__.py DESCRIPTION
Requests HTTP Library
~~~~~~~~~~~~~~~~~~~~~ Requests is an HTTP library, written in Python, for human beings. Basic GET
usage: >>> import requests
>>> r = requests.get('https://www.python.org')
>>> r.status_code
200
>>> 'Python is a programming language' in r.content
True ... or POST: >>> payload = dict(key1='value1', key2='value2')
>>> r = requests.post('http://httpbin.org/post', data=payload)
>>> print(r.text)
{
...
"form": {
"key2": "value2",
"key1": "value1"
},
...
} The other HTTP methods are supported - see `requests.api`. Full documentation
is at <http://python-requests.org>. :copyright: (c) 2017 by Kenneth Reitz.
:license: Apache 2.0, see LICENSE for more details. PACKAGE CONTENTS
__version__
_internal_utils
adapters
api
auth
certs
compat
cookies
exceptions
help
hooks
models
packages
sessions
status_codes
structures
utils FUNCTIONS
check_compatibility(urllib3_version, chardet_version) DATA
__author__ = 'Kenneth Reitz'
__author_email__ = 'me@kennethreitz.org'
__build__ = 137220
__cake__ = u'\u2728 \U0001f370 \u2728'
__copyright__ = 'Copyright 2017 Kenneth Reitz'
__description__ = 'Python HTTP for Humans.'
__license__ = 'Apache 2.0'
__title__ = 'requests'
__url__ = 'http://python-requests.org'
__version__ = '2.18.4'
codes = <lookup 'status_codes'> VERSION
2.18.4 AUTHOR
Kenneth Reitz Process finished with exit code 0
获取requests所有的方法和类,就使用dir吧
import requests
print dir(requests)
返回如下:
['ConnectTimeout', 'ConnectionError', 'DependencyWarning', 'FileModeWarning', 'HTTPError', 'NullHandler', 'PreparedRequest', 'ReadTimeout', 'Request', 'RequestException', 'RequestsDependencyWarning', 'Response', 'Session', 'Timeout', 'TooManyRedirects', 'URLRequired', '__author__', '__author_email__', '__build__', '__builtins__', '__cake__', '__copyright__', '__description__', '__doc__', '__file__', '__license__', '__name__', '__package__', '__path__', '__title__', '__url__', '__version__', '_internal_utils', 'adapters', 'api', 'auth', 'certs', 'chardet', 'check_compatibility', 'codes', 'compat', 'cookies', 'delete', 'exceptions', 'get', 'head', 'hooks', 'logging', 'models', 'options', 'packages', 'patch', 'post', 'put', 'request', 'session', 'sessions', 'status_codes', 'structures', 'urllib3', 'utils', 'warnings']
2. HTTP协议:
根据 HTTP 标准, HTTP 请求可以使用多种请求方法。
HTTP1.0 定义了三种请求方法: GET, POST 和 HEAD 方法。
HTTP1.1 新增了五种请求方法: 共GET, POST, HEAD, OPTIONS, PUT, DELETE, TRACE 和 CONNECT 方法
3. requests模块入门:
#HTTP请求类型
#get类型
r = requests.get('https://github.com/timeline.json')
#post类型
r = requests.post("http://m.ctrip.com/post")
#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': ''}
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
url = 'http://example.com/some/cookie/setting/url'
r = requests.get(url)
r.cookies['example_cookie_name'] #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) #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)
4、Requests示例
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
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