超级鹰，字符，点触，滑块验证码识别_超级鹰验证码识别

目录

字符验证码

导入 pip install pillow

导入：pip install Pytesseract

点触验证

超级鹰接口代码

测试代码

滑块验证

---

字符验证码

导入 ；pip install pillow

导入：pip install Pytesseract

PIL库

Windows下安装
https://digi.bib.uni-mannheim.de/tesseract/可自行下载,点击下一步即可;

# -*- coding: utf-8 -*-
from PIL import Image
 
im = Image.open('1.png')     #从文件中加载图像
img_gray = im.convert('L')  # 对图片进行灰度化
 
 
# ig.save('2.png')   保存灰度化的
 
 
'''对图片进行2值化'''
def binarization(ig):
    w, h = img_gray.size
    tmp = 0
    for i in range(w):
        for j in range(h):
            tmp += ig.getpixel((i, j))
    avg_pixel = tmp / w / h
    # 二值化处理
    for i in range(w):
        for j in range(h):
            p = ig.getpixel((i, j))
            if p > avg_pixel:
                ig.putpixel((i, j), 255)
            else:
                ig.putpixel((i, j), 0)
    return ig
 
 
# img_bz = binarization(img_gray)
# img_bz.save('3.png')
 
'''找到噪点范围'''
def point_list(i, j, prange):
    for x in range(i-prange, i+prange):
        for y in range(j - prange, j + prange):
            if x ==i and y==j:
                continue
            yield (x,y)
 
'''传入需要降噪的二值化图片'''
def reduce_noise(ig):
    w,h = ig.size
    board_rate = 0.06
    prange = 9   #可以改的范围自己调主要是看周围多少黑点
    for i in range(w):
        for j in range(h):
            if i < w * board_rate or i > w * (1 - board_rate) or j < h * board_rate or j > h * (1 - board_rate):
                ig.putpixel((i, j), 255)
                continue
            p = ig.getpixel((i, j))
            if p < 100:
                count = 0
                for x, y in point_list(i, j, prange):
                    if ig.getpixel((x, y)) > 100:
                        count += 1
                if count > 0.5 * ((prange * 2 + 1) ** 2 - 1):
                    ig.putpixel((i, j), 255)
    return ig
 
# ig_nz = reduce_noise(img_bz)
# ig_nz.save('img_nz.png')  #生成完整的图片方便识别
 
 
'''识别图片'''
import pytesseract
pytesseract.pytesseract.tesseract_cmd=r'J:\Tesseract\tesseract.exe'
zhi=pytesseract.image_to_string('img_nz.png')
print(zhi)

点触验证

超级鹰的使用

超级鹰平台配置

超级鹰接口代码

 3. 下载开发文档

4. 创建类的第三个参数是第2步创建的软件的ID

超级鹰接口代码

#!/usr/bin/env python
# coding:utf-8
 
import requests
from hashlib import md5
 
class Chaojiying_Client(object):
 
    def __init__(self, username, password, soft_id):
        self.username = username
        password =  password.encode('utf8')
        self.password = md5(password).hexdigest()
        self.soft_id = soft_id
        self.base_params = {
            'user': self.username,
            'pass2': self.password,
            'softid': self.soft_id,
        }
        self.headers = {
            'Connection': 'Keep-Alive',
            'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
        }
 
    def PostPic(self, im, codetype):
        """
        im: 图片字节
        codetype: 题目类型 参考 http://www.chaojiying.com/price.html
        """
        params = {
            'codetype': codetype,
        }
        params.update(self.base_params)
        files = {'userfile': ('ccc.jpg', im)}
        r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files, headers=self.headers)
        return r.json()
 
    def PostPic_base64(self, base64_str, codetype):
        """
        im: 图片字节
        codetype: 题目类型 参考 http://www.chaojiying.com/price.html
        """
        params = {
            'codetype': codetype,
            'file_base64':base64_str
        }
        params.update(self.base_params)
        r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, headers=self.headers)
        return r.json()
 
    def ReportError(self, im_id):
        """
        im_id:报错题目的图片ID
        """
        params = {
            'id': im_id,
        }
        params.update(self.base_params)
        r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)
        return r.json()
 
 
if __name__ == '__main__':
    chaojiying = Chaojiying_Client('超级鹰用户名', '超级鹰用户名的密码', '96001')	#用户中心>>软件ID 生成一个替换 96001
    im = open('a.jpg', 'rb').read()													#本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
    print(chaojiying.PostPic(im, 1902))												#1902 验证码类型  官方网站>>价格体系 3.4+版 print 后要加()
    #print chaojiying.PostPic(base64_str, 1902)  #此处为传入 base64代码

