网络爬虫——古诗文网中验证码（超级鹰）

网络爬虫——古诗文网中验证码（超级鹰）

目标网址: 古诗文网

目标网址：https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx

任务要求：

（1）通过selenium的方式模拟该网站的登录，并成功输入用户名和密码；

（2）保存验证码图片，并使用输入式验证码识别的方式识别验证码的文字，获取后输入到输入框中，

（3）验证登录是否成功。

源码：

超级鹰源码：

import requests
from hashlib import md5

class Chaojiying_Client(object):

    def __init__(self, username, password, soft_id):
        self.username = username
        # todo:更改点一
        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 PostPic(self, im, codetype):
        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 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()

识别源码：

from selenium import webdriver 
from selenium.common.exceptions import TimeoutException , NoSuchElementException
import time 
from PIL import Image
import pytesseract
import chaojiying

browser = webdriver.Edge('E:\\anaconda\\Scripts\\msedgedriver.exe')
# browser = webdriver.Chrome()
try:
    browser.get('https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx')
except TimeoutException:
    print('Time Out')

try:   
    username = browser.find_element_by_xpath('//*[@id="email"]')
    username.send_keys('自己账号')
    time.sleep(1)

    password = browser.find_element_by_xpath('//*[@id="pwd"]')
    password.send_keys('自己密码')
    time.sleep(1)

    pictureN = browser.find_element_by_xpath('//*[@id="imgCode"]')

    browser.save_screenshot('login.png')

    loc = pictureN.location
    size = pictureN.size

    left = loc['x']
    top = loc['y']
    bottom = top+size['height']
    right = left+size['width']

    page = Image.open('login.png')
    Code = page.crop((left,top,right,bottom))
    Code.save('code.png')

    chaojiying = Chaojiying_Client('超级鹰账号', '密码', 'ID')#ID 具体看软件ID。
    im = open('code.png', 'rb').read()
    text = chaojiying.PostPic(im,2004)['pic_str']
    print(text)

#     text = pytesseract.image_to_string(Image.open('code.png'))
#     print(text)    

    CodeWhere = browser.find_element_by_xpath('//*[@id="code"]')
    CodeWhere.send_keys(text)
    time.sleep(5)

    Submit = browser.find_element_by_xpath('//*[@id="denglu"]')
    Submit.click()
    time.sleep(5)
except NoSuchElementException:
    print('No Element')
finally:
    browser.close()