几种验证码识别

了解更多关注微信公众号“木下学Python”吧~
原文：https://blog.csdn.net/zjkpy_5/article/details/83472122

1.图形验证码

import pytesseract
from PIL import Image

im=Image.open('image.png')

转化为灰度图像

im = im.convert('L') #转化为灰度图像
threshold = 127
table = []
for i in range(256):
if i < threshold:
table.append(0)
else:
table.append(1)

im = im.point(table,'1')
print(pytesseract.image_to_string(im))

2.极验验证码

import time
from io import BytesIO
from PIL import Image
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

EMAIL = '1347904922@qq.com'
PASSWORD = 'Zjk12345'
BORDER = 6
INIT_LEFT = 60

class CrackGeetest():
def init(self):
self.url = 'https://account.geetest.com/login'
self.browser = webdriver.Chrome()
self.wait = WebDriverWait(self.browser, 20)
self.email = EMAIL
self.password = PASSWORD

def __del__(self):
    self.browser.close()

def get_geetest_button(self):
    """
    获取初始验证按钮
    :return:
    """
    button = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'geetest_radar_tip')))
    return button

def get_position(self):
    """
    获取验证码位置
    :return: 验证码位置元组
    """
    img = self.wait.until(EC.presence_of_element_located((By.CLASS_NAME, 'geetest_canvas_img')))
    time.sleep(2)
    location = img.location
    size = img.size
    top, bottom, left, right = location['y'], location['y'] + size['height'], location['x'], location['x'] + size[
        'width']
    return (top, bottom, left, right)

def get_screenshot(self):
    """
    获取网页截图
    :return: 截图对象
    """
    screenshot = self.browser.get_screenshot_as_png()
    screenshot = Image.open(BytesIO(screenshot))
    return screenshot

def get_slider(self):
    """
    获取滑块
    :return: 滑块对象
    """
    slider = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'geetest_slider_button')))
    return slider

def get_geetest_image(self, name='captcha.png'):
    """
    获取验证码图片
    :return: 图片对象
    """
    top, bottom, left, right = self.get_position()
    print('验证码位置', top, bottom, left, right)
    screenshot = self.get_screenshot()
    captcha = screenshot.crop((left, top, right, bottom))
    captcha.save(name)
    return captcha

def open(self):
    """
    打开网页输入用户名密码
    :return: None
    """
    self.browser.get(self.url)
    email = self.wait.until(EC.presence_of_element_located((By.ID, 'email')))
    password = self.wait.until(EC.presence_of_element_located((By.ID, 'password')))
    email.send_keys(self.email)
    password.send_keys(self.password)

def get_gap(self, image1, image2):
    """
    获取缺口偏移量
    :param image1: 不带缺口图片
    :param image2: 带缺口图片
    :return:
    """
    left = 60
    for i in range(left, image1.size[0]):
        for j in range(image1.size[1]):
            if not self.is_pixel_equal(image1, image2, i, j):
                left = i
                return left
    return left

def is_pixel_equal(self, image1, image2, x, y):
    """
    判断两个像素是否相同
    :param image1: 图片1
    :param image2: 图片2
    :param x: 位置x
    :param y: 位置y
    :return: 像素是否相同
    """
    # 取两个图片的像素点
    pixel1 = image1.load()[x, y]
    pixel2 = image2.load()[x, y]
    threshold = 60
    if abs(pixel1[0] - pixel2[0]) < threshold and abs(pixel1[1] - pixel2[1]) < threshold and abs(
            pixel1[2] - pixel2[2]) < threshold:
        return True
    else:
        return False

def get_track(self, distance):
    """
    根据偏移量获取移动轨迹
    :param distance: 偏移量
    :return: 移动轨迹
    """
    # 移动轨迹
    track = []
    # 当前位移
    current = 0
    # 减速阈值
    mid = distance * 4 / 5
    # 计算间隔
    t = 0.2
    # 初速度
    v = 0

    while current < distance:
        if current < mid:
            # 加速度为正2
            a = 2
        else:
            # 加速度为负3
            a = -3
        # 初速度v0
        v0 = v
        # 当前速度v = v0 + at
        v = v0 + a * t
        # 移动距离x = v0t + 1/2 * a * t^2
        move = v0 * t + 1 / 2 * a * t * t
        # 当前位移
        current += move
        # 加入轨迹
        track.append(round(move))
    return track

