<爬虫>验证码登录三种方式

一、手动输入

import requests
from bs4 import BeautifulSoup

'''手动输入验证码：用浏览器登录古诗文网，抓包获取登录接口和form表单；
                   将验证码图片下载，输入验证码，加入form表单；
                   获取form表单所需参数；
                   带着form表单发送登录请求
                   注：需要建立会话'''

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; Win64; x64) '
                         'AppleWebKit/537.36 (KHTML, like Gecko) '
                         'Chrome/73.0.3683.86 Safari/537.36'}

def download_code(s):
    #向登录界面发送请求
    url = 'https://so.gushiwen.org/user/login.aspx?from='
    r = s.get(url,headers=headers)

    #解析获取验证码图片链接
    soup = BeautifulSoup(r.text,'lxml')
    img_src = soup.find('img',id='imgCode')['src']
    img_url = 'https://so.gushiwen.org' + img_src
    print(img_url)

    #向图片链接发送请求，下载图片
    r_img = s.get(img_url,headers=headers)
    with open('img/code.png','wb') as fp:
        fp.write(r_img.content)

    #查找form表单所需的两个参数
    __VIEWSTATE = soup.find('input',id='__VIEWSTATE')['value']
    __VIEWSTATEGENERATOR = soup.find('input',id='__VIEWSTATEGENERATOR')['value']

    return __VIEWSTATE,__VIEWSTATEGENERATOR

def login(s,VIEW,VIEWG):
    post_url = 'https://so.gushiwen.org/user/login.aspx?from='

    code = input('输入验证码：')

    form_data = {'__VIEWSTATE':VIEW,
                '__VIEWSTATEGENERATOR': VIEWG,
                'code':code,
                'denglu':'登录',
                'email':'18404904721',
                'from':'',
                'pwd':'gjp625262'}

    r = s.post(url=post_url,headers=headers,data=form_data)

    with open('gushi.html','w',encoding='utf8') as fp:
        fp.write(r.text)

def main():
    #创建会话
    s = requests.Session()

    #下载验证码
    VIEW,VIEWG = download_code(s)

    #进行登录
    login(s,VIEW,VIEWG)


if __name__ == '__main__':
    main()

二、tesseract光学识别

from PIL import Image
import pytesseract

'''下载tesseract
    pip install pytesseract'''

#打开图片
img = Image.open(r'img/code.png')

#转化为灰度图片
img = img.convert('L')

#二值化处理
threshold = 140
table = []
for i in range(256):
    if i < threshold:
        table.append(0)
    else:
        table.append(1)
out = img.point(table,'1')
out.show()
img = img.convert('RGB')

#识别图片
print(pytesseract.image_to_string(img))

三、打码平台（云打码）

from YDMHTTPDemo3 import YDMHttp
'''打码平台：云打码
             打码兔'''

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

# 用户名
username    = 'mianxiang_mei'

# 密码
password    = 'gjp625262'

# 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       = 8212

# 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      = 'dbd2645a635701a0a9f19fd0072d82c3'

# 图片文件
filename    = 'img/code.png'

# 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))

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

附：云打码调用的类

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