数美验证码-空间推测-爬虫

前言

因为要训练识别验证码的模型，需要爬取源数据。
如果需要其他的类型，自行修改

爬取结果

这边把图片跟文本命名一样的。

代码

import time
import json
import requests


def save_image_from_url(url, file_path):
    response = requests.get(url)
    with open(file_path, 'wb') as f:
        f.write(response.content)


if __name__ == '__main__':
    """
    @author: xXinG
    @dec:    爬取数美验证码空间 逻辑推理图片、文本
    @time: 2023/4/26 19:50
    """

    execute_count = 100  # 爬取条数

    start_time = time.time()
    for i in range(execute_count):
        url = "https://captcha1.fengkongcloud.cn/ca/v1/register"

        querys = {"callback": "0", "channel": "DEFAULT",
                  "captchaUuid": "20240426194937QdanEmbtwJrRaJwbdG", "rversion": "1.0.4", "lang": "zh-cn",
                  "data": "{}", "model": "spatial_select", "sdkver": "1.1.3", "organization": "d6tpAY1oV0Kv5jRSgxQr",
                  "appId": "default"}

        response = requests.request("GET", url, params=querys)
        data_str = response.text[2:-1]  # 去掉字符串开头的'0('和结尾的')'
        data_dict = json.loads(data_str)  # 将字符串转换为字典

        if data_dict['code'] == 1100:
            url = data_dict['detail']['bg']  # 图片url, 需要加上  https://castatic.fengkongcloud.cn/
            des = data_dict['detail']['order']  # 空间目标描述

            last_slash_index = url.rfind('/')
            jpg_start_index = url.find('.jpg')
            name = url[last_slash_index + 1:jpg_start_index]  # 图片命名

            save_image_from_url('https://castatic.fengkongcloud.cn' + data_dict['detail']['bg'],
                                './result/img/' + name + '.jpg')

            with open("./result/label/" + name + '.txt', "w", encoding="utf-8") as f:
                f.write(des[0])
            print("完成 -> " + name)

    end_time = time.time()
    print("总共用时: " + str(end_time - start_time) + "秒")

这边测试爬取100张

给大家看看训练好的模型 哈哈