5）定制头和cookie信息
header = {'user-agent': 'my-app/0.0.1''} cookie = {'key':'value'} r = requests.get/post('your url',headers=header,cookies=cookie) data = {'some': 'data'} headers = {'content-type': 'application/json', 'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:22.0) Gecko/20100101 Firefox/22.0'} r = requests.post('https://api.github.com/some/endpoint', data=data, headers=headers) print(r.text)
6）响应状态码
使用requests方法后，会返回一个response对象，其存储了服务器响应的内容，如上实例中已经提到的 r.text、r.status_code……
获取文本方式的响应体实例：当你访问 r.text 之时，会使用其响应的文本编码进行解码，并且你可以修改其编码让 r.text 使用自定义的编码进行解码。
r = requests.get('http://www.itwhy.org') print(r.text, '\n{}\n'.format('*'*79), r.encoding) r.encoding = 'GBK' print(r.text, '\n{}\n'.format('*'*79), r.encoding)
示例代码：
import requests r = requests.get('https://github.com/Ranxf') # 最基本的不带参数的get请求 print(r.status_code) # 获取返回状态 r1 = requests.get(url='http://dict.baidu.com/s', params={'wd': 'python'}) # 带参数的get请求 print(r1.url) print(r1.text) # 打印解码后的返回数据
运行结果：
/usr/bin/python3.5 /home/rxf/python3_1000/1000/python3_server/python3_requests/demo1.py 200 http://dict.baidu.com/s?wd=python ………… Process finished with exit code 0 r.status_code #如果不是200，可以使用 r.raise_for_status() 抛出异常
7）响应
r.headers #返回字典类型,头信息 r.requests.headers #返回发送到服务器的头信息 r.cookies #返回cookie r.history #返回重定向信息,当然可以在请求是加上allow_redirects = false 阻止重定向
8）超时
r = requests.get('url',timeout=1) #设置秒数超时，仅对于连接有效
9)会话对象，能够跨请求保持某些参数
s = requests.Session() s.auth = ('auth','passwd') s.headers = {'key':'value'} r = s.get('url') r1 = s.get('url1')
10）代理
proxies = {'http':'ip1','https':'ip2' } requests.get('url',proxies=proxies)
汇总：
# 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': '香港', '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=香港 #获取/修改网页编码 r = requests.get('https://github.com/timeline.json') print （r.encoding） #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://10.10.1.10:3128", "https": "http://10.10.1.100:4444", } r = requests.get('http://m.ctrip.com', proxies=proxies) #如果代理需要用户名和密码，则需要这样： proxies = { "http": "http://user:pass@10.10.1.10:3128/", } # 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': '香港', '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=香港 #获取/修改网页编码 r = requests.get('https://github.com/timeline.json') print （r.encoding） #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://10.10.1.10:3128", "https": "http://10.10.1.100:4444", } r = requests.get('http://m.ctrip.com', proxies=proxies) #如果代理需要用户名和密码，则需要这样： proxies = { "http": "http://user:pass@10.10.1.10:3128/", }
3、示例代码
GET请求
# 1、无参数实例 import requests ret = requests.get('https://github.com/timeline.json') print(ret.url) print(ret.text) # 2、有参数实例 import requests payload = {'key1': 'value1', 'key2': 'value2'} ret = requests.get("http://httpbin.org/get", params=payload) print(ret.url) print(ret.text)
POST请求
# 1、基本POST实例 import requests payload = {'key1': 'value1', 'key2': 'value2'} ret = requests.post("http://httpbin.org/post", data=payload) print(ret.text) # 2、发送请求头和数据实例 import requests import json url = 'https://api.github.com/some/endpoint' payload = {'some': 'data'} headers = {'content-type': 'application/json'} ret = requests.post(url, data=json.dumps(payload), headers=headers) print(ret.text) print(ret.cookies)请求参数
请求参数
def request(method, url, **kwargs): """Constructs and sends a :class:`Request <Request>`. :param method: method for the new :class:`Request` object. :param url: URL for the new :class:`Request` object. :param params: (optional) Dictionary or bytes to be sent in the query string for the :class:`Request`. :param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`. :param json: (optional) json data to send in the body of the :class:`Request`. :param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`. :param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`. :param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': file-tuple}``) for multipart encoding upload. ``file-tuple`` can be a 2-tuple ``('filename', fileobj)``, 3-tuple ``('filename', fileobj, 