测试代码

import time
 
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.action_chains  import ActionChains
from chaojiying_Python.chaojiying import Chaojiying_Client
 
user=''
password=''
 
 
 
wb = webdriver.Chrome()
wb.get("https://aq.yy.com/")
 
# 选择iframe
fr = wb.find_element(by=By.XPATH,value='//iframe[@frameborder="0"]')
wb.switch_to.frame(fr)
 
# 选择登录注册
wb.find_element(by=By.XPATH,value='//a[@class="lnRegister"]').click()
 
# 切换焦点
wb.switch_to.window(wb.window_handles[1])
print(wb.title)
 
# 选择iframe
ifr = wb.find_element(by=By.XPATH,value='//iframe[@frameborder="no"]')
wb.switch_to.frame(ifr)
 
# 数据输入框进行输入
wb.find_element(by=By.XPATH, value='//input[@placeholder="输入你的手机号"]').send_keys("17688888888")
wb.find_element(by=By.XPATH, value='//input[@placeholder="设置你帐号的登录密码"]').send_keys("qwe123456")
wb.find_element(by=By.XPATH, value='//input[@placeholder="再次输入密码"]').send_keys("qwe123456")
 
time.sleep(2)
#-----------------------------------------------------------
 
def get_code():
    code_img = 'yy_register.png'
    wb.find_element(by=By.ID, value="interActiveWrap").screenshot(code_img)
    return code_img
 
get_code()
 
time.sleep(2)
 
 
# 超级鹰识别
def img_identify(img_path):
    chaojiying = Chaojiying_Client(username=user, password=password,
                                   soft_id='931146')  # 用户中心>>软件ID 生成一个替换 96001
    im = open(img_path, 'rb').read()  # 本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
    resp = chaojiying.PostPic(im, 9103)
    # {'err_no': 0, 'err_str': 'OK', 'pic_id': '2219320570832210076', 'pic_str': '80,110|146,95|222,109', 'md5': '6896edf2ee6d75a59c81b24ce73967f6'}
    # '80,110|146,95|222,109'
    pic_str = resp.get('pic_str')  # '80,110|146,95|222,109'
    pic_list = pic_str.split("|")  # ['80,110','146,95','222,109']
    return pic_list
 
 
img_list = img_identify('yy_register.png')
 
# 点击图片
def img_click(my_list):
    img_element = wb.find_element(by=By.ID, value="interActiveWrap")
    for i in my_list:
        data = i.split(',')  #['80','110']
        x = int(data[0])  # 80
        y = int(data[1])  # 110
        # 将鼠标移动到距某个元素多少距离的位置
        ActionChains(wb).move_to_element_with_offset(img_element, xoffset=x, yoffset=y).click().perform()
        time.sleep(2)
    wb.find_element(by=By.XPATH, value='//span[@class="pw_submit"]').click()
 
img_click(img_list)
 
 
wb.find_element(by=By.XPATH, value='//span[@node-name="JCheck"]').click()
wb.find_element(by=By.XPATH, value='//a[@class="btn_blue_v3"]').click()
 
 
 
 
 
 
 
 

滑块验证

"""
1.打开 https://captcha1.scrape.center/
2.点击登录出现滑块验证
3.计算滑块需要移动的距离
    1、知道他们颜色的色差
        a.如果能够得到完整的图片
        b.再得到缺口图片
            就可以找到移动的结束位置
        c.能够得到滑块图片
            就可以找到移动的开始位置
4.使用selenium的动作链进行操作
"""
import time
from PIL import Image
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By
 
def get_captcha():
    # (1)隐藏滑块  得到缺口图
    js_hide_slice ='document.getElementsByClassName("geetest_canvas_slice")[0].style.display="none"'
    driver.execute_script(js_hide_slice)
    # 截取缺口图
    part_imgpath = "./part.png"
    driver.find_element_by_class_name("geetest_canvas_bg").screenshot(part_imgpath)
 
