├── .gitignore ├── LICENSE ├── README.md ├── img ├── 226md.png └── image.png ├── requirements.txt ├── research.md └── src ├── gpt4_ocr_demo.py └── local_ocr_demo.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/latest/usage/project/#working-with-version-control 110 | .pdm.toml 111 | .pdm-python 112 | .pdm-build/ 113 | 114 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 115 | __pypackages__/ 116 | 117 | # Celery stuff 118 | celerybeat-schedule 119 | celerybeat.pid 120 | 121 | # SageMath parsed files 122 | *.sage.py 123 | 124 | # Environments 125 | .env 126 | .venv 127 | env/ 128 | venv/ 129 | ENV/ 130 | env.bak/ 131 | venv.bak/ 132 | 133 | # Spyder project settings 134 | .spyderproject 135 | .spyproject 136 | 137 | # Rope project settings 138 | .ropeproject 139 | 140 | # mkdocs documentation 141 | /site 142 | 143 | # mypy 144 | .mypy_cache/ 145 | .dmypy.json 146 | dmypy.json 147 | 148 | # Pyre type checker 149 | .pyre/ 150 | 151 | # pytype static type analyzer 152 | .pytype/ 153 | 154 | # Cython debug symbols 155 | cython_debug/ 156 | 157 | # PyCharm 158 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 159 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 160 | # and can be added to the global gitignore or merged into this file. For a more nuclear 161 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 162 | #.idea/ 163 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # openai-captcha-detection 2 | 3 | ## 项目简介 4 | 5 | openai-captcha-detection 是一个使用 OpenAI 进行验证码识别的工具。目前验证码识别准确率100%，通过调用 OpenAI 的 API，这个项目可以实现对复杂验证码图片的文本识别，帮助开发者在验证码处理场景中进行自动化操作。 6 | 7 | ## 功能特点 8 | - 利用 OpenAI 的 GPT-4 模型进行 OCR（光学字符识别），可以识别各种类型的验证码。 9 | - 提供简单易用的 API 接口，方便在其他项目中集成使用。 10 | 11 | ## 环境准备 12 | 13 | 在使用此项目前，请确保已经安装好以下工具： 14 | - Python 3.7 及以上版本 15 | - pip 包管理工具 16 | 17 | ## 安装与使用 18 | 19 | ### 克隆项目并运行验证 20 | 1. 克隆仓库并进入项目目录： 21 | ```sh 22 | git clone --depth 1 https://github.com/zgimszhd61/openai-capcha-detection 23 | cd openai-capcha-detection 24 | ``` 25 | 26 | 2. 设置 OpenAI API 密钥： 27 | ```sh 28 | export OPENAI_API_KEY=[你的API_KEY] 29 | ``` 30 | 31 | 3. 安装所需依赖包： 32 | ```sh 33 | pip install -r requirements.txt 34 | ``` 35 | 36 | 4. 运行验证码识别脚本： 37 | ```sh 38 | python3 src/gpt4_ocr_demo.py 39 | ``` 40 | 41 | ### 在其他项目中集成使用 42 | 你可以在自己的项目中集成 `openai-captcha-detection` 来实现验证码识别。以下是一个使用示例： 43 | 44 | ```python 45 | from gpt4_ocr_demo import OCRClient 46 | 47 | def recognize_captcha(image_path): 48 | # 创建 OCRClient 实例 49 | ocr_client = OCRClient() 50 | 51 | # 将图片编码为 base64 格式 52 | encoded_image = ocr_client.encode_image_to_base64(image_path) 53 | 54 | # 调用 GPT-4 OCR 函数进行识别 55 | captcha_text = ocr_client.invoke_gpt4_ocr(encoded_image) 56 | 57 | return captcha_text 58 | 59 | if __name__ == "__main__": 60 | image_path = "226md.png" 61 | recognized_text = recognize_captcha(image_path) 62 | print("识别出的验证码是：", recognized_text) 63 | ``` 64 | 65 | ## 项目结构 66 | - `src/gpt4_ocr_demo.py`：封装了与 OpenAI API 交互的客户端类，包括图像编码与验证码识别的主要功能。演示如何使用 GPT-4 模型进行验证码识别的脚本。 67 | - 68 | ## 注意事项 69 | - 请确保您在使用 OpenAI API 时具有有效的 API Key，并注意使用频率以免超出额度。 70 | - 识别效果取决于验证码的复杂程度以及 GPT-4 模型的能力，某些复杂验证码可能会存在识别错误的情况。 71 | 72 | ## 未来规划 73 | - 提升对复杂验证码类型的识别精度。 74 | - 增加更多的 API 支持，以更好地适应多样化的验证码类型。 75 | - 提供更便捷的命令行界面以供用户直接使用。 76 | 77 | ## 许可证 78 | 此项目遵循 MIT 许可证，详细内容请查看 [LICENSE](LICENSE) 文件。 79 | -------------------------------------------------------------------------------- /img/226md.