在当今数据驱动的时代，网络爬虫已成为获取互联网信息的重要手段。然而，许多网站如12306都实施了严格的反爬虫机制，特别是对于动态加载的内容。本文将详细介绍如何使用Selenium模拟真实浏览器行为，有效绕过这些限制，成功抓取12306旅游产品数据。
12306反爬机制分析
12306作为中国铁路官方售票平台，对其旅游产品数据实施了多层次防护：
动态内容加载：大量使用JavaScript异步加载数据，传统爬虫无法获取
验证码系统：复杂图片验证码和滑动验证码阻止自动化访问
请求头检测：验证User-Agent、Referer等头部信息
行为分析：检测鼠标移动、点击模式等人类特征
IP限制：频繁请求会导致IP地址被暂时封锁
Selenium技术简介
Selenium是一个自动化Web测试工具，但其浏览器自动化能力使其成为应对反爬策略的利器：
真实浏览器环境：完全模拟用户操作，生成合法流量模式
JavaScript执行：能够处理动态加载内容
元素交互：可以模拟点击、输入等用户行为
跨平台支持：支持Chrome、Firefox、Edge等主流浏览器
环境准备与配置
所需工具和库安装
首先确保安装以下Python库：
bash
pip install selenium beautifulsoup4 pandas webdriver-manager
WebDriver管理
Selenium需要对应浏览器的驱动程序。推荐使用webdriver-manager自动管理驱动：
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.chrome.options import Options
def setup_driver():
chrome_options = Options()
chrome_options.add_argument('--no-sandbox')
chrome_options.add_argument('--disable-dev-shm-usage')
chrome_options.add_argument('--disable-blink-features=AutomationControlled')
chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"])
chrome_options.add_experimental_option('useAutomationExtension', False)
chrome_options.add_argument('--start-maximized') # 最大化窗口
# 使用webdriver-manager自动下载和管理ChromeDriver
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service, options=chrome_options)
# 执行CDP命令隐藏WebDriver特征
driver.execute_script("Object.defineProperty(navigator, 'webdriver', {get: () => undefined})")
driver.execute_cdp_cmd('Page.addScriptToEvaluateOnNewDocument', {
'source': '''
Object.defineProperty(navigator, 'webdriver', {
get: () => undefined
})
'''
})
return driver爬虫设计与实现
页面分析与等待策略
12306旅游产品页面()采用动态加载方式，需要合理设置等待时间：
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
def wait_for_element(driver, by, value, timeout=10):
"""等待元素出现"""
try:
element = WebDriverWait(driver, timeout).until(
EC.presence_of_element_located((by, value))
)
return element
except Exception as e:
print(f"元素加载超时: {value}")
return None
def slow_scroll(driver, scroll_pause_time=0.5):
"""模拟人类缓慢滚动页面"""
last_height = driver.execute_script("return document.body.scrollHeight")
while True:
# 随机滚动距离，模拟人类行为
scroll_height = random.randint(300, 800)
driver.execute_script(f"window.scrollBy(0, {scroll_height});")
time.sleep(scroll_pause_time)
new_height = driver.execute_script("return document.body.scrollHeight")
if new_height == last_height:
break
last_height = new_height处理验证码挑战
当遇到验证码时，我们需要人工干预或使用OCR服务：
def handle_verification(driver):
"""处理验证码挑战"""
try:
# 检查是否有验证码出现
captcha_element = wait_for_element(driver, By.ID, "code", timeout=5)
if captcha_element:
print("验证码出现，请手动解决...")
# 暂停程序，等待用户手动处理验证码
input("解决验证码后按回车键继续...")
