使用Python和Selenium自动下载考后核验照片

import os
import time
import psutil
from selenium.webdriver.chrome.options import Options
from selenium import webdriver
from selenium.webdriver.common.by import By
import openpyxl
import urllib.request

# 检查是否已经存在浏览器实例，如果存在则不再创建
for proc in psutil.process_iter():
    try:
        if 'chrome' in proc.name() and '--remote-debugging-port=9224' in proc.cmdline():
            options = Options()
            options.add_experimental_option('debuggerAddress', '127.0.0.1:9224')
            break
    except:
        pass
else:
    # 创建浏览器实例
    os.system(r'start chrome --remote-debugging-port=9224 --user-data-dir="D:\评阅用"')
    options = Options()
    options.add_experimental_option('debuggerAddress', '127.0.0.1:9224')

# 在已有的浏览器实例中查找标签页
driver = webdriver.Chrome(options=options)
tabs = driver.window_handles
for tab in tabs:
    driver.switch_to.window(tab)
    if driver.title == '考后核验':
        print('登陆成功')
        break

# 打开Excel表格
wb = openpyxl.load_workbook(r'C:\Users\Administrator\Desktop\考后核验.xlsx')
sheet = wb.active

# 创建照片文件夹
photo_folder = r'C:\Users\Administrator\Desktop\照片'
if not os.path.exists(photo_folder):
    os.mkdir(photo_folder)

# 遍历时间单元K列
time_set = set()
for row in sheet.iter_rows(min_row=2, max_row=sheet.max_row, min_col=11, max_col=11):
    for cell in row:
        # 获取时间单元内的数据
        data = cell.value
        if data and data not in time_set:
            # 创建子文件夹
            folder_name = time.strftime('%Y-%m-%d %H-%M-%S', time.strptime(data, '%Y-%m-%d %H:%M:%S'))
            folder_path = os.path.join(photo_folder, folder_name)
            if not os.path.exists(folder_path):
                os.mkdir(folder_path)
            time_set.add(data)

# 遍历表格内'A'列数据
for row in sheet.iter_rows(min_row=2, max_row=sheet.max_row, min_col=1, max_col=1):
    for cell in row:
        # 获取学号
        student_id = cell.value
        if student_id:
            # 在网页内查找考生信息
            search_input = driver.find_element(By.XPATH, '//input[@placeholder="姓名/考生号"]')
            search_input.clear()
            search_input.send_keys(student_id)
            time.sleep(1)  # 等待页面加载完成
            search_button = driver.find_element(By.XPATH, '//button[@class="ant-btn ant-btn-primary"]')
            driver.execute_script('arguments[0].click();', search_button)
            time.sleep(1)  # 等待页面加载完成

            # 查找时间和考场编号
            time_cells = driver.find_elements(By.XPATH, '//td[@class="ant-table-column-has-actions ant-table-column-has-sorters" and @style="text-align: center;"]')
            room_cells = driver.find_elements(By.XPATH, '//td[@class="ant-table-column-has-actions ant-table-column-has-sorters" and @style="text-align: center;"]')
            
            # 遍历时间和考场编号，查找匹配的数据
            for time_cell, room_cell in zip(time_cells, room_cells):
                time_text = time_cell.text
                room_text = room_cell.text
                if time_text in time_set:
                    # 在对应的时间文件夹下创建考场编号文件夹
                    folder_name = room_text.replace(':', '-') # 将时间格式中的冒号替换为短横线
                    folder_path = os.path.join(photo_folder, time_text, folder_name)
                    if not os.path.exists(folder_path):
                        os.makedirs(folder_path)
                        
                    # 获取学号和姓名
                    student_id_element = driver.find_element(By.XPATH, f'//td[@class="ant-table-column-has-actions ant-table-column-has-sorters" and text()="{time_text}"]/preceding-sibling::td')
                    student_name_element = driver.find_element(By.XPATH, f'//td[@class="ant-table-column-has-actions ant-table-column-has-sorters" and text()="{time_text}"]/following-sibling::td')
                    student_id_text = student_id_element.text
                    student_name_text = student_name_element.text
                    
                    # 获取照片链接
                    photo_element = driver.find_element(By.XPATH, f'//td[@class="ant-table-column-has-actions ant-table-column-has-sorters" and text()="{time_text}"]/following-sibling::td//img')
                    photo_url = photo_element.get_attribute("src")
                    
                    # 下载照片
                    photo_name = student_id_text + '_' + student_name_text + '.jpg'
                    photo_path = os.path.join(folder_path, photo_name)
                    urllib.request.urlretrieve(photo_url, photo_path)