6) 身份验证
基本身份认证(HTTP Basic Auth)
import requests from requests.auth import HTTPBasicAuth r = requests.get('https://httpbin.org/hidden-basic-auth/user/passwd', auth=HTTPBasicAuth('user', 'passwd')) # r = requests.get('https://httpbin.org/hidden-basic-auth/user/passwd', auth=('user', 'passwd')) # 简写 print(r.json())
另一种非常流行的HTTP身份认证形式是摘要式身份认证,Requests对它的支持也是开箱即可用的:
requests.get(URL, auth=HTTPDigestAuth('user', 'pass')
Cookies与会话对象
如果某个响应中包含一些Cookie,你可以快速访问它们:
import requests r = requests.get('http://www.google.com.hk/') print(r.cookies['NID']) print(tuple(r.cookies))
要想发送你的cookies到服务器,可以使用 cookies 参数:
import requests url = 'http://httpbin.org/cookies' cookies = {'testCookies_1': 'Hello_Python3', 'testCookies_2': 'Hello_Requests'} # 在Cookie Version 0中规定空格、方括号、圆括号、等于号、逗号、双引号、斜杠、问号、@,冒号,分号等特殊符号都不能作为Cookie的内容。 r = requests.get(url, cookies=cookies) print(r.json())
会话对象让你能够跨请求保持某些参数,最方便的是在同一个Session实例发出的所有请求之间保持cookies,且这些都是自动处理的,甚是方便。
下面就来一个真正的实例,如下是快盘签到脚本:
import requests 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) # s.auth = ('superuser', '123') s.get('https://www.kuaipan.cn/account_login.htm') _URL = 'http://www.kuaipan.cn/index.php' s.post(_URL, params={'ac':'account', 'op':'login'}, data={'username':'****@foxmail.com', 'userpwd':'********', 'isajax':'yes'}) r = s.get(_URL, params={'ac':'zone', 'op':'taskdetail'}) print(r.json()) s.get(_URL, params={'ac':'common', 'op':'usersign'})
requests模块抓取网页源码并保存到文件示例
这是一个基本的文件保存操作,但这里有几个值得注意的问题:
1.安装requests包,命令行输入pip install requests即可自动安装。很多人推荐使用requests,自带的urllib.request也可以抓取网页源码
2.open方法encoding参数设为utf-8,否则保存的文件会出现乱码。
3.如果直接在cmd中输出抓取的内容,会提示各种编码错误,所以保存到文件查看。
4.with open方法是更好的写法,可以自动操作完毕后释放资源
#! /urs/bin/python3
import requests
'''requests模块抓取网页源码并保存到文件示例'''
html = requests.get("http://www.baidu.com")
with open('test.txt', 'w', encoding='utf-8') as f:
f.write(html.text)
'''读取一个txt文件,每次读取一行,并保存到另一个txt文件中的示例'''
ff = open('testt.txt', 'w', encoding='utf-8')
with open('test.txt', encoding="utf-8") as f:
for line in f:
ff.write(line)
ff.close()
因为在命令行中打印每次读取一行的数据,中文会出现编码错误,所以每次读取一行并保存到另一个文件,这样来测试读取是否正常。(注意open的时候制定encoding编码方式)
自动登陆"示例:
#!/usr/bin/env python # -*- coding:utf-8 -*- import requests # ############## 方式一 ############## """ # ## 1、首先登陆任何页面,获取cookie i1 = requests.get(url="http://dig.chouti.com/help/service") i1_cookies = i1.cookies.get_dict() # ## 2、用户登陆,携带上一次的cookie,后台对cookie中的 gpsd 进行授权 i2 = requests.post( url="http://dig.chouti.com/login", data={ 'phone': "8615131255089", 'password': "xxooxxoo", 'oneMonth': "" }, cookies=i1_cookies ) # ## 3、点赞(只需要携带已经被授权的gpsd即可) gpsd = i1_cookies['gpsd'] i3 = requests.post( url="http://dig.chouti.com/link/vote?linksId=8589523", cookies={'gpsd': gpsd} ) print(i3.text) """ # ############## 方式二 ############## """ import requests session = requests.Session() i1 = session.get(url="http://dig.chouti.com/help/service") i2 = session.post( url="http://dig.chouti.com/login", data={ 'phone': "8615131255089", 'password': "xxooxxoo", 'oneMonth': "" } ) i3 = session.post( url="http://dig.chouti.com/link/vote?linksId=8589523" ) print(i3.text) """ #!