爬虫入门--验证码识别

第三方使用 超级鹰

使用步骤

• 1.注册账号
• 2.关注微信公众号并绑定账号，赠送1000题分
• 3.参考示例代码
• 4.引入demo

简单案例

实例代码

import requests
from lxml import etree
from chaojiying import Chaojiying_Client

if __name__ == '__main__':
    url = 'https://so.gushiwen.cn/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'
    }

    page_text = requests.get(url=url, headers=headers).text
    tree = etree.HTML(page_text)
    code_url = 'https://so.gushiwen.cn/' + tree.xpath('//*[@id="imgCode"]/@src')[0]
    print(code_url)
    code_img = requests.get(url=code_url, headers=headers).content
    with open('./code.jpg', 'wb') as fp:
        fp.write(code_img)

    chaojiying = Chaojiying_Client('账号', '密码', '软件ID')  # 用户中心>>软件ID 生成一个替换 96001
    im = open('code.jpg', 'rb').read()  # 本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
    print(chaojiying.PostPic(im, 1902))  # 1902 验证码类型  官方网站>>价格体系 3.4+版 print 后要加()
    # print chaojiying.PostPic(base64_str, 1902)  #此处为传入 base64代码
    # {'err_no': 0, 'err_str': 'OK', 'pic_id': '2208010261088120004', 'pic_str': 's26w','md5': '343d4304f28b4bdd4ef3dbf6c8de142c'}

贴出官方API解析类做参考，基本不用动，调用时候修改账号,密码,软件ID,验证码类型即可

import requests
from hashlib import md5


class Chaojiying_Client(object):

    def __init__(self, username, password, soft_id):
        self.username = username
        password = password.encode('utf8')
        self.password = md5(password).hexdigest()
        self.soft_id = soft_id
        self.base_params = {
            'user': self.username,
            'pass2': self.password,
            'softid': self.soft_id,
        }
        self.headers = {
            'Connection': 'Keep-Alive',
            'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
        }

    def PostPic(self, im, codetype):
        """
        im: 图片字节
        codetype: 题目类型 参考 http://www.chaojiying.com/price.html
        """
        params = {
            'codetype': codetype,
        }
        params.update(self.base_params)
        files = {'userfile': ('ccc.jpg', im)}
        r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files,
                          headers=self.headers)
        return r.json()

    def PostPic_base64(self, base64_str, codetype):
        """
        im: 图片字节
        codetype: 题目类型 参考 http://www.chaojiying.com/price.html
        """
        params = {
            'codetype': codetype,
            'file_base64': base64_str
        }
        params.update(self.base_params)
        r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, headers=self.headers)
        return r.json()

    def ReportError(self, im_id):
        """
        im_id:报错题目的图片ID
        """
        params = {
            'id': im_id,
        }
        params.update(self.base_params)
        r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)
        return r.json()