def get_info(self, html=None):
"""Get hit card info, which is the old info with updated new time."""
if not html:
time.sleep(1)
res = self.sess.get(self.base_url)
html = res.content.decode()
try:
old_infos = re.findall(r'oldInfo: ({[^\n]+})', html)
if len(old_infos) != 0:
old_info = json.loads(old_infos[0])
else:
raise RegexMatchError("未发现缓存信息，请先至少手动成功打卡一次再运行脚本")
def_info = json.loads(re.findall(r'def = ({[^\n]+})', html)[0])
magic_code = re.findall(
r'"([0-9a-z]{32})": "([0-9]{10})","([0-9a-z]{32})":"([0-9a-z]{32})"', html)[0]
magic_code_group = {
magic_code[0]: magic_code[1],
magic_code[2]: magic_code[3]
}
except IndexError as err:
raise RegexMatchError(
'Relative info not found in html with regex: ' + str(err))
except json.decoder.JSONDecodeError as err:
raise DecodeError('JSON decode error: ' + str(err))
new_info = def_info.copy()
new_info.update(magic_code_group)
ocr = ddddocr.DdddOcr()
resp = self.sess.get(self.captcha_url)
# form change
new_info['szgjcs'] = ""
new_info['zgfx14rfhsj'] = ""
new_info['geo_api_info'] = old_info['geo_api_info'] # 定位
new_info['address'] = old_info['address']
new_info['area'] = old_info['area']
new_info['city'] = old_info['city']
new_info['ismoved'] = 0
new_info['sfzx'] = old_info['sfzx'] # 在校
new_info['sfymqjczrj'] = old_info['sfymqjczrj'] # 入境
new_info['sfqrxxss'] = 1 # 属实
new_info['campus'] = '紫金港校区' #校区
new_info['verifyCode'] = ocr.classification(resp.content)#验证码
self.info = new_info
# print(json.dumps(self.info))
return new_info
def yzm():
try:
# 获取验证码
# 获取验证码
operation = True
counter = 0
while (operation):
if counter > 5:
operation = False
WebDriverWait(driver, 10).until(
EC.presence_of_element_located(
(By.XPATH, "//*[@id='imgObjjgRegist']")))
imgelement = driver.find_elements_by_xpath(
'//*[@id="imgObjjgRegist"]') # 定位验证码
if not imgelement:
return
try:
imgelement[0].screenshot('./save.png')
except Exception as e:
print("截图失败")
print(e)
counter += 1
continue
# 验证码识别
ocr = ddddocr.DdddOcr()
with open('./save.png', 'rb') as f:
img_bytes = f.read()
res = ocr.classification(img_bytes)
f.close()
print(res)
driver.find_element_by_id('yzm').send_keys(res)
driver.find_element_by_id('pass-dialog').click()
counter += 1
sleep(1)
if not driver.find_elements_by_class_name("weui-toptips_warn"):
operation = False
except Exception as e:
print("验证码处理失败")
print(e)
def do_auto_work(browser):
browser.get("https://hk.sz.gov.cn:8118/userPage/login")
mouse = ActionChains(browser)
msgbox = browser.find_element(
By.XPATH, '//*[@id="winLoginNotice"]/div[@class="flexbox btngroup"]')
mouse.move_to_element(msgbox).click()
mouse.perform()
card_type_node = browser.find_element(
By.XPATH, '//select[@id="select_certificate"]')
card_selector = Select(card_type_node)
card_selector.select_by_index(1)
id_card_node = browser.find_element(By.XPATH,
'//input[@id="input_idCardNo"]')
id_card_node.send_keys("111111")
pwd_node = browser.find_element(By.XPATH, '//input[@id="input_pwd"]')
pwd_node.send_keys("111111")
#
# # 隐式等待
# browser.implicitly_wait(5)
# img_verify_node = browser.find_element(By.XPATH, '//*[@id="img_verify"]')
# 显式等待
wait = WebDriverWait(browser, 30)
img_verify_node = wait.until(
expected_conditions.presence_of_element_located(
(By.XPATH, '//*[@id="img_verify"]')))
bytes = base64.b64decode(img_verify_node.screenshot_as_base64)
img_verify_ocr_result = ddddocr.DdddOcr().classification(bytes)
input_verify_code_node = browser.find_element(
By.XPATH, '//input[@id="input_verifyCode"]')
input_verify_code_node.send_keys(img_verify_ocr_result)
import ddddocr
ocr = ddddocr.DdddOcr(show_ad=False)
def get_num(img_bytes) -> int:
ret = ocr.classification(img_bytes)
ret = ret or '0'
if 'l' in ret:
ret = '1'
return int(ret)
import random
import time
import traceback
from tempfile import NamedTemporaryFile
from typing import List, Callable, Dict
import ddddocr
from loguru import logger
from selenium.common.exceptions import NoSuchElementException, TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.remote.webelement import WebElement
from selenium.webdriver.support import expected_conditions
from selenium.webdriver.support.select import Select
from selenium.webdriver.support.wait import WebDriverWait
ocr = ddddocr.DdddOcr()
class PageOperations:
operations = {} # type: Dict[str, Callable]
operation_children_dict = {} # type: Dict[str, List[str]]
def __init__(self):
raise NotImplementedError()
@staticmethod
def run(name: str, kwargs=None):
if kwargs is None:
kwargs = {}
try:
logger.info(f"run operation {name}")
if ocr_mode == "本地1":
# 这一行代码用于关闭tensorflow的gpu模式（如果使用，内存占用翻几倍）
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
import muggle_ocr
# 初始化；model_type 包含了 ModelType.OCR/ModelType.Captcha 两种
sdk = muggle_ocr.SDK(model_type=muggle_ocr.ModelType.OCR)
if ocr_mode == "本地2":
import tr
if ocr_mode == "本地3":
import ddddocr
ocr = ddddocr.DdddOcr(show_ad=False, old=True)
if ocr_mode == "本地4":
import easyocr
# 'ch_tra' 中文繁体
easyocr_reader = easyocr.Reader(['ch_sim', 'en'], gpu=False,
verbose=False) # this needs to run only once to load the model into memory
else:
if ocr_mode == "网络1":
import queue
# 这一行创建了发包队列
baidu_queue = queue.Queue(baidu_QPS)
config = {
'appId': 'PCR',
'apiKey': baidu_apiKey,
def __init__(self):
self.oldocr = ddddocr.DdddOcr(old=True, show_ad=False)
self.ocr = ddddocr.DdddOcr(show_ad=False)
self.det = ddddocr.DdddOcr(det=True, show_ad=False)
def detect(input):
ocr = ddddocr.DdddOcr(show_ad=0)
with input as f:
res = ocr.classification(f.read())
return res