'content_type')`` or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content-type'`` is a string defining the content type of the given file and ``custom_headers`` a dict-like object containing additional headers to add for the file. :param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth. :param timeout: (optional) How long to wait for the server to send data before giving up, as a float, or a :ref:`(connect timeout, read timeout) <timeouts>` tuple. :type timeout: float or tuple :param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed. :type allow_redirects: bool :param proxies: (optional) Dictionary mapping protocol to the URL of the proxy. :param verify: (optional) whether the SSL cert will be verified. A CA_BUNDLE path can also be provided. Defaults to ``True``. :param stream: (optional) if ``False``, the response content will be immediately downloaded. :param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair. :return: :class:`Response <Response>` object :rtype: requests.Response Usage:: >>> import requests >>> req = requests.request('GET', 'http://httpbin.org/get') <Response [200]> """ def param_method_url(): # requests.request(method='get', url='http://127.0.0.1:8000/test/') # requests.request(method='post', url='http://127.0.0.1:8000/test/') pass def param_param(): # - 可以是字典 # - 可以是字符串 # - 可以是字节（ascii编码以内） # requests.request(method='get', # url='http://127.0.0.1:8000/test/', # params={'k1': 'v1', 'k2': '水电费'}) # requests.request(method='get', # url='http://127.0.0.1:8000/test/', # params="k1=v1&k2=水电费&k3=v3&k3=vv3") # requests.request(method='get', # url='http://127.0.0.1:8000/test/', # params=bytes("k1=v1&k2=k2&k3=v3&k3=vv3", encoding='utf8')) # 错误 # requests.request(method='get', # url='http://127.0.0.1:8000/test/', # params=bytes("k1=v1&k2=水电费&k3=v3&k3=vv3", encoding='utf8')) pass def param_data(): # 可以是字典 # 可以是字符串 # 可以是字节 # 可以是文件对象 # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # data={'k1': 'v1', 'k2': '水电费'}) # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # data="k1=v1; k2=v2; k3=v3; k3=v4" # ) # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # data="k1=v1;k2=v2;k3=v3;k3=v4", # headers={'Content-Type': 'application/x-www-form-urlencoded'} # ) # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # data=open('data_file.py', mode='r', encoding='utf-8'), # 文件内容是：k1=v1;k2=v2;k3=v3;k3=v4 # headers={'Content-Type': 'application/x-www-form-urlencoded'} # ) pass def param_json(): # 将json中对应的数据进行序列化成一个字符串，json.dumps(...) # 然后发送到服务器端的body中，并且Content-Type是 {'Content-Type': 'application/json'} requests.request(method='POST', url='http://127.0.0.1:8000/test/', json={'k1': 'v1', 'k2': '水电费'}) def param_headers(): # 发送请求头到服务器端 requests.request(method='POST', url='http://127.0.0.1:8000/test/', json={'k1': 'v1', 'k2': '水电费'}, headers={'Content-Type': 'application/x-www-form-urlencoded'} ) def param_cookies(): # 发送Cookie到服务器端 requests.request(method='POST', url='http://127.0.0.1:8000/test/', data={'k1': 'v1', 'k2': 'v2'}, cookies={'cook1': 'value1'}, ) # 也可以使用CookieJar（字典形式就是在此基础上封装） from http.cookiejar import CookieJar from http.cookiejar import Cookie obj = CookieJar() obj.set_cookie(Cookie(version=0, name='c1', value='v1', port=None, domain='', path='/', secure=False, expires=None, discard=True, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False, port_specified=False, domain_specified=False, domain_initial_dot=False, path_specified=False) ) requests.request(method='POST', url='http://127.0.0.1:8000/test/', data={'k1': 'v1', 'k2': 'v2'}, cookies=obj) def param_files(): # 发送文件 # file_dict = { # 'f1': open('readme', 'rb') # } # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # files=file_dict) # 发送文件，定制文件名 # file_dict = { # 'f1': ('test.txt', open('readme', 'rb')) # } # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # files=file_dict) # 发送文件，定制文件名 # file_dict = { # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf") # } # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # files=file_dict) # 