亚马逊验证码识别

一.通过ocr识别亚马逊验证码

# -*- coding: utf-8 -*-
# @Time    : 2021/10/8 8:38
# @Author  :
import numpy as np
from urllib.request import urlopen

import cv2
import easyocr
# from torchvision import transforms
# trans = transforms.ToTensor()


# opencv链接转图片
def url_to_image(url):
    # download the image, convert it to a NumPy array, and then read
    # it into OpenCV format
    resp = urlopen(url)
    # bytearray将数据转换成（返回）一个新的字节数组
    # asarray 复制数据，将结构化数据转换成ndarray
    image = np.asarray(bytearray(resp.read()), dtype="uint8")
    # cv2.imdecode()函数将数据解码成Opencv图像格式
    image = cv2.imdecode(image, cv2.IMREAD_COLOR)
    # return the image
    return image


# initialize the list of image URLs to download
# amazon captcha img url
# https://www.amazon.com/errors/validateCaptcha
urls = [
    "https://images-na.ssl-images-amazon.com/captcha/ddwwidnf/Captcha_hkpyvxpepn.jpg",
]

# loop over the image URLs
for url in urls:
    # download the image URL and display it
    print("downloading %s" % (url))
    img = url_to_image(url)
    reader = easyocr.Reader(['ch_sim', 'en'])
    print("亚马逊验证码结果:", reader.readtext(img))
    cv2.imshow("img", img)
    # res = cv2.resize(img, (192, 64))
    # image  = trans(res)
    # cv2.imshow('new_img', res)
    cv2.waitKey(0)