Python+Selenium自动化: 从网页抓取数据并保存照片

import os
import time
import psutil
from selenium.webdriver.chrome.options import Options
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import openpyxl
import requests

# 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
if not os.path.exists(r'C:\Users\Administrator\Desktop\照片'):
    os.mkdir(r'C:\Users\Administrator\Desktop\照片')

# 遍历时间单元K列
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:
            # 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(r'C:\Users\Administrator\Desktop\照片', folder_name)
            if not os.path.exists(folder_path):
                os.mkdir(folder_path)

            # 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 = WebDriverWait(driver, 10).until(EC.presence_of_element_located((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 = WebDriverWait(driver, 10).until(EC.element_to_be_clickable((By.XPATH, '//button[@class="ant-btn ant-btn-primary"]')))
                        driver.execute_script('arguments[0].click();', search_button)
                        time.sleep(2)  # 等待页面加载完成
                        
                        # 获取所有时间单元元素
                        time_elements = WebDriverWait(driver, 10).until(EC.presence_of_all_elements_located((By.XPATH, '//td[@class="ant-table-column-has-actions ant-table-column-has-sorters" and @style="text-align: center;"]')))
                        for time_element in time_elements:
                            time_text = time_element.text
                            # 与时间单元数据对比
                            if time_text == data:
                                # 获取考场编号元素
                                exam_room_elements = WebDriverWait(driver, 10).until(EC.presence_of_all_elements_located((By.XPATH, '//td[@class="ant-table-column-has-actions ant-table-column-has-sorters" and @style="text-align: center;"]')))
                                for exam_room_element in exam_room_elements:
                                    exam_room_text = exam_room_element.text
                                    # 与'H'列数据对比
                                    if exam_room_text == sheet.cell(row=cell.row, column=8).value:
                                        # 创建考场编号文件夹
                                        exam_room_folder = os.path.join(folder_path, exam_room_text)
                                        if not os.path.exists(exam_room_folder):
                                            os.mkdir(exam_room_folder)

                                        # 获取学号和姓名
                                        student_info_elements = WebDriverWait(driver, 10).until(EC.presence_of_all_elements_located((By.XPATH, '//td[@class="ant-table-column-has-actions ant-table-column-has-sorters" and @style="text-align: center;"]')))
                                        for i in range(len(student_info_elements)):
                                            if i % 2 == 0:
                                                student_id_text = student_info_elements[i].text
                                            else:
                                                student_name_text = student_info_elements[i].text
                                                # 提取学号和姓名的数字和文字部分
                                                student_id_num = ''.join(filter(str.isdigit, student_id_text))
                                                student_name = ''.join(filter(str.isalpha, student_name_text))
                                                # 照片名称
                                                photo_name = student_id_num + '_' + student_name + '.jpg'
                                                # 保存照片
                                                photo_path = os.path.join(exam_room_folder, photo_name)
                                                photo_element = WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.XPATH, '//div[@class="img-lazy-load"]/img')))
                                                photo_src = photo_element.get_attribute('src')
                                                response = requests.get(photo_src)
                                                with open(photo_path, 'wb') as f:
                                                    f.write(response.content)
                                                driver.back()
                                                time.sleep(1)  # 等待页面加载完成