python爬虫之滑动验证码[完整版] - 简书 - 《Python无用笔记》

滑动验证码破解大致流程为：
被以下专题收入，发现更多相似内容
更多精彩内容">推荐阅读更多精彩内容

0.1132021.02.26 12:17:42 字数 415 阅读 60

python爬虫之滑动验证码[完整版] - 简书 - 图2

爬虫的一大难点就是破解验证码。验证码大致上分为文字识别、滑动、文字点击、图像识别等，本文讲的是其中的滑动验证码。滑动验证码，需要我们将滑块移至图片缺口位置。

滑动验证码破解大致流程为：

1 - 启动浏览器，并进行截图，分割出验证码部分

2 - 将分割得到的验证码图片，发至超级鹰平台，获取返回的坐标

3 - 使用 selenium 模拟移动滑块

使用工具：python，selenium，chromedriver，chrome 浏览器

下面就是喜闻乐见的操作步骤讲解环节了（´◔౪◔）

代码部分：

from selenium import webdriver
from selenium.webdriver.common.action_chains import ActionChains
import time
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from PIL import Image
import os
import sys
path = os.path.dirname(os.path.dirname(__file__))
sys.path.append(path)
from chaojiying import Chaojiying_Client
import requests
from hashlib import md5
class main():
    def __init__(self):
        self.url = 'http://www.geetest.com/Register'
        self.file_path = './img/code_picture.png'
        self.file_path2 = './img/code_picture2.png'
        self.distance = 0
        self.key = 0
    def Launch_browser(self):
        self.driver = webdriver.Chrome()
        self.wait = WebDriverWait(self.driver, 10, 0.5)
        self.driver.get(self.url)
        Phone_Number = self.driver.find_element_by_xpath(
            '/html/body/div[1]/div/div[8]/div/div[2]/div[1]/div[2]/div/div[2]/div[1]/input')
        Verification_Code = self.driver.find_element_by_xpath(
            '/html/body/div[1]/div/div[8]/div/div[2]/div[1]/div[2]/div/div[2]/div[2]/input')
        Code_Button = self.driver.find_element_by_xpath(
            '/html/body/div[1]/div/div[8]/div/div[2]/div[1]/div[2]/div/div[2]/div[2]/div[1]/div')
        Phone_Number.send_keys('12345678910')
        Code_Button.click()
        self.slider = self.wait.until(EC.presence_of_element_located((By.CLASS_NAME, 'geetest_slider_button')))
    def get_picture(self):
        self.driver.save_screenshot(self.file_path)
    def crop_picture(self):
        image = Image.open(self.file_path)
        weight, height = image.size
        box = (weight * 1/2 - 130, height * 1/2 - 130, weight * 1/2 + 130, height * 1/2 + 25)
        region = image.crop(box)
        region.save(self.file_path2)
    def cjy(self):
        self.chaojiying = Chaojiying_Client('xxx', 'xxx', 'xxx')
        im = open('./img/code_picture2.png', 'rb').read()
        re = self.chaojiying.PostPic(im, 9101)
        print(re)
        self.distance = int(re['pic_str'].split(',')[0]) - 25
        print(self.distance)
        self.im_id = re['pic_id']
        print(self.im_id)
    def get_track(self):
        self.track = []
        mid = self.distance * 4 / 5
        current = 0
        t = 0.2
        v = 0
        while current < self.distance:
            if current < mid:
                a = 8
            else:
                a = -12
            v0 = v
            v = v0 + a * t
            move = v * t + 1 / 2 * a * t * t
            current += move
            self.track.append(round(move))
        print(self.track)
    def move(self):
        self.track = [self.distance]
        ActionChains(self.driver).click_and_hold(self.slider).perform()
        for x in self.track:
            ActionChains(self.driver).move_by_offset(xoffset=x, yoffset=0).perform()
        time.sleep(2)
        ActionChains(self.driver).release().perform()
    def check(self):
        if self.key ==1:
            pass
        else:
            re = self.chaojiying.ReportError(self.im_id)
            print(re)
    def quit(self):
        time.sleep(5)
        self.driver.quit()
    def main(self):
        self.Launch_browser()
        self.get_picture()
        self.crop_picture()
        self.cjy()
        self.move()
        self.check()
        self.quit()
if __name__ == '__main__':
    ma = main()
    ma.main()