Python+Selenium自动化抓取网页数据并分类保存

import os
import time
import psutil
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
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
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_folders = set()  # 用于记录已创建的时间文件夹
for row in sheet.iter_rows(min_row=2, max_row=sheet.max_row, min_col=11, max_col=11):
    for cell in row:
        # 获取时间单元内的数据
        data = cell.value
        if data and data not in time_folders:
            # 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)
            os.mkdir(folder_path)
            time_folders.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

            # 获取考生信息页面的HTML
            html = driver.page_source

            # 查找所有时间单元和考场编号元素
            time_elements = driver.find_elements(By.XPATH, '//td[@class="ant-table-column-has-actions ant-table-column-has-sorters" and @style="text-align: center;"]')
            room_elements = driver.find_elements(By.XPATH, '//td[@class="ant-table-column-has-actions ant-table-column-has-sorters" and @style="text-align: center;"]')

            # 遍历时间单元和考场编号元素
            for time_element, room_element in zip(time_elements, room_elements):
                time_text = time_element.text
                room_text = room_element.text

                # 提取时间和考场编号
                time_value = time_text.split('|')[-1].strip()
                room_value = room_text.strip()

                # 检查时间和考场编号与表格数据是否匹配
                if time_value in time_folders:
                    # 获取照片URL
                    img_element = driver.find_element(By.XPATH, '//img[@alt="报名照片"]')
                    img_url = img_element.get_attribute('src')

                    # 创建考场编号文件夹
                    room_folder_path = os.path.join(photo_folder, time_value, room_value)
                    if not os.path.exists(room_folder_path):
                        os.mkdir(room_folder_path)

                    # 下载照片
                    response = requests.get(img_url)
                    img_name = f'{student_id}.jpg'
                    img_path = os.path.join(room_folder_path, img_name)
                    with open(img_path, 'wb') as f:
                        f.write(response.content)
                    print(f'下载照片成功: {img_path}')