https://github.com/SkyBlueEternal/667788

动态爬虫+logo识别
https://github.com/SkyBlueEternal/667788

Last synced: 4 months ago
JSON representation

动态爬虫+logo识别

• Host: GitHub
• URL: https://github.com/SkyBlueEternal/667788
• Owner: SkyBlueEternal
• License: gpl-3.0
• Created: 2020-08-28T06:15:46.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2020-08-31T10:07:34.000Z (about 5 years ago)
• Last Synced: 2025-07-01T13:59:31.525Z (4 months ago)
• Language: Python
• Size: 16.1 MB
• Stars: 8
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-hacking-lists - SkyBlueEternal/667788 - 动态爬虫+logo识别 (Python)

README

          
![GNU General Public License v3.0](https://img.shields.io/badge/GNU%20General%20Public%20License-V3.0-red) ![SkyBlueEternal](https://img.shields.io/badge/By-SkyBlueEternal-yellow)  ![Project](https://img.shields.io/badge/project-https://github.com/SkyBlueEternal/667788-blue)

# 667788项目 动态爬虫+logo识别

   #### 本项目为识别引擎示例，可以结合信息收集接口，对于网站批量识别。

# 实现原理

   使用seleniumrequests和OpenCV开发的引擎，调用方法在Main.py之中。

# 目录结构

- 667788

  baidu.png

  main.py

  - api_lib

    - chromedriver_linux64

         chromedriver

    - chromedriver_mac64

         chromedriver

    - chromedriver_win32

         chromedriver.exe

  - py_lib

      dynamic_crawler.py

      env_settings.py

      logo_recognition.py

      random_str.py

# 环境搭建

需要指定谷歌浏览器版本 谷歌浏览器：86.0.4209.2 win32 

使用pip install -r requirements.txt 安装，可能会提示找不到模块，则需要去模块官网下载对应版本。

# 使用方法

启动：Python main.py 

样本设置在 logo_recognition.LogoRec().test_xfeatures2d(key, "baidu.png")

目标站点设置在 dynamic_crawler.RequestsHttp(url="https://www.baidu.com/").requests_get()

# 识别结果

## 样本

![img](./baidu.png)

## 识别情况

![img](./-1950992685154535579.png)