    # (2)显示滑块  隐藏缺口图  得到滑块图
    js_show_slice = 'document.getElementsByClassName("geetest_canvas_slice")[0].style.display="block"'
    js_hide_part= 'document.getElementsByClassName("geetest_canvas_bg")[0].style.display="none"'
    driver.execute_script(js_show_slice + ";" + js_hide_part)
    # 截取滑块图
    slice_imgpath = "./slice.png"
    driver.find_element_by_class_name("geetest_canvas_slice").screenshot(slice_imgpath)
 
    # (3)显示完整图
    js_show_full1 = 'document.getElementsByClassName("geetest_canvas_fullbg")[0].style.display="block"'
    js_show_full2 = 'document.getElementsByClassName("geetest_canvas_fullbg")[0].style.opacity="1"'
    driver.execute_script(js_show_full1+";"+js_show_full2)
    # 截取完整图
    full_imgpath = "./full.png"
    driver.find_element_by_class_name("geetest_canvas_fullbg").screenshot(full_imgpath)
 
    #还原  目的 还原成原来的模样  包含缺口图与滑块
    js_hide_full1 = 'document.getElementsByClassName("geetest_canvas_fullbg")[0].style.display="none"'
    js_hide_full2 = 'document.getElementsByClassName("geetest_canvas_fullbg")[0].style.opacity="0"'
    js_show_part = 'document.getElementsByClassName("geetest_canvas_bg")[0].style.display="block"'
    driver.execute_script(js_hide_full1 + ";" + js_hide_full2+ ";" +js_show_part)
 
    return part_imgpath,slice_imgpath,full_imgpath
 
# 1.计算滑块的x轴坐标
def get_slice_x(img_sclice):
    img = Image.open(img_sclice)
    w, h = img.size
    for x in range(w):
        for y in range(h):
            rgb = img.getpixel((x,y)) # (255,255,255)
            if rgb[0] + rgb[1] + rgb[2] < 600:
                print("滑块的坐标", x)
                return x
 
# 2.计算缺口图的x轴坐标
def get_bg_x(img_bg, img_full):
    bg = Image.open(img_bg)
    full = Image.open(img_full)
    w, h = bg.size
    for x in range(w):
        for y in range(h):
            bg_point = bg.getpixel((x,y))
            full_point = full.getpixel((x, y))
            r = bg_point[0] - full_point[0]
            g = bg_point[1] - full_point[1]
            b = bg_point[2] - full_point[2]
            abs_value = abs(r) + abs(g) + abs(b)   # 33
            if abs_value > 180:
                print("缺口的坐标", x)
                return x
 
# 计算滑动的距离
def get_distance(img_slice, img_bg, img_full):
    slice_x = get_slice_x(img_slice)
    bg_x = get_bg_x(img_bg, img_full)
    data = abs(slice_x - bg_x)
    print('计算距离',data)
    return data
 
# 模拟滑动
def move_silder(tracks):# 100
    # 确定滑块对象
    element = driver.find_element(by=By.CLASS_NAME, value='geetest_slider_button')
    action_chains = ActionChains(driver)
    # 执行滑块的动作
    action_chains.click_and_hold(element).perform()
    action_chains.pause(0.2)
    action_chains.move_by_offset(tracks-10, 0) #
    action_chains.pause(0.6)
    action_chains.move_by_offset(10, 0)  #
    action_chains.pause(0.6)
    action_chains.release().perform()
 
 
if __name__ == '__main__':
    driver = webdriver.Chrome()
    url = 'https://captcha1.scrape.center/'
    driver.get(url)
    time.sleep(5)  # 这里需要有一个停顿
    driver.find_element(by=By.CLASS_NAME, value='el-button--primary').click()
    time.sleep(2)
    # 解决问题3的截图操作（a,b,c）
    img_bg, img_slice, img_full = get_captcha()
    # 计算距离
        # 1.计算滑块的x轴坐标
    # get_slice_x('slice.png')
        # 2.计算缺口图的x轴坐标
    # get_bg_x('part.png', 'full.png')
    distance = get_distance(img_slice, img_bg, img_full)
    move_silder(distance)