from selenium import webdriver
import pytesser3
import os
import sys, time
from PIL import Image, ImageEnhance
url = "http://ターゲットURLL"
driver = webdriver.Chrome()
time.sleep(2)
driver.get(url)
time.sleep(5)
try:
account = driver.find_element_by_id('_account')
password = driver.find_element_by_id('_password')
region = driver.find_element_by_id('_regionId')
captcha = driver.find_element_by_id('_captcha')
except:
print("查找元素出现异常")
# 网页截图 + 验证码截图
try:
driver.get_screenshot_as_file('G:\\temp\\page\\loginPage1.png') # 比较好理解
im = Image.open('G:\\temp\\page\\loginPage1.png')
box = (884, 684, 1024, 734) # 设置要裁剪的区域，这个坐标是验证码图片这个长方形的左上角坐标和右下角坐标，不懂可以问UI美工，用图形编辑工具很容易获得
region = im.crop(box) # 此时，region是一个新的图像对象。
region.save("G:\\temp\\captcha\\image_code.png")
except:
print("网页截图 + 验证码截图出现异常")
driver.close()
# --------------------图片增强+自动识别简单验证码-----------------------------
# 防止图片还没保存好，就开始识别
time.sleep(3)
im = Image.open("G:\\temp\\captcha\\image_code.png")
imgry = im.convert('L') # 图像加强，二值化
sharpness = ImageEnhance.Contrast(imgry) # 对比度增强
sharp_img = sharpness.enhance(2.0)
sharp_img.save("G:\\temp\\captcha\\image_code.png")
time.sleep(2)
def image_file_to_string(file):
cwd = os.getcwd()
try:
os.chdir("D:\\programs\\Tesseract-OCR")
return pytesser3.image_file_to_string(file)
finally:
os.chdir(cwd)
# code即为识别出的图片数字str类型
code = image_file_to_string("G:\\temp\\captcha\\image_code.png")
time.sleep(1)
print(code)