Python+Selenium自动化: 批量下载考生照片并分类保存

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

# 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列创建时间文件夹
for row in sheet.iter_rows(min_row=2, max_row=sheet.max_row, min_col=11, max_col=11):
    for cell in row:
        data = cell.value
        if data:
            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)

# 遍历表格内'A'列数据，查找考生信息并下载照片
for row in sheet.iter_rows(min_row=2, max_row=sheet.max_row, min_col=1, max_col=1):
    for cell in row:
        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

            # 获取考生姓名
            name_element = driver.find_element(By.XPATH, '//td[@class=""]')
            name = name_element.text

            # 获取考场编号和时间
            room_elements = driver.find_elements(By.XPATH, '//td[@class="ant-table-column-has-actions ant-table-column-has-sorters" and @style="text-align: center;"]')
            for i in range(len(room_elements)):
                room_element = room_elements[i]
                room = room_element.text
                time_element = driver.find_elements(By.XPATH, '//td[@class="ant-table-column-has-actions ant-table-column-has-sorters" and @style="text-align: center;"]')[i]
                time_str = time_element.text

                # 检查是否已经存在考场编号文件夹，如果不存在则创建
                room_folder_path = os.path.join(photo_folder, time_str, room)
                if not os.path.exists(room_folder_path):
                    os.mkdir(room_folder_path)

                # 获取照片链接
                photo_element = driver.find_element(By.XPATH, '//img[@alt="" and @title="报名照片"]')
                photo_url = photo_element.get_attribute("src")

                # 下载照片
                photo_name = f'{student_id}_{name}.jpg'
                photo_path = os.path.join(room_folder_path, photo_name)
                urllib.request.urlretrieve(photo_url, photo_path)

                print(f'下载照片成功：{photo_path}')

driver.quit()