requests模拟登陆 &验证码

194 阅读4分钟

文章目录

1.requests的高级应用 ~ 会话维持

# 利用Session对象发送get请求:
    from requests import Session
    session = Session()
    res = session.get(url=url, headers=headers)
    
# 利用Session对象发送post请求:
	from requests import Session
    session = Session()
    data = {
    	"username": "Jeremy",
        "pwd": "123456"
    }
    res = session.get(url=url, data=data, headers=headers)

模拟登陆快代理


from requests import Session
# 1.实例化session对象
session = Session()
url = "https://www.kuaidaili.com/login/"
data = {
	...
}
# 2.发送post请求
res_login = session.post(...)
# 3.访问跟人中心页面
res_index = session.get(...)
# 4.写入文件看效果
with open('index.html', 'w', encoding="utf-8") as f:
    f.write(res_index.text)

2.打码平台

#使用流程:

  • 注册账号:
    普通账户: 充钱的
    开发账户: 调接口进行打码
  • 登陆普通用户: 查询剩余积分, 在线充值
  • 开发者登陆:
    我的软件–>创建新软件: 名字随便, 秘钥不要改—>软件代码 + 通讯秘钥
    开发文档:PythonHTTP操作示例

3.云打码平台接口使用

# 获取验证码:
import http.client, mimetypes, urllib, json, time, requests

######################################################################

class YDMHttp:

    apiurl = 'http://api.yundama.com/api.php'
    username = ''
    password = ''
    appid = ''
    appkey = ''

    def __init__(self, username, password, appid, appkey):
        self.username = username  
        self.password = password
        self.appid = str(appid)
        self.appkey = appkey

    def request(self, fields, files=[]):
        response = self.post_url(self.apiurl, fields, files)
        response = json.loads(response)
        return response
    
    def balance(self):
        data = {'method': 'balance', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey}
        response = self.request(data)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['balance']
        else:
            return -9001
    
    def login(self):
        data = {'method': 'login', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey}
        response = self.request(data)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['uid']
        else:
            return -9001

    def upload(self, filename, codetype, timeout):
        data = {'method': 'upload', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey, 'codetype': str(codetype), 'timeout': str(timeout)}
        file = {'file': filename}
        response = self.request(data, file)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['cid']
        else:
            return -9001

    def result(self, cid):
        data = {'method': 'result', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey, 'cid': str(cid)}
        response = self.request(data)
        return response and response['text'] or ''

    def decode(self, filename, codetype, timeout):
        cid = self.upload(filename, codetype, timeout)
        if (cid > 0):
            for i in range(0, timeout):
                result = self.result(cid)
                if (result != ''):
                    return cid, result
                else:
                    time.sleep(1)
            return -3003, ''
        else:
            return cid, ''

    def report(self, cid):
        data = {'method': 'report', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey, 'cid': str(cid), 'flag': '0'}
        response = self.request(data)
        if (response):
            return response['ret']
        else:
            return -9001

    def post_url(self, url, fields, files=[]):
        for key in files:
            files[key] = open(files[key], 'rb');
        res = requests.post(url, files=files, data=fields)
        return res.text

#################只有一下部分需要作出修改, 上面的类不需要该#########################

# 用户名
username    = '用户名'

# 密码
password    = '密码'                            

# 软件ID,开发者分成必要参数。登录开发者后台【我的软件】获得!
appid       = 软件id  # 创建软件时生成的                                    

# 软件密钥,开发者分成必要参数。登录开发者后台【我的软件】获得!
appkey      = '软件秘钥'   # 创建软件时生成的

# 图片文件
filename    = '验证码图片的路径'                        

# 验证码类型,# 例:1004表示4位字母数字,不同类型收费不同。请准确填写,否则影响识别率。在此查询所有类型 http://www.yundama.com/price.html
codetype    = 验证码类型

# 超时时间,秒
timeout     = 60                                    

# 检查
if (username == 'username'):
    print('请设置好相关参数再测试')
else:
    # 初始化
    yundama = YDMHttp(username, password, appid, appkey)

    # 登陆云打码
    uid = yundama.login();
    print('uid: %s' % uid)

    # 查询余额
    balance = yundama.balance();
    print('balance: %s' % balance)

    # 开始识别,图片路径,验证码类型ID,超时时间(秒),识别结果
    cid, result = yundama.decode(filename, codetype, timeout);
    # 注意:(result就是识别的结果)

4.隐藏参数与模拟登陆

# 古诗文网模拟登陆
import requests
from requests import Session
from bs4 import BeautifulSoup

session = Session()
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'
}
# 1.我们为了获取隐藏的参数, get一次登录界面, 从登录界面中提取出隐藏的参数, 下载验证码的图片
url_get = 'https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx'
res = session.get(url=url_get, headers=headers)
soup = BeautifulSoup(res.text, 'lxml')
# 获取隐藏参数

# 下载验证码图片

# 2.云打码平台打码
import http.client, mimetypes, urllib, json, time, requests
######################################################################
# 调用接口
class YDMHttp:
	pass
########################### 需要用户自己编写 ##########################
# 用户名
# 普通用户的用户名和密码
username = '...'
# 密码
password = '...'
# 软件ID,开发者分成必要参数。登录开发者后台【我的软件】获得!
appid = 8796
# 软件密钥,开发者分成必要参数。登录开发者后台【我的软件】获得!
appkey = 'bc5770c166e86900c6e9b04efc159229'
# 图片文件
filename = 'code.jpg'
# 验证码类型,# 例:1004表示4位字母数字,不同类型收费不同。请准确填写,否则影响识别率。在此查询所有类型 http://www.yundama.com/price.html
codetype = 1004
# 超时时间,秒
timeout = 60
# 检查
if (username == 'username'):
    print('请设置好相关参数再测试')
else:
    # 初始化
    yundama = YDMHttp(username, password, appid, appkey)

    # 登陆云打码
    uid = yundama.login();
    print('uid: %s' % uid)

    # 查询余额
    balance = yundama.balance();
    print('balance: %s' % balance)

    # 开始识别,图片路径,验证码类型ID,超时时间(秒),识别结果
    cid, result = yundama.decode(filename, codetype, timeout);
    print('cid: %s, result: %s' % (cid, result))

######################################################################

# 确定post请求的url, 构建登录需要的数据
url_post = '...'
data = {
   ...
}
res = session.post(url=url_post, headers=headers, data=data)
with open('login.html', 'w', encoding='utf-8') as f:
    f.write(res.text)