使用selenium获取列表数据并展示；获取标题-图片-超链接数据

编程语言 2025-04-08 11:52:22 阅读次数: 0

代码：

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time

# 设置 Chrome 浏览器选项
chrome_options = Options()
chrome_options.add_argument("--start-maximized")  # 启动时最大化窗口

# 指定 ChromeDriver 路径
driver_path = r'D:\software\chromedriver\chromedriver127\chromedriver-win64\chromedriver.exe'


# 定义公共常量
BASE_URL = "http://www.***.com"
TARGET_XPATH = "/html/body/div[6]/ul[1]/li/font[1]/b"
SUCCESS_TEXT = "5"
NEW_PAGE_URL = "http://www.***.com/Home/Category/index/fClass/295.html"
LI_TARGET_XPATH = "//ul[@class='class_gdlist_frm']//li"


# 创建 Service 对象并传入 ChromeDriver 路径
service = Service(executable_path=driver_path)

# 启动浏览器并打开百度首页
driver = webdriver.Chrome(service=service, options=chrome_options)
driver.get(BASE_URL)



# 等待页面加载完成，假设等待某个元素加载完成
# 企查查已陪伴您1428天
WebDriverWait(driver, 600).until(
    EC.presence_of_element_located((By.XPATH, TARGET_XPATH))
)

# 获取目标元素
element = driver.find_element(By.XPATH, TARGET_XPATH)

# 获取并打印该元素的文本内容
element_text = element.text
if element_text == SUCCESS_TEXT:

    driver.get(NEW_PAGE_URL)  # 跳转到新页面


# 等待页面加载完成
time.sleep(2)  # 等待 2 秒以确保页面加载

# 查找所有商品的 li 项目
items = driver.find_elements(By.XPATH, LI_TARGET_XPATH)

# 遍历每个 li 项目，提取数据
for item in items:
    try:
        # 获取标题
        title_element = item.find_element(By.XPATH, ".//a[@title]")
        title = title_element.get_attribute("title")

        # 获取价格
        price_element = item.find_element(By.XPATH, ".//span//big")
        price = price_element.text

        # 获取图片链接
        image_element = item.find_element(By.XPATH, ".//img")
        image_url = image_element.get_attribute("src")

        # 获取商品详情链接
        detail_link_element = item.find_element(By.XPATH, ".//a[@title]")
        detail_link = detail_link_element.get_attribute("href")

        # 打印提取的数据
        print(f"标题: {title}")
        print(f"价格: {price}")
        print(f"图片: {image_url}")
        print(f"超链接: {detail_link}")
        print("-" * 50)  # 分隔符

    except Exception as e:
        print(f"Error occurred: {e}")


print("Element Text:", element_text)



# 等待一段时间，保持浏览器开启
input("Press Enter to close the browser...")

# 关闭浏览器
# driver.quit()

解释：