/usr/bin/env python # -*- coding:utf-8 -*- import requests from bs4 import BeautifulSoup # ############## 方式一 ############## # # # 1. 访问登陆页面,获取 authenticity_token # i1 = requests.get('https://github.com/login') # soup1 = BeautifulSoup(i1.text, features='lxml') # tag = soup1.find(name='input', attrs={'name': 'authenticity_token'}) # authenticity_token = tag.get('value') # c1 = i1.cookies.get_dict() # i1.close() # # # 1. 携带authenticity_token和用户名密码等信息,发送用户验证 # form_data = { # "authenticity_token": authenticity_token, # "utf8": "", # "commit": "Sign in", # "login": "wupeiqi@live.com", # 'password': 'xxoo' # } # # i2 = requests.post('https://github.com/session', data=form_data, cookies=c1) # c2 = i2.cookies.get_dict() # c1.update(c2) # i3 = requests.get('https://github.com/settings/repositories', cookies=c1) # # soup3 = BeautifulSoup(i3.text, features='lxml') # list_group = soup3.find(name='div', class_='listgroup') # # from bs4.element import Tag # # for child in list_group.children: # if isinstance(child, Tag): # project_tag = child.find(name='a', class_='mr-1') # size_tag = child.find(name='small') # temp = "项目:%s(%s); 项目路径:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, ) # print(temp) # ############## 方式二 ############## # session = requests.Session() # # 1. 访问登陆页面,获取 authenticity_token # i1 = session.get('https://github.com/login') # soup1 = BeautifulSoup(i1.text, features='lxml') # tag = soup1.find(name='input', attrs={'name': 'authenticity_token'}) # authenticity_token = tag.get('value') # c1 = i1.cookies.get_dict() # i1.close() # # # 1. 携带authenticity_token和用户名密码等信息,发送用户验证 # form_data = { # "authenticity_token": authenticity_token, # "utf8": "", # "commit": "Sign in", # "login": "wupeiqi@live.com", # 'password': 'xxoo' # } # # i2 = session.post('https://github.com/session', data=form_data) # c2 = i2.cookies.get_dict() # c1.update(c2) # i3 = session.get('https://github.com/settings/repositories') # # soup3 = BeautifulSoup(i3.text, features='lxml') # list_group = soup3.find(name='div', class_='listgroup') # # from bs4.element import Tag # # for child in list_group.children: # if isinstance(child, Tag): # project_tag = child.find(name='a', class_='mr-1') # size_tag = child.find(name='small') # temp = "项目:%s(%s); 项目路径:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, ) # print(temp) #!/usr/bin/env python # -*- coding:utf-8 -*- import time import requests from bs4 import BeautifulSoup session = requests.Session() i1 = session.get( url='https://www.zhihu.com/#signin', headers={ 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36', } ) soup1 = BeautifulSoup(i1.text, 'lxml') xsrf_tag = soup1.find(name='input', attrs={'name': '_xsrf'}) xsrf = xsrf_tag.get('value') current_time = time.time() i2 = session.get( url='https://www.zhihu.com/captcha.gif', params={'r': current_time, 'type': 'login'}, headers={ 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36', }) with open('zhihu.gif', 'wb') as f: f.write(i2.content) captcha = input('请打开zhihu.gif文件,查看并输入验证码:') form_data = { "_xsrf": xsrf, 'password': 'xxooxxoo', "captcha": 'captcha', 'email': '424662508@qq.com' } i3 = session.post( url='https://www.zhihu.com/login/email', data=form_data, headers={ 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36', } ) i4 = session.get( url='https://www.zhihu.com/settings/profile', headers={ 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36', } ) soup4 = BeautifulSoup(i4.text, 'lxml') tag = soup4.find(id='rename-section') nick_name = tag.find('span',class_='name').string print(nick_name) #!