python的網絡編程能力十分強大,其中python中的requests庫宣言:HTTP for Humans (給人用的 HTTP 庫)html
在網絡編程中,最基本的任務包含:python
- 發送請求
- 登陸
- 獲取數據
- 解析數據
- 反序列化打印內容
目錄:nginx
1、安裝git
2、基本用法github
5、請求頭json
6、響應頭api
7、響應內容瀏覽器
pip install requests
import requests cs_url = 'http://httpbin.org' r = requests.get("%s/%s" % (cs_url, 'get')) r = requests.post("%s/%s" % (cs_url, 'post')) r = requests.put("%s/%s" % (cs_url, 'put')) r = requests.delete("%s/%s" % (cs_url, 'delete')) r = requests.patch("%s/%s" % (cs_url, 'patch')) r = requests.options("%s/%s" % (cs_url, 'get'))
#!/usr/bin/env python # -*- coding: utf-8 -*- import requests payload = {'key1': 'value1', 'key2': 'value2'} # URL 傳參 r = requests.get("http://httpbin.org/get", params=payload) # 獲取請求的 URL print "GET URL:", r.url # POST 發送編碼爲表單形式的數據,requests 會自動將 Python 字典序列化爲實際的表單內容 r = requests.post("http://httpbin.org/post", data=payload) # 獲取響應內容,string print "POST Response:\n", r.content if r.headers.get("content-type") == "application/json": # 獲取響應內容,dict類型 print "r.json:\n", r.json() print "form:\n", r.json().get("form")
輸出結果:
GET URL: http://httpbin.org/get?key2=value2&key1=value1 POST Response: { "args": {}, "data": "", "files": {}, "form": { "key1": "value1", "key2": "value2" }, "headers": { "Accept": "*/*", "Accept-Encoding": "gzip, deflate", "Content-Length": "23", "Content-Type": "application/x-www-form-urlencoded", "Host": "httpbin.org", "User-Agent": "python-requests/2.11.1" }, "json": null, "origin": "124.250.131.130", "url": "http://httpbin.org/post" } r.json: {u'files': {}, u'origin': u'124.250.131.130', u'form': {u'key2': u'value2', u'key1': u'value1'}, u'url': u'http://httpbin.org/post', u'args': {}, u'headers': {u'Content-Length': u'23', u'Accept-Encoding': u'gzip, deflate', u'Accept': u'*/*', u'User-Agent': u'python-requests/2.11.1', u'Host': u'httpbin.org', u'Content-Type': u'application/x-www-form-urlencoded'}, u'json': None, u'data': u''} form: {u'key2': u'value2', u'key1': u'value1'}
#!/usr/bin/env python # -*- coding: utf-8 -*- import requests url = "http://github.com" # requests 默認自動地處理了 301/302 跳轉。在通過跳轉的請求中,返回的 URL 和狀態碼都是跳轉以後的信息;惟獨在 history 中,用 Python 列表記錄了跳轉狀況 r = requests.get("http://github.com") print "request URL:", url print "*"*60 print "默認狀況,response url:", r.url print "默認狀況,response status code:", r.status_code print "默認狀況,response history:", r.history print "*"*60 # 有時候咱們也想單步追蹤頁面跳轉狀況。此時,能夠給請求加上 allow_redirects = False 參數。 r = requests.get("http://github.com", allow_redirects=False) print "禁止自動跳轉後,response Uurl:", r.url print "禁止自動跳轉後,response status code:", r.status_code print "禁止自動跳轉後,response history:", r.history
#!/usr/bin/env python # -*- coding: utf-8 -*- import requests cs_url = 'http://httpbin.org/get' r = requests.get(cs_url) # 查看請求頭 print "定製前:\n", r.request.headers # 定製請求頭,HTTP 頭部是大小寫不敏感的,以下,User-Agent或user-agent都可 header = { # 微信UA 'User-Agent': 'Mozilla/5.0 (Linux; Android 4.1.1; MI 2 Build/JRO03L) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/37.0.0.0 Mobile MQQBrowser/6.8 TBS/036887 Safari/537.36 MicroMessenger/6.3.27.880 NetType/WIFI Language/zh_CN', # 用戶cookie 'Cookie': 'gr_user_id=2e25dc22-6d3a-4190-86ce-2f0a04f357f5;PHPSESSID=786dcb5b1233dadc80817ea0e58a5de0', 'Accept-Encoding': 'gzip', } r = requests.get(cs_url, headers=header) # 查看請求頭 print "定製後:\n", r.request.headers
輸出結果:
定製前: {'Connection': 'keep-alive', 'Accept-Encoding': 'gzip, deflate', 'Accept': '*/*', 'User-Agent': 'python-requests/2.11.1'} 定製後: {'Connection': 'keep-alive', 'Cookie': 'gr_user_id=2e25dc22-6d3a-4190-86ce-2f0a04f357f5;PHPSESSID=786dcb5b1233dadc80817ea0e58a5de0', 'Accept-Encoding': 'gzip', 'Accept': '*/*', 'User-Agent': 'Mozilla/5.0 (Linux; Android 4.1.1; MI 2 Build/JRO03L) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/37.0.0.0 Mobile MQQBrowser/6.8 TBS/036887 Safari/537.36 MicroMessenger/6.3.27.880 NetType/WIFI Language/zh_CN'}
#!/usr/bin/env python # -*- coding: utf-8 -*- import requests cs_url = 'http://httpbin.org/get' r = requests.get(cs_url) print r.headers
輸出結果:
{'Content-Length': '240', 'Server': 'nginx', 'Connection': 'keep-alive', 'Access-Control-Allow-Credentials': 'true', 'Date': 'Wed, 07 Dec 2016 06:22:51 GMT', 'Access-Control-Allow-Origin': '*', 'Content-Type': 'application/json'}
#!/usr/bin/env python # -*- coding: utf-8 -*- import requests cs_url = 'http://httpbin.org/get' r = requests.get(cs_url) if r.status_code == requests.codes.ok: print "以字節形式返回:\n", r.content print " Unicode編碼的文本信息返回:\n", r.text
#!/usr/bin/env python # -*- coding: utf-8 -*- import requests r = requests.get("http://httpbin.org/get") if r.headers.get("content-type") == "application/json": # 獲取響應內容,dict類型 print "r.json:\n", r.json() print "origin:", r.json().get("origin") else: print r.content
HTTP 協議是無狀態的。所以,若不借助其餘手段,遠程的服務器就沒法知道之前和客戶端作了哪些通訊.Cookie就是「其餘手段」之一。
Cookie 一個典型的應用場景,就是用於記錄用戶在網站上的登陸狀態。
1.用戶登陸成功後,服務器下發一個(一般是加密了的)Cookie 文件。
2.客戶端(一般是網頁瀏覽器)將收到的 Cookie 文件保存起來。
3.下次客戶端與服務器鏈接時,將 Cookie 文件發送給服務器,由服務器校驗其含義,恢復登陸狀態(從而避免再次登陸)
爲了演示該實例,提供服務端簡單接口實例代碼以下:
# 使用cookie演示登陸功能接口 def cookie(request): username = request.GET.get("user") password = request.GET.get("pwd") cookie_content = request.COOKIES login_flag = cookie_content.get("is_login") if login_flag=="True" or (username == "qa" and password == "4399"): msg = { "msg": "login success! Welcome~~", "recive_cookie": cookie_content } response = JsonResponse(msg) response.set_cookie("is_login", True) else: msg = { "msg": "username or password error,please try again!", "recive_cookie": cookie_content } response = JsonResponse(msg) response.set_cookie("is_login", False) return response
cookie示例代碼以下,cookie既可經過requests的cookies參數傳遞,也能夠在requests的headers參數傳遞。(同時存在headers和cookies參數時,headers中的cookie會覆蓋cookies參數中的cookie)
#!/usr/bin/env python # -*- coding: utf-8 -*- import requests url = "http://10.1.102.75:8000/cookie" r = requests.get(url) print "沒有發送cookie時,服務端返回內容爲:", r.content print "獲取服務端設置的cookie,cookie爲:", r.cookies print "*" * 100 cookies = { "is_login": "True" } r = requests.get(url, cookies=cookies) print "發送cookie時,服務端返回內容爲:", r.content print "獲取服務端設置的cookie,cookie爲:", r.cookies print "*" * 100 headers = { 'cookie': 'send_headers=send cookie form client headers' } r = requests.get(url, headers=headers) print "發送cookie時,服務端返回內容爲:", r.content print "獲取服務端設置的cookie,cookie爲:", r.cookies print "*" * 100
輸出結果如:
會話對象讓你可以跨請求保持某些參數。它也會在同一個 Session 實例發出的全部請求之間保持 cookie,因此若是你向同一主機發送多個請求,底層的 TCP 鏈接將會被重用,從而帶來顯著的性能提高。看本實例以前請先閱讀cookie章節