def move_to_gap(self, slider, track):
    """
    拖动滑块到缺口处
    :param slider: 滑块
    :param track: 轨迹
    :return:
    """
    ActionChains(self.browser).click_and_hold(slider).perform()
    for x in track:
        ActionChains(self.browser).move_by_offset(xoffset=x, yoffset=0).perform()
    time.sleep(0.5)
    ActionChains(self.browser).release().perform()

def login(self):
    """
    登录
    :return: None
    """
    submit = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'login-btn')))
    submit.click()
    time.sleep(10)
    print('登录成功')

def crack(self):
    # 输入用户名密码
    self.open()
    # 点击验证按钮
    button = self.get_geetest_button()
    button.click()
    # 获取验证码图片
    image1 = self.get_geetest_image('captcha1.png')
    # 点按呼出缺口
    slider = self.get_slider()
    slider.click()
    # 获取带缺口的验证码图片
    image2 = self.get_geetest_image('captcha2.png')
    # 获取缺口位置
    gap = self.get_gap(image1, image2)
    print('缺口位置', gap)
    # 减去缺口位移
    gap -= BORDER
    # 获取移动轨迹
    track = self.get_track(gap)
    print('滑动轨迹', track)
    # 拖动滑块
    self.move_to_gap(slider, track)

    success = self.wait.until(
        EC.text_to_be_present_in_element((By.CLASS_NAME, 'geetest_success_radar_tip_content'), '验证成功'))
    print(success)

    # 失败后重试
    if not success:
        self.crack()
    else:
        self.login()

if name == 'main':
crack = CrackGeetest()
crack.crack()

3.微博宫格验证码

import os
import time
from io import BytesIO
from PIL import Image
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from os import listdir

USERNAME = '15874295385'
PASSWORD = 'fpdpvx119'

TEMPLATES_FOLDER = 'templates/'

class CrackWeiboSlide():
def init(self):
self.url = 'https://passport.weibo.cn/signin/login?entry=mweibo&r=https://m.weibo.cn/'
self.browser = webdriver.Chrome()
self.wait = WebDriverWait(self.browser, 20)
self.username = USERNAME
self.password = PASSWORD

def __del__(self):
    self.browser.close()

def open(self):
    """
    打开网页输入用户名密码并点击
    :return: None
    """
    self.browser.get(self.url)
    username = self.wait.until(EC.presence_of_element_located((By.ID, 'loginName')))
    password = self.wait.until(EC.presence_of_element_located((By.ID, 'loginPassword')))
    submit = self.wait.until(EC.element_to_be_clickable((By.ID, 'loginAction')))
    username.send_keys(self.username)
    password.send_keys(self.password)
    submit.click()

def get_position(self):
    """
    获取验证码位置
    :return: 验证码位置元组
    """
    try:
        img = self.wait.until(EC.presence_of_element_located((By.CLASS_NAME, 'patt-shadow')))
    except TimeoutException:
        print('未出现验证码')
        self.open()
    time.sleep(2)
    location = img.location
    size = img.size
    top, bottom, left, right = location['y'], location['y'] + size['height'], location['x'], location['x'] + size[
        'width']
    return (top, bottom, left, right)

def get_screenshot(self):
    """
    获取网页截图
    :return: 截图对象
    """
    screenshot = self.browser.get_screenshot_as_png()
    screenshot = Image.open(BytesIO(screenshot))
    return screenshot

def get_image(self, name='captcha.png'):
    """
    获取验证码图片
    :return: 图片对象
    """
    top, bottom, left, right = self.get_position()
    print('验证码位置', top, bottom, left, right)
    screenshot = self.get_screenshot()
    captcha = screenshot.crop((left, top, right, bottom))
    captcha.save(name)
    return captcha

def is_pixel_equal(self, image1, image2, x, y):
    """
    判断两个像素是否相同
    :param image1: 图片1
    :param image2: 图片2
    :param x: 位置x
    :param y: 位置y
    :return: 像素是否相同
    """
    # 取两个图片的像素点
    pixel1 = image1.load()[x, y]
    pixel2 = image2.load()[x, y]
    threshold = 20
    if abs(pixel1[0] - pixel2[0]) < threshold and abs(pixel1[1] - pixel2[1]) < threshold and abs(
            pixel1[2] - pixel2[2]) < threshold:
        return True
    else:
        return False

