requests模拟登陆 + 验证码

requests模拟登陆 + 验证码

昨日回顾:

多线程爬虫:

​ 爬虫线程: 爬取数据

​ 解析线程: 解析数据 + 入库

​ 第三方容器: 队列 --> Queue

​ 主函数:

​ 程序入口:

from requests import Session

session = Session()

# 1.get请求
res = session.get(url=url, headers=headers)

# 2.post请求
data = {
    'key':'value'
}
res = session.post(url=url, headers=headers, data=data)
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
session = Session()
url = "https://www.kuaidaili.com/login/"
data = {
'next': "",
'kf5_return_to': 
'username': '3338003899@qq.com'
'passwd': 'qq123456'
}
res_login = session.post(url=url, data=data, headers=headers)
res_index = session.get("https://www.kuaidaili.com/usercenter/", headers=headers)
with open('index.html', 'w', encoding="utf-8") as f:
    f.write(res_index.text)
# 第三方打码平台打码原理: 

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-8w2QIlU1-1574649955340)(C:\Users\Administrator\AppData\Roaming\Typora\typora-user-images\1564710233699.png)]


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

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-urpAVNly-1574649955341)(C:\Users\Administrator\AppData\Roaming\Typora\typora-user-images\1564711983672.png)]


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    = 'jeremy0820'

# 密码
password    = '0820_ab'                            

# 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       = 7608                                    

# 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      = '106f27ed6a4ef2c97652c68a76a505f9'    

# 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);

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

4.动态传参与模拟登陆
# 古诗文网模拟登陆
import requests
from lxml import etree

# 获取隐藏参数
session =  requests.Session()
url = "https://so.gushiwen.org/user/login.aspx"

headers = {"headers":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36"}
response = session.get(url=url, headers=headers).text
etree_obj = etree.HTML(response)
__VIEWSTATE = etree_obj.xpath("//input[@id='__VIEWSTATE']/@value")
__VIEWSTATEGENERATOR = etree_obj.xpath("//input[@id='__VIEWSTATEGENERATOR']/@value")
print(__VIEWSTATE)
print(__VIEWSTATEGENERATOR)

# 获取验证码图片:
url_image = 'https://so.gushiwen.org/RandCode.ashx'
content = session.get(url=url_image, headers=headers).content
with open("./code.jpg", "wb") as f:
    f.write(content)


# 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

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

# 用户名
username    = 'jeremy0820'

# 密码
password    = '0820_ab'                            

# 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       = 7608                                    

# 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      = '106f27ed6a4ef2c97652c68a76a505f9'    

# 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("验证码识别结果:", result)
data = {
    "__VIEWSTATE": __VIEWSTATE,
    "__VIEWSTATEGENERATOR": __VIEWSTATEGENERATOR,
    "from": "",
    "email": "yujeremy0820@gmail.com",
    "pwd": "0820@ab",
    "code": result,
    "denglu": "登录",
}
login =session.post(url=url, headers=headers, data=data)
index_url = 'https://so.gushiwen.org/user/collect.aspx'
index_content = session.get(url=index_url, headers=headers).text
with open('./shi.html', "w", encoding="utf-8") as f:
    print("开始写文件")
    f.write(index_content)

“from”: “”,
“email”: “yujeremy0820@gmail.com”,
“pwd”: “0820@ab”,
“code”: result,
“denglu”: “登录”,
}
login =session.post(url=url, headers=headers, data=data)
index_url = ‘https://so.gushiwen.org/user/collect.aspx’
index_content = session.get(url=index_url, headers=headers).text
with open(’./shi.html’, “w”, encoding=“utf-8”) as f:
print(“开始写文件”)
f.write(index_content)


  • 1
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

仙女肖消乐

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值