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/XiaomingX/openai-captcha-detection/dda9a1bdf3d43e226b44d5b9a3bcecc523bc9777/img/226md.png -------------------------------------------------------------------------------- /img/image.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/XiaomingX/openai-captcha-detection/dda9a1bdf3d43e226b44d5b9a3bcecc523bc9777/img/image.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | pytesseract 2 | pillow 3 | opencv-python 4 | openai 5 | python-dotenv 6 | httpx[socks] -------------------------------------------------------------------------------- /research.md: -------------------------------------------------------------------------------- 1 | # 最新的验证码识别技术 2 | 3 | ### AI驱动的识别技术 4 | 5 | **YOLO模型突破** 6 | - 研究人员改进了YOLO图像处理模型，使其能够100%识别Google reCAPTCHAv2验证码，这比之前的68-71%成功率有了很大提升。 7 | 8 | **深度学习方法** 9 | - 使用卷积神经网络（CNN），验证码识别准确率超过96%。 10 | - LSTM RNN（长短期记忆网络）在处理扭曲文本方面也非常有效。 11 | 12 | ### 混合识别系统 13 | 14 | **AI与人工结合** 15 | - 将光学字符识别（OCR）技术与人工标注结合，提升识别效果。 16 | - 使用机器学习模型不断学习，并通过众包标注来改进模型。 17 | 18 | ### 新一代验证码 19 | 20 | **认知深度学习验证码** 21 | - 结合文本、图像和认知特征的多重验证，增加验证码多样性。 22 | - 使用对抗样本和神经风格迁移技术，增加机器识别的难度。 23 | 24 | ### 商业化解决方案 25 | 26 | **主流破解服务** 27 | - **Capsolver**：利用先进的AI技术进行验证码破解。 28 | - **CapMonster Cloud**：声称拥有99%的识别率。 29 | - **Anti Captcha**：提供完全由人工完成的验证服务。 30 | 31 | 这些新技术的迅速发展意味着传统验证码可能需要重新设计，以保证网络安全。 -------------------------------------------------------------------------------- /src/gpt4_ocr_demo.py: -------------------------------------------------------------------------------- 1 | import base64 2 | from openai import OpenAI 3 | from dotenv import load_dotenv 4 | import os 5 | import logging 6 | import time 7 | from PIL import Image 8 | import io 9 | 10 | class OCRClient: 11 | def __init__(self, model="gpt-4o-mini"): 12 | self._load_environment() 13 | self.client = self._initialize_openai_client() 14 | self.model = model 15 | self.max_retries = 3 # Set maximum retries for API calls 16 | self.retry_delay = 2 # Delay between retries in seconds 17 | 18 | def _load_environment(self): 19 | """Load environment variables and check API key.""" 20 | load_dotenv() 21 | self.api_key = os.getenv("OPENAI_API_KEY") 22 | if not self.api_key: 23 | raise ValueError("API key not found. Please set OPENAI_API_KEY in the environment variables.") 24 | 25 | def _initialize_openai_client(self): 26 | """Initialize and return an OpenAI client.""" 27 | return OpenAI(api_key=self.api_key) 28 | 29 | def resize_image(self, image_path, max_size=(300, 100)): 30 | """Resize image to reduce size for faster processing.""" 31 | with Image.open(image_path) as img: 32 | img.thumbnail(max_size) 33 | buffered = io.BytesIO() 34 | img.save(buffered, format="PNG") 35 | return buffered.getvalue() 36 | 37 | def encode_image_to_base64(self, image_data): 38 | """Encode image data to base64 string.""" 39 | return base64.b64encode(image_data).decode('utf-8') 40 | 41 | def invoke_gpt4o_ocr(self, encoded_image): 42 | """Invoke GPT-4o-mini to perform OCR with retries for robustness.""" 43 | for attempt in range(self.max_retries): 44 | try: 45 | completion = self.client.chat.completions.create( 46 | model=self.model, 47 | messages=[ 48 | { 49 | "role": "user", 50 | "content": [ 51 | {"type": "text", "text": "请对这张图片进行OCR识别，并输出最准确的验证码，以项目列表格式直接输出识别出的结果，不要输出其他内容。"}, 52 | {"type": "image_url", "image_url": {"url": "data:image/png;base64," + encoded_image}} 53 | ] 54 | } 55 | ], 56 | max_tokens=300, 57 | ) 58 | result = completion.choices[0].message.content.replace("-", "").strip() 59 | return result 60 | except Exception as e: 61 | logging.warning(f"Attempt {attempt + 1} failed with error: {e}") 62 | if attempt < self.max_retries - 1: 63 | time.sleep(self.retry_delay) 64 | else: 65 | logging.error("Max retries reached. OCR process failed.") 