soilgd/截图.py

from selenium import webdriver
from selenium.webdriver.edge.service import Service as EdgeService
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.edge.options import Options
import requests
import os
import time
import re

# 设置Edge选项
edge_options = Options()
edge_options.add_argument('--headless')  # 如果不需要看到浏览器运行界面，则取消此行注释
edge_options.add_argument('--disable-gpu')

# 设置webdriver路径，注意替换为你自己的msedgedriver路径
webdriver_path = "D:/Drivers/msedgedriver.exe"
service = EdgeService(executable_path=webdriver_path)

driver = webdriver.Edge(service=service, options=edge_options)
wait = WebDriverWait(driver, 10)  # 等待元素加载的最大等待时间

save_dir = r"C:\Users\Administrator\Pictures\Captures"
if not os.path.exists(save_dir):
    os.makedirs(save_dir)


def sanitize_filename(filename):
    """Remove or replace characters that are invalid in filenames."""
    return re.sub(r'[<>:"/\\|?*]', '_', filename)


def download_images_from_page(page_url, index_offset=0):
    images = driver.find_elements(By.TAG_NAME, 'img')

    for img_index, img in enumerate(images):
        try:
            img_url = img.get_attribute('src')
            if img_url is None or img_url == '':
                print(f"跳过无src属性的图片 {img_index + index_offset}")
                continue

            response = requests.get(img_url)
            if response.status_code == 200:
                # 使用页面URL作为文件名的基础，并添加图片索引以确保唯一性
                page_name = sanitize_filename(page_url.replace('https://', '').replace('http://', ''))
                save_filename = f"{page_name}_image_{img_index + index_offset}.png"
                save_path = os.path.join(save_dir, save_filename)

                with open(save_path, 'wb') as file:
                    file.write(response.content)
                print(f"已保存: {save_path}")
            else:
                print(f"无法下载图片 {img_index + index_offset}, 状态码: {response.status_code}")
        except Exception as e:
            print(f"处理图片 {img_index + index_offset} 时出错: {e}")


try:
    driver.get('https://tsl.uad360.com/')
    time.sleep(5)  # 给页面加载留出时间

    current_url = driver.current_url
    # 获取初始页面的所有图片
    download_images_from_page(current_url)

    # 找到页面中的所有链接
    links = driver.find_elements(By.TAG_NAME, 'a')
    total_links = len(links)

    for link_index, link in enumerate(links):
        try:
            link_url = link.get_attribute('href')
            if link_url is None or link_url == '':
                print(f"跳过无效链接 {link_index}")
                continue

            # 打开新标签页
            driver.execute_script("window.open();")
            driver.switch_to.window(driver.window_handles[1])

            # 访问链接指向的页面
            driver.get(link_url)
            time.sleep(5)  # 给页面加载留出时间

            # 下载该页面的所有图片
            download_images_from_page(link_url, index_offset=(link_index + 1) * total_links)

            # 关闭当前标签页并切换回原始标签页
            driver.close()
            driver.switch_to.window(driver.window_handles[0])
        except Exception as e:
            print(f"处理链接 {link_index} 时出错: {e}")
finally:
    driver.quit()