Python Selenium动态渲染页面和抓取的使用指南

# 安装Selenium库
pip install selenium
 
# 下载浏览器驱动（以Chrome为例）
# 驱动版本需与浏览器版本严格www.chinasem.cn对应
# 下载地址：https://chromedriver.chromium.org/downloads

from selenium import webdriver
 
# 方式一：指定驱动路径
driver = webdriver.Chrome(executable_path='/path/to/chromedriver')
 
# 方式二：配置环境变量（推荐）
# 将chromedriver放入系统PATH路径
driver = webdriver.Chrome()

driver = webdriver.Chrome()
try:
    driver.get("https://example.com")  # 访问页面
    element = driver.find_element(By.ID, "search")  # 元素定位
    element.send_keys("Selenium")  # 输入文本
    element.submit()  # 提交表单
    print(driver.page_source)  # 获取渲染后源码
finally:
    driver.quit()  # 关闭浏览器

from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
 
# 显式等待：直到元素存在（最多等待10秒）
element = WebDriverWait(driver, 10).until(
    EC.presence_of_element_located((By.CSS_SELECTOR, ".dynamic-content"))
)
 
# 隐式等待：全局设置元素查找超时
driver.implicitly_wait(5)

# 滚动加载
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
 
# 鼠标悬停
from selenium.webdriver.common.action_chains import ActionChains
hover_element = driver.find_element(By.ID, "dropdown")
ActionChains(driver).move_to_element(hover_element).perform()
 
# 文件上传
file_input = driver.find_element(By.XPATH, "//input[@type='file']")
file_input.send_keys("/path/to/local/file.jpg")

# 代理配置
from selenium.webdriver.chrome.options import Options
 
chrome_options = Options()
chrome_options.add_argument('--proxy-server=http://user:pass@proxy.example.com:8080')
driver = webdriver.Chrome(options=chrome_options)
 
# 随机User-Agent
from fake_useragent import UserAgent
 
ua = UserAgent()
chrome_options.add_argument(f'user-agent={ua.random}')
 
# Cookies管理
driver.add_cookie({'name': 'session', 'value': 'abcChina编程123'})  # 设置Cookie
print(driver.get_cookies())  # 获取所有Cookies

from selenium import webdriver
from selenium.webdriver.common.by import By
import time
 
# 初始化配置
options = webdriver.ChromeOptions()
options.add_argument('--headless')  # 无头模式
options.add_argument('--disable-blink-features=AutomationControlled')  # 反爬规避
driver = webdriver.Chrome(options=options)
 
try:
    # 登录操作
    driver.get("https://www.example.com/login")
    driver.find_element(By.ID, "username").send_keys("your_user")
    driver.find_element(By.ID, "password").send_keys("your_pass")
    driver.find_element(By.ID, "login-btn").click()
    time.sleep(3)  # 等待登录跳转
 
    # 访问商品页
    driver.get("https://www.example.com/product/12345#reviews")
    
    # 滚动加载评论
    for _ in range(5):
        driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
        time.sleep(2)
    
    # 提取评论数据
    comments = driver.find_elements(By.CSS_SELECTOR, ".review-item")
    for idx, comment in enumerate(compythonments, 1):
        print(f"Comment {idx}:")
        print("User:", comment.find_element(By.CSS_SELECTOR, ".user").text)
        print("Content:", comment.find_element(By.CSS_SELECTOR, ".content").text)
        print("Rating:", comment.find_element(By.CSS_SELECTOR, ".rating").get_attribute('aria-label'))
        print("-" * 50)
 
finally:
    driver.quit()

# 复用浏览器实例（适用于多页面抓取）
def get_driver():
    if not hasattr(get_driver, 'instance'):
        get_driver.instance = webdriver.Chrome()
    return get_driver.instance
 
# 合理设置超时时间
driver.set_page_load_timeout(30)  # 页面加载超时
driver.set_script_timeout(10)  # 异步脚本执行超时

from selenium.common.exceptions import (
    NoSuchElementException,
    TimeoutException,
    StaleElementReferenceException
)
 
try:
    # 操作代码
except NoSuchElementException:
    print("元素未找到，可能页面结构变化")
except TimeoutException:
    print("页面加载超时，尝试重试")
except StaleElementReferenceException:
    print("元素已失效，需重新定位")