def same_image(self, image, template):
    """
    识别相似验证码
    :param image: 待识别验证码
    :param template: 模板
    :return:
    """
    # 相似度阈值
    threshold = 0.99
    count = 0
    for x in range(image.width):
        for y in range(image.height):
            # 判断像素是否相同
            if self.is_pixel_equal(image, template, x, y):
                count += 1
    result = float(count) / (image.width * image.height)
    if result > threshold:
        print('成功匹配')
        return True
    return False

def detect_image(self, image):
    """
    匹配图片
    :param image: 图片
    :return: 拖动顺序
    """
    for template_name in listdir(TEMPLATES_FOLDER):
        print('正在匹配', template_name)
        template = Image.open(TEMPLATES_FOLDER + template_name)
        if self.same_image(image, template):
            # 返回顺序
            numbers = [int(number) for number in list(template_name.split('.')[0])]
            print('拖动顺序', numbers)
            return numbers

def move(self, numbers):
    """
    根据顺序拖动
    :param numbers:
    :return:
    """
    # 获得四个按点
    circles = self.browser.find_elements_by_css_selector('.patt-wrap .patt-circ')
    dx = dy = 0
    for index in range(4):
        circle = circles[numbers[index] - 1]
        # 如果是第一次循环
        if index == 0:
            # 点击第一个按点
            ActionChains(self.browser) \
                .move_to_element_with_offset(circle, circle.size['width'] / 2, circle.size['height'] / 2) \
                .click_and_hold().perform()
        else:
            # 小幅移动次数
            times = 30
            # 拖动
            for i in range(times):
                ActionChains(self.browser).move_by_offset(dx / times, dy / times).perform()
                time.sleep(1 / times)
        # 如果是最后一次循环
        if index == 3:
            # 松开鼠标
            ActionChains(self.browser).release().perform()
        else:
            # 计算下一次偏移
            dx = circles[numbers[index + 1] - 1].location['x'] - circle.location['x']
            dy = circles[numbers[index + 1] - 1].location['y'] - circle.location['y']

def crack(self):
    """
    破解入口
    :return:
    """
    self.open()
    # 获取验证码图片
    image = self.get_image('captcha.png')
    numbers = self.detect_image(image)
    self.move(numbers)
    time.sleep(10)
    print('识别结束')

if name == 'main':
crack = CrackWeiboSlide()
crack.crack()

4.超级鹰接口验证码

import requests
from hashlib import md5

class Chaojiying(object):

def __init__(self, username, password, soft_id):
    self.username = username
    self.password = md5(password.encode('utf-8')).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 post_pic(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 report_error(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()
©著作权归作者所有,转载或内容合作请联系作者
平台声明：文章内容（如有图片或视频亦包括在内）由作者上传并发布，文章内容仅代表作者本人观点，简书系信息发布平台，仅提供信息存储服务。

推荐阅读更多精彩内容

  • 爬虫 之 极验验证码
    验证码的另一种方法：极验验证码， 此文章代码非原创，如有侵权，请告知删除。 我们以bilibili为例：https...
    煎炼阅读 1,544评论 0赞 0
  • 滑动验证码-转载
    我们可以借助插件来做 打开插件，找到自己需要的验证码 筛选有用的路径 把对应的视图函数也拿过来，注意还需要一个ge...
    程序员之路阅读 1,373评论 0赞 1
  • selenium用法详解
    selenium用法详解 selenium主要是用来做自动化测试，支持多种浏览器，爬虫中主要用来解决JavaScr...
    陳_CHEN_陈阅读 3,960评论 1赞 5
  • 2018-08-29
    前言 离上一篇更新的博文应该过了挺久的了（python爬虫（上）–请求——关于旅游网站的酒店评论爬取（传参方法））...
    Mrhyden阅读 530评论 0赞 0
  • 幸福是给别人的，痛苦与孤独则是自己的
    爱笑的女生运气不会太差 总听人这么说 今年24岁的我 在我过往的二十四年里 也算见过形形色色的笑容 有一种人是骨子...
    不懂事的大人阅读 277评论 0赞 1