Python+KgCaptcha实现验证码的开发详解

本攻略将详细讲解使用Python编写KgCaptcha验证码的实现方法，并提供两个示例说明。

什么是KgCaptcha

KgCaptcha是一种验证码技术，它与传统的验证码比如数字、字母、图片等不同，它采用了数据分析、人工智能、机器学习等技术，能够更好地识别人机行为，提高网站的安全性。

技术实现

第一步：安装依赖库

我们需要使用Python的requests库来发送请求，使用Pillow库处理图片，使用Numpy库进行矩阵计算。

pip install requests
pip install Pillow
pip install numpy

第二步：请求KgCaptcha API

import requests
def get_captcha():
    url = "https://captcha.su.panda.gt/verify"
    headers = {
        "accept": "application/json, text/javascript, */*; q=0.01",
        "accept-language": "zh-CN,zh;q=0.9",
        "content-type": "application/x-www-form-urlencoded; charset=UTF-8",
        "cookie": "kg_mid=5e41bddd0f56a48103df4cb7bd95502f; u=92596538; uid=92596538; sid=1420787359024089296; _qddamta_4000415090=3-0; Hm_lvt_d7682ab43891c68a00de46e9ce5b76aa=1635325487; captcha=sound//25452269/2.mp3; captcha_token=87862d910e6c424db56e80e8022c1d9b_846665308e024f5eae64ce08dfd72aef",
        "referer": "https://www.kugou.com/yy/index.php?r=play/getdata&hash=808597A4B1E3A976DDF46B180259AB79",
        "sec-ch-ua": ""Google Chrome";v="93", ""Not;A Brand";v="99", ""Chromium";v="93"",
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": ""macOS"",
        "sec-fetch-dest": "empty",
        "sec-fetch-mode": "cors",
        "sec-fetch-site": "same-origin",
        "x-requested-with": "XMLHttpRequest"
    }
    data = {
        "url": "https://captcha.su.panda.gt/captcha.jpg", # 验证码图片的地址
        "referer": "https://www.kugou.com/yy/index.php?r=play/getdata&hash=808597A4B1E3A976DDF46B180259AB79", # 参考来源
        "upstream": "kiner-proxy",
        "token": "87862d910e6c424db56e80e8022c1d9b", # 验证码token
        #"dynamic": 1
    }
    response = requests.post(url, data=data, headers=headers)
    return response.json()

captcha_json = get_captcha()
print(captcha_json) # 输出验证码json信息

第三步：获取验证码图片

from PIL import Image
import requests
import io
import numpy as np

# 请求验证码图片
def get_captcha_image(url):
    response = requests.get(url)
    image = Image.open(io.BytesIO(response.content))
    return image

# 处理图片，转换为矩阵格式
def process_image(image):
    grey_image = image.convert('L')
    binary_image = grey_image.point(lambda x: 0 if x < 128 else 255, '1')
    binary_matrix = np.array(binary_image).astype(int)
    return binary_matrix

captcha_image_url = captcha_json['captcha']
captcha_image = get_captcha_image(captcha_image_url)
captcha_matrix = process_image(captcha_image)
print(captcha_matrix) # 输出图片矩阵

第四步：识别验证码

import requests
import json
import numpy as np

# 识别验证码
def recognize_captcha(captcha_matrix):
    # 构建验证码二进制字符串，将矩阵转换为字符串
    captcha_bin_str = ''.join([''.join([str(x) for x in row]) for row in captcha_matrix])
    url = "https://captcha.su.panda.gt/recognize"
    headers = {
        "Content-Type": "application/json;charset=UTF-8",
        "Referer": "https://captcha.su.panda.gt"
    }
    data = {
        "xxc": 1,
        "ac": "default",
        "captcha": captcha_bin_str,
        "dynamic": 0,
        "gt": captcha_json['gt'],
        "token": captcha_json['token']
    }
    response = requests.post(url, data=json.dumps(data), headers=headers)
    print(response.text) # 输出验证码识别结果

recognize_captcha(captcha_matrix)

示例说明

示例一：获取验证码信息

import requests
import json

def get_captcha_info():
    url = "https://captcha.su.panda.gt/get_captcha"
    headers = {
        "Host": "captcha.su.panda.gt",
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36 Edg/93.0.961.38",
        "Accept": "application/json, text/javascript, */*; q=0.01",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Referer": "https://www.codesky.me/article/?13/",
        "X-Requested-With": "XMLHttpRequest"
    }
    response = requests.get(url, headers=headers)
    return response.json()

captcha_info = get_captcha_info()
print(captcha_info) # 输出验证码信息json

示例二：获取指定ID的验证码信息

import requests
import json

def get_captcha_info_by_id(id):
    url = f"https://captcha.su.panda.gt/get_captcha?id={id}"
    headers = {
        "Host": "captcha.su.panda.gt",
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36 Edg/93.0.961.38",
        "Accept": "application/json, text/javascript, */*; q=0.01",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Referer": "https://www.codesky.me/article/?13/",
        "X-Requested-With": "XMLHttpRequest"
    }
    response = requests.get(url, headers=headers)
    return response.json()

captcha_info = get_captcha_info_by_id(1234)
print(captcha_info) # 输出指定ID的验证码信息json

以上示例中，第一个示例获取了一个新的验证码信息，第二个示例获取了ID为1234的验证码信息。