#!/usr/bin/env python # -*- coding: utf-8 -*- import requests login_url = "http://10.1.102.75:8000/cookie?user=qa&pwd=4399" access_url = "http://10.1.102.75:8000/cookie" s = requests.Session() r = s.get(login_url) print "傳入正確帳號與密碼正確登陸後,服務端返回內容爲:", r.content print "獲取服務端設置的cookie,cookie爲:", r.cookies print "*" * 100 r = s.get(access_url) print "已登陸後,不發送已登陸cookie時或登陸帳號,訪問首頁時,服務端返回內容爲:", r.content print "獲取服務端設置的cookie,cookie爲:", r.cookies print "*" * 100 cookies = { "other_cookie": "test send order cookie" } r = s.get(access_url, cookies=cookies) print "已登陸後,添加發送非登陸cookie,訪問首頁時服務端返回內容爲:", r.content print "獲取服務端設置的cookie,cookie爲:", r.cookies print "*" * 100
輸出結果以下:
爲防止服務器不能及時響應,大部分發至外部服務器的請求都應該帶着 timeout 參數。若是沒有 timeout,你的代碼可能會掛起若干分鐘甚至更長時間。
>>> r = requests.get('https://github.com', timeout=5) >>> r = requests.get('https://github.com', timeout=None) >>>
Requests 能夠爲 HTTPS 請求驗證 SSL 證書,就像 web 瀏覽器同樣。要想檢查某個主機的 SSL 證書,你可使用 verify 參數:
>>> requests.get('https://github.com', verify=True) <Response [200]>
默認狀況下, verify 是設置爲 True 的,若是SSL認證失敗,能夠嘗試將verify驗證關閉,verify=False
1 #!/usr/bin/env python 2 # -*- coding: utf-8 -*- 3 4 """ 5 微信端抽獎活動 6 多線程抽獎,測試前提:去掉一個用戶只能參與一次的限制 7 """ 8 import requests 9 from time import ctime 10 import threading 11 12 13 def draw_lottery(): 14 lottery_url = "http://10.1.102.75:8000/activity/gsdzzlottery/lottery" 15 headers = { 16 # 微信UA 17 'user-agent': 'Mozilla/5.0 (Linux; Android 4.1.1; MI 2 Build/JRO03L) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/37.0.0.0 Mobile MQQBrowser/6.8 TBS/036887 Safari/537.36 MicroMessenger/6.3.27.880 NetType/WIFI Language/zh_CN', 18 # 用戶cookie 19 'cookie': 'gr_user_id=2e25dc22-6d3a-4190-86ce-2f0a04f357f5; Hm_lvt_0d8e9cf3502496036a00d10b24863c6d=1478072857,1480158524; PHPSESSID=786dcb5b1233dadc80817ea0e58a5de0' 20 } 21 try: 22 conn = requests.get(lottery_url, headers=headers, verify=False) 23 print conn.text 24 except Exception, e: 25 print e 26 27 28 if __name__ == '__main__': 29 print 'start:', ctime() 30 for j in range(2): 31 threads = 300 32 threads_list = [] 33 for i in range(threads): 34 t = threading.Thread(target=draw_lottery, args=()) 35 threads_list.append(t) 36 for i in range(threads): 37 threads_list[i].start() 38 # keep thread 39 for i in range(threads): 40 threads_list[i].join() 41 42 print 'end:', ctime()
#!/usr/bin/env python # -*- coding: utf-8 -*- """ 使用裝飾器,併發請求 """ import requests from time import ctime import threading def thread_request(count, loop): """併發請求裝飾器,count: 線程數 ; loop: 循環次數 """ def outer(main_func): def inner(): # print "before %s" % main_func for j in range(loop): threads_list = [] for i in range(count): t = threading.Thread(target=main_func, args=()) threads_list.append(t) for th in threads_list: th.start() # keep thread for th in threads_list: th.join() # print "after %s" % main_func return inner return outer @thread_request(count=2, loop=2) def get_result(): url = "http://a.demo.4399th.com/eventapi/base/get_result" data = {"hd_id": 1} headers = { # 微信UA # 'user-agent': 'Mozilla/5.0 (Linux; Android 4.1.1; MI 2 Build/JRO03L) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/37.0.0.0 Mobile MQQBrowser/6.8 TBS/036887 Safari/537.36 MicroMessenger/6.3.27.880 NetType/WIFI Language/zh_CN', # 用戶cookie 'cookie': 'a_demo_4399th_com=60a78048563a4b58e5d27d45390be36c' } try: conn = requests.post(url, data=data, headers=headers, verify=False) print conn.text except Exception, e: print e @thread_request(count=2, loop=1) def login(): print "do login" if __name__ == '__main__': print 'start:', ctime() get_result() print 'end:', ctime()