实现简单的模拟登录网站

本次登录站点为古诗文网

URL：https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx

对于验证码的解析：采用云打码API接口实现 http://www.yundama.com

主页面实现代码：

import requests
requests.packages.urllib3.disable_warnings()        #禁用证书安装警告
from lxml import etree
from verify import getCodeDate

#获取网站的登录页面链接
url=‘https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx‘

S=requests.Session()
user_agent={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36"}

page_text=requests.get(url=url,headers=user_agent,verify=False).text    #登录页面文本内容
tree=etree.HTML(page_text)
i_url=tree.xpath(‘//img[@id="imgCode"]/@src‘)[0]            #解析出验证码的url
code_img_url="https://so.gushiwen.org"+i_url                #拼接完整验证码完整的URI

#通过session去访问验证码url请求  为避免HTTPS中的ssl验证关闭验证
img_data=S.get(url=code_img_url,headers=user_agent,verify=False).content

with open(‘./code/code.jpg‘,‘wb‘)as f:
    f.write(img_data)               #验证码本地持久化存储
f.close()

#调用云打码API去解析验证码文本内容
code_text=getCodeDate(‘bobo328410948‘,‘bobo328410948‘,‘./code/code.jpg‘,1004)
print(code_text)

login_url=‘https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx‘
data={
    "__VIEWSTATE":"pnxXA5gIeJn+zyAzqHvjCGecHVkhFmDqa2YvRtvdp/9Yexq5Mngv8LjGEY4AmtwlXa36vUe0p4FxAvwDWIwYSiwv4g/7+oomRXa4hlKrhenT/ydAGJAQBzbXVbQ=",
    "__VIEWSTATEGENERATOR":"C93BE1AE",
    "from":"http://so.gushiwen.org/user/collect.aspx",
    "email":"123456@163.com",
    "pwd":"1159402553",
    "code":code_text,
    "denglu":"登录",
}
user_page=S.post(url=login_url,data=data,headers=user_agent).text
print(user_page)
with open(‘./gushi.html‘,‘w‘,encoding=‘utf-8‘)as f:
    f.write(user_page)

云打码的API接口代码：

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

对云打码API接口封装的函数代码：

from ydm import YDMHttp

def getCodeDate(userName,pwd,codePath,codeType):
    # 用户名(普通用户)
    username    = userName

    # 密码
    password    = pwd

    # 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       = 6003

    # 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      = ‘1f4b564483ae5c907a1d34f8e2f2776c‘

    # 图片文件
    filename    = codePath

    # 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    = codeType

    # 超时时间，秒
    timeout     = 20
    result = None
    # 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))
    return result

原文地址：https://www.cnblogs.com/wen-kang/p/10952674.html