使用pytesseract库实现Python验证码识别的详细指南

文章目录

摘要

  python中使用pytesseract库进行ocr识别，需要安装Tesseract-OCR，通过指定pytesseract.tesseract_cmd路径，可以将esseract-OCR集成到pytho程序中，避免客户端电脑的依赖。

1、安装Tesseract-OCR

Tesseract是一个高度精确的开源OCR（光学字符识别）系统，广泛应用于文本识别项目中。

2、在python中使用

pip install pytesseract

3、本地图片识别

import pytesseract
from PIL import Image

# 获取文件的绝对路径
def get_abspath(filename):
    try:
        current_dir = os.getcwd()
        filename = os.path.normpath(os.path.join(current_dir, filename))
        # print(f"get_abspath文件路径：{filename}")
        return filename
    except Exception as e:
        print(f"获取文件绝对路径时出现错误: {e}")
        return ""
        
# 手动指定路径（Windows常见） Tesseract 系统路径
driver_path = r"Tesseract-OCR\\tesseract.exe"
pytesseract.pytesseract.tesseract_cmd = get_abspath(driver_path)

#使用示例
if __name__ == "__main__":
  # 1 识别本地图片 
  # 英文识别
  current_dir = os.getcwd()
    filename = os.path.normpath(os.path.join(current_dir, f"code.jpg"))
    file = Image.open(filename)
    text = pytesseract.image_to_string(file, lang="eng")
    print(text)
  #中文识别，需要下载语言包
    filename = os.path.normpath(os.path.join(current_dir, f"sushi.png"))
    file = Image.open(filename)
    text = pytesseract.image_to_string(file, lang='chi_sim') 
    print(f"识别结果：{text}")

识别结果示例：

4、结合playwright动态识别网站验证码

import os
import pytesseract
from PIL import Image
from playwright.sync_api import Playwright
import tools.pwHander as pwHander
from PIL import Image

# 获取文件的绝对路径
def get_abspath(filename):
    try:
        current_dir = os.getcwd()
        filename = os.path.normpath(os.path.join(current_dir, filename))
        # print(f"get_abspath文件路径：{filename}")
        return filename
    except Exception as e:
        print(f"获取文件绝对路径时出现错误: {e}")
        return ""
        
# 手动指定路径（Windows常见） Tesseract 系统路径
driver_path = r"Tesseract-OCR\\tesseract.exe"
pytesseract.pytesseract.tesseract_cmd = get_abspath(driver_path)

# 验证码图片识别
def get_captcha(page: Playwright, element_selector="img#captcha", file_name="code.jpg"):
    try:
        current_dir = os.getcwd()
        filename = os.path.normpath(os.path.join(current_dir, f"{file_name}"))
               
        # 通过class选择器获取img元素
        code_img = page.locator(element_selector)
        if not code_img:
            raise ValueError("验证码元素未找到！")

        # 刷新验证码
        # code_img.click()

        # 下载验证码图片
        code_img.screenshot(path=filename)

        file = Image.open(filename)
        text = pytesseract.image_to_string(file, lang="eng")
        print("验证码识别结果:", text)
        return text.strip()
    except Exception as e:
        print(f"获取验证码 失败：{str(e)}")
        return ""
#使用示例
if __name__ == "__main__":
  # 2 动态识别网站验证码
  with sync_playwright() as p:
   		browser = p.chromium.launch(headless=False, slow_mo=1000)
        context = browser.new_context()
        page = context.new_page()
        page.goto("测试网址")
	    # 验证码图片下载
	    imgText = get_captcha(page, "img#jcaptcha")
	    print(f"验证码：{imgTest}")

作者：深海蓝山的博客