/usr/bin/env python # -*- coding:utf-8 -*- import re import json import base64 import rsa import requests def js_encrypt(text): b64der = 'MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQCp0wHYbg/NOPO3nzMD3dndwS0MccuMeXCHgVlGOoYyFwLdS24Im2e7YyhB0wrUsyYf0/nhzCzBK8ZC9eCWqd0aHbdgOQT6CuFQBMjbyGYvlVYU2ZP7kG9Ft6YV6oc9ambuO7nPZh+bvXH0zDKfi02prknrScAKC0XhadTHT3Al0QIDAQAB' der = base64.standard_b64decode(b64der) pk = rsa.PublicKey.load_pkcs1_openssl_der(der) v1 = rsa.encrypt(bytes(text, 'utf8'), pk) value = base64.encodebytes(v1).replace(b'\n', b'') value = value.decode('utf8') return value session = requests.Session() i1 = session.get('https://passport.cnblogs.com/user/signin') rep = re.compile("'VerificationToken': '(.*)'") v = re.search(rep, i1.text) verification_token = v.group(1) form_data = { 'input1': js_encrypt('wptawy'), 'input2': js_encrypt('asdfasdf'), 'remember': False } i2 = session.post(url='https://passport.cnblogs.com/user/signin', data=json.dumps(form_data), headers={ 'Content-Type': 'application/json; charset=UTF-8', 'X-Requested-With': 'XMLHttpRequest', 'VerificationToken': verification_token} ) i3 = session.get(url='https://i.cnblogs.com/EditDiary.aspx') print(i3.text) #!/usr/bin/env python # -*- coding:utf-8 -*- import requests # 第一步:访问登陆页,拿到X_Anti_Forge_Token,X_Anti_Forge_Code # 1、请求url:https://passport.lagou.com/login/login.html # 2、请求方法:GET # 3、请求头: # User-agent r1 = requests.get('https://passport.lagou.com/login/login.html', headers={ 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36', }, ) X_Anti_Forge_Token = re.findall("X_Anti_Forge_Token = '(.*?)'", r1.text, re.S)[0] X_Anti_Forge_Code = re.findall("X_Anti_Forge_Code = '(.*?)'", r1.text, re.S)[0] print(X_Anti_Forge_Token, X_Anti_Forge_Code) # print(r1.cookies.get_dict()) # 第二步:登陆 # 1、请求url:https://passport.lagou.com/login/login.json # 2、请求方法:POST # 3、请求头: # cookie # User-agent # Referer:https://passport.lagou.com/login/login.html # X-Anit-Forge-Code:53165984 # X-Anit-Forge-Token:3b6a2f62-80f0-428b-8efb-ef72fc100d78 # X-Requested-With:XMLHttpRequest # 4、请求体: # isValidate:true # username:15131252215 # password:ab18d270d7126ea65915c50288c22c0d # request_form_verifyCode:'' # submit:'' r2 = requests.post( 'https://passport.lagou.com/login/login.json', headers={ 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36', 'Referer': 'https://passport.lagou.com/login/login.html', 'X-Anit-Forge-Code': X_Anti_Forge_Code, 'X-Anit-Forge-Token': X_Anti_Forge_Token, 'X-Requested-With': 'XMLHttpRequest' }, data={ "isValidate": True, 'username': '15131255089', 'password': 'ab18d270d7126ea65915c50288c22c0d', 'request_form_verifyCode': '', 'submit': '' }, cookies=r1.cookies.get_dict() ) print(r2.text)