66 | return None 67 | 68 | def main(): 69 | # Setup logging 70 | logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s") 71 | 72 | try: 73 | # Create an OCR client instance 74 | ocr_client = OCRClient() 75 | 76 | # Set image path and load image 77 | image_path = 'img/226md.png' 78 | 79 | # Resize and encode the image to base64 80 | resized_image_data = ocr_client.resize_image(image_path) 81 | encoded_image = ocr_client.encode_image_to_base64(resized_image_data) 82 | 83 | # Invoke OCR function 84 | captcha_text = ocr_client.invoke_gpt4o_ocr(encoded_image) 85 | 86 | # Output the recognized text 87 | if captcha_text: 88 | print("识别出的验证码是：", captcha_text) 89 | else: 90 | print("验证码识别失败，请稍后重试。") 91 | except Exception as e: 92 | logging.error(f"An error occurred: {e}") 93 | 94 | if __name__ == "__main__": 95 | main() 96 | -------------------------------------------------------------------------------- /src/local_ocr_demo.py: -------------------------------------------------------------------------------- 1 | import asyncio 2 | from typing import Tuple, Optional 3 | import pytesseract 4 | from PIL import Image, ImageFilter, ImageOps 5 | 6 | class ThreeAntiCaptchaImageSolver: 7 | def __init__(self, tesseract_cmd: str = "tesseract", psm: int = 8): 8 | # 设置 Tesseract OCR 可执行文件的路径 9 | pytesseract.pytesseract.tesseract_cmd = tesseract_cmd 10 | self.psm = psm # OCR 识别模式 11 | 12 | def preprocess_image(self, image_path: str) -> Image.Image: 13 | """ 14 | 对图像进行预处理：灰度化、二值化、锐化等 15 | """ 16 | image = Image.open(image_path) 17 | image = ImageOps.grayscale(image) # 转为灰度图像 18 | image = image.filter(ImageFilter.MedianFilter()) # 去噪 19 | image = ImageOps.autocontrast(image) # 自动对比度调整 20 | threshold = 128 # 二值化阈值 21 | image = image.point(lambda p: p > threshold and 255) # 二值化 22 | return image 23 | 24 | async def solve(self, image_path: str, custom_config: Optional[str] = None) -> Tuple[str, bool]: 25 | """ 26 | 使用 OCR 识别验证码文本 27 | """ 28 | try: 29 | # 预处理图像 30 | image = self.preprocess_image(image_path) 31 | 32 | # 使用 pytesseract 识别验证码文本 33 | config = custom_config if custom_config else f"--psm {self.psm}" 34 | captcha_text = pytesseract.image_to_string(image, config=config) 35 | 36 | # 去除空白符并检查长度是否符合预期 37 | captcha_text = captcha_text.strip() 38 | if captcha_text: 39 | return captcha_text, True 40 | else: 41 | return "Recognition failed - No text detected", False 42 | 43 | except Exception as err: 44 | return f"An unexpected error occurred: {err}", False 45 | 46 | async def report_bad(self, reason: str = "Low accuracy") -> Tuple[str, bool]: 47 | """ 48 | 模拟报告错误验证码，记录日志 49 | """ 50 | # 可以将错误原因记录在日志中，方便后续分析 51 | with open("error_log.txt", "a") as log_file: 52 | log_file.write(f"Bad captcha reported: {reason}\n") 53 | return "Logged error report", True 54 | 55 | 56 | async def main(): 57 | image_path = "img/226md.png" 58 | solver = ThreeAntiCaptchaImageSolver(psm=8) 59 | result, success = await solver.solve(image_path) 60 | print(f"Result: {result}, Success: {success}") 61 | 62 | # 示例：在验证码识别错误的情况下报告 63 | if not success: 64 | await solver.report_bad("Recognition did not meet expected accuracy") 65 | 66 | 67 | if __name__ == "__main__": 68 | asyncio.run(main()) 69 | --------------------------------------------------------------------------------