Python实战使用Selenium爬取网页数据

pip install selenium

from selenium import webdriver
# 指定chromedriver.exe的路径
driver_path = r"C:\path\to\chromedriver.exe"
# 创建一个WebDriver实例，指定使用Chrome浏览器
driver = webdriver.Chrome(driver_path)
# 访问目标网站
driver.get("https://www.example.com")
# 获取网页标题
page_title = driver.title
print("Page Title:", page_title)
# 关闭浏览器
driver.quit()

from selenium import webdriver
from selenium.webdriver.common.keys import Keys

driver_path = r"C:\path\to\chromedriver.exe"
driver = webdriver.Chrome(driver_path)

driver.get("https://www.example.com/login")

# 定位用户名和密码输入框
username_input = driver.find_element_by_name("username")
password_input = driver.find_element_by_name("password")

# 输入用户名和密码
username_input.send_keys("your_username")
password_input.send_keys("your_password")

# 模拟点击登录按钮
login_button = driver.find_element_by_xpath("//button[@type='submit']")
login_button.click()

# 其他操作...

# 关闭浏览器
driver.quit()

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

driver_path = r"C:\path\to\chromedriver.exe"
driver = webdriver.Chrome(driver_path)

driver.get("https://www.example.com/dynamic-content")

# 等待指定元素出现，最多等待10秒
element = WebDriverWait(driver, 10).until(
    EC.presence_of_element_located((By.ID, "dynamic-element-id"))
)

# 操作该元素...

driver.quit()

from selenium import webdriver

driver_path = r"C:\path\to\chromedriver.exe"
driver = webdriver.Chrome(driver_path)

# 设置隐式等待时间为10秒
driver.implicitly_wait(10)

driver.get("https://www.example.com/dynamic-content")

# 尝试定位元素
element = driver.find_element_by_id("dynamic-element-id")

# 操作该元素...

driver.quit()