天天看点

tesseract 图片验证码初级

另存为图片,后缀名.png

下载tesseract

配置环境变量 上方新建第一空 TESSDATA_PREFIX 第二空找到tesseract.exe 右键属性,安全–对象属性

ctrl+左键 pytesseract 进入修改路径 C:\Tesseract-OCR\tesseract.exe 改成双斜杠

代码:

import pytesseract
from PIL import Image

# image = Image.open('code.png')
image = Image.open('code4.png')
# image1 = Image.open('code.png')
# image.show()

tesseract_data = '--tessdata-dir "C:\\Tesseract-OCR\\tessdata"'
#彩色图变成灰度图
image = image.convert('L')
# image.show()

#取出干扰线
# threshold = 170
threshold = 125
table = []
for i in range(256):
    if i<threshold:
        table.append(0)
    else:
        table.append(1)
image = image.point(table,'1')
# image.show()
image_str = pytesseract.image_to_string(image,config=tesseract_data)
print(image_str)
           

运行结果

E:\project\python.exe C:/Users/Administrator/Desktop/四阶xpat爬虫系列/Requests/Requests01/Requests01/day14/demo_tesseract.py

KVGi

Process finished with exit code 0