发送文件，定制文件名 # file_dict = { # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf", 'application/text', {'k1': '0'}) # } # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # files=file_dict) pass def param_auth(): from requests.auth import HTTPBasicAuth, HTTPDigestAuth ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('wupeiqi', 'sdfasdfasdf')) print(ret.text) # ret = requests.get('http://192.168.1.1', # auth=HTTPBasicAuth('admin', 'admin')) # ret.encoding = 'gbk' # print(ret.text) # ret = requests.get('http://httpbin.org/digest-auth/auth/user/pass', auth=HTTPDigestAuth('user', 'pass')) # print(ret) # def param_timeout(): # ret = requests.get('http://google.com/', timeout=1) # print(ret) # ret = requests.get('http://google.com/', timeout=(5, 1)) # print(ret) pass def param_allow_redirects(): ret = requests.get('http://127.0.0.1:8000/test/', allow_redirects=False) print(ret.text) def param_proxies(): # proxies = { # "http": "61.172.249.96:80", # "https": "http://61.185.219.126:3128", # } # proxies = {'http://10.20.1.128': 'http://10.10.1.10:5323'} # ret = requests.get("http://www.proxy360.cn/Proxy", proxies=proxies) # print(ret.headers) # from requests.auth import HTTPProxyAuth # # proxyDict = { # 'http': '77.75.105.165', # 'https': '77.75.105.165' # } # auth = HTTPProxyAuth('username', 'mypassword') # # r = requests.get("http://www.google.com", proxies=proxyDict, auth=auth) # print(r.text) pass def param_stream(): ret = requests.get('http://127.0.0.1:8000/test/', stream=True) print(ret.content) ret.close() # from contextlib import closing # with closing(requests.get('http://httpbin.org/get', stream=True)) as r: # # 在此处理响应。 # for i in r.iter_content(): # print(i) def requests_session(): import requests session = requests.Session() ### 1、首先登陆任何页面，获取cookie i1 = session.get(url="http://dig.chouti.com/help/service") ### 2、用户登陆，携带上一次的cookie，后台对cookie中的 gpsd 进行授权 i2 = session.post( url="http://dig.chouti.com/login", data={ 'phone': "8615131255089", 'password': "xxxxxx", 'oneMonth': "" } ) i3 = session.post( url="http://dig.chouti.com/link/vote?linksId=8589623", ) print(i3.text)
json请求：
#! /usr/bin/python3 import requests import json class url_request(): def __init__(self): ''' init ''' if __name__ == '__main__': heard = {'Content-Type': 'application/json'} payload = {'CountryName': '中国', 'ProvinceName': '四川省', 'L1CityName': 'chengdu', 'L2CityName': 'yibing', 'TownName': '', 'Longitude': '107.33393', 'Latitude': '33.157131', 'Language': 'CN'} r = requests.post("http://www.xxxxxx.com/CityLocation/json/LBSLocateCity", heards=heard, data=payload) 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.dump(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：
#! /usr/bin/python3 import requests class url_request(): def __init__(self): """init""" if __name__ == '__main__': heards = {'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=url, heards=heards, data=XML) data = r.text print(data)
状态异常处理
import requests URL = 'http://ip.taobao.com/service/getIpInfo.php' # 淘宝IP地址库API try: r = requests.get(URL, params={'ip': '8.8.8.8'}, timeout=1) r.raise_for_status() # 如果响应状态码不是 200，就主动抛出异常 except requests.RequestException as e: print(e) else: result = r.json() print(type(result), result, sep='\n')
上传文件
使用request模块，也可以上传文件，文件的类型会自动进行处理：
import requests url = 'http://127.0.0.1:8080/upload' files = {'file': open('/home/rxf/test.jpg', 'rb')} #files = {'file': ('report.jpg', open('/home/lyb/sjzl.mpg', 'rb'))} #显式的设置文件名 r = requests.post(url, files=files) print(r.text)
request更加方便的是，可以把字符串当作文件进行上传：
import requests url = 'http://127.0.0.1:8080/upload' files = {'file': open('/home/rxf/test.jpg', 'rb')} #files = {'file': ('report.jpg', open('/home/lyb/sjzl.mpg', 'rb'))} #显式的设置文件名 r = requests.post(url, files=files) print(r.text)
request更加方便的是，可以把字符串当作文件进行上传：
import requests url = 'http://127.0.0.1:8080/upload' files = {'file': ('test.txt', b'Hello Requests.')} #必需显式的设置文件名 r = requests.post(url, files=files) print(r.text)