return True
except:
pass
return False数据提取实现
提取旅游产品信息的完整实现：
from bs4 import BeautifulSoup
import pandas as pd
import re
def extract_tour_products(driver):
"""提取旅游产品信息"""
# 等待产品列表加载
wait_for_element(driver, By.CLASS_NAME, "product-list", timeout=15)
# 缓慢滚动加载所有内容
slow_scroll(driver)
# 获取页面源码并使用BeautifulSoup解析
page_source = driver.page_source
soup = BeautifulSoup(page_source, 'html.parser')
products = []
product_items = soup.find_all('div', class_='product-item')
for item in product_items:
try:
# 提取产品名称
name_elem = item.find('div', class_='product-name')
name = name_elem.text.strip() if name_elem else "未知产品"
# 提取价格信息
price_elem = item.find('div', class_='product-price')
price_text = price_elem.text.strip() if price_elem else "0"
price = re.search(r'(\\d+)', price_text.replace(',', ''))
price = int(price.group(1)) if price else 0
# 提取出发地/目的地
route_elem = item.find('div', class_='product-route')
route = route_elem.text.strip() if route_elem else ""
# 提取产品详情链接
link_elem = item.find('a', href=True)
link = "https://kyfw.12306.cn" + link_elem['href'] if link_elem else ""
# 提取产品图片
img_elem = item.find('img', src=True)
img_url = img_elem['src'] if img_elem else ""
products.append({
'name': name,
'price': price,
'route': route,
'link': link,
'image_url': img_url,
'crawled_time': pd.Timestamp.now()
})
except Exception as e:
print(f"提取产品信息时出错: {e}")
continue
return products完整爬虫流程
整合以上功能的完整实现：
import random
import json
from datetime import datetime
import time
import pandas as pd
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from bs4 import BeautifulSoup
import re
# 代理信息
proxyHost = "www.16yun.cn"
proxyPort = "5445"
proxyUser = "16QMSOML"
proxyPass = "280651"
def get_proxy_url():
"""生成带认证的代理URL"""
return f"http://{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}"
def setup_driver():
"""设置带代理的浏览器实例"""
chrome_options = Options()
# 添加代理服务器配置（带认证）
proxy_url = get_proxy_url()
chrome_options.add_argument(f'--proxy-server={proxy_url}')
# 其他配置
chrome_options.add_argument('--no-sandbox')
chrome_options.add_argument('--disable-dev-shm-usage')
chrome_options.add_argument('--disable-blink-features=AutomationControlled')
chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"])
chrome_options.add_experimental_option('useAutomationExtension', False)
chrome_options.add_argument('--start-maximized')
# 使用webdriver-manager自动下载和管理ChromeDriver
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service, options=chrome_options)
# 执行CDP命令隐藏WebDriver特征
driver.execute_script("Object.defineProperty(navigator, 'webdriver', {get: () => undefined})")
driver.execute_cdp_cmd('Page.addScriptToEvaluateOnNewDocument', {
'source': '''
Object.defineProperty(navigator, 'webdriver', {
get: () => undefined
})
'''
})
return driver
def wait_for_element(driver, by, value, timeout=10):
"""等待元素出现"""
try:
element = WebDriverWait(driver, timeout).until(
EC.presence_of_element_located((by, value))
)
return element
except Exception as e:
print(f"元素加载超时: {value}")
return None
def slow_scroll(driver, scroll_pause_time=0.5):
"""模拟人类缓慢滚动页面"""
last_height = driver.execute_script("return document.body.scrollHeight")
while True:
# 随机滚动距离，模拟人类行为
scroll_height = random.randint(300, 800)
driver.execute_script(f"window.scrollBy(0, {scroll_height});")
time.sleep(scroll_pause_time)
new_height = driver.execute_script("return document.body.scrollHeight")
if new_height == last_height:
break
last_height = new_height
def handle_verification(driver):
"""处理验证码挑战"""
try:
# 检查是否有验证码出现
captcha_element = wait_for_element(driver, By.ID, "code", timeout=5)
if captcha_element:
print("验证码出现，请手动解决...")
# 暂停程序，等待用户手动处理验证码
input("解决验证码后按回车键继续...")
return True
except:
pass
return False
def extract_tour_products(driver):
"""提取旅游产品信息"""
# 等待产品列表加载
wait_for_element(driver, By.CLASS_NAME, "product-list", timeout=15)
# 缓慢滚动加载所有内容
slow_scroll(driver)
# 获取页面源码并使用BeautifulSoup解析
page_source = driver.page_source
soup = BeautifulSoup(page_source, 'html.parser')
products = []
product_items = soup.find_all('div', class_='product-item')
for item in product_items:
try:
# 提取产品名称
name_elem = item.find('div', class_='product-name')
name = name_elem.text.strip() if name_elem else "未知产品"
# 提取价格信息
price_elem = item.find('div', class_='product-price')
price_text = price_elem.text.strip() if price_elem else "0"
price = re.search(r'(\\d+)', price_text.replace(',', ''))
price = int(price.group(1)) if price else 0
# 提取出发地/目的地
route_elem = item.find('div', class_='product-route')
route = route_elem.text.strip() if route_elem else ""
# 提取产品详情链接
link_elem = item.find('a', href=True)
link = "https://kyfw.12306.cn" + link_elem['href'] if link_elem else ""
# 提取产品图片
img_elem = item.find('img', src=True)
img_url = img_elem['src'] if img_elem else ""
products.append({
'name': name,
'price': price,
'route': route,
'link': link,
'image_url': img_url,
'crawled_time': pd.Timestamp.now()
})
except Exception as e:
print(f"提取产品信息时出错: {e}")
continue
return products
def crawl_12306_tours():
"""爬取12306旅游产品的完整流程"""
print("启动浏览器（使用代理服务器）...")
print(f"代理服务器: {proxyHost}:{proxyPort}")
driver = setup_driver()
try:
# 访问12306旅游产品页面
print("访问12306旅游产品页面...")
driver.get("https://kyfw.12306.cn/otn/product/index.html")
# 等待页面加载
time.sleep(3)
# 检查并处理验证码
if handle_verification(driver):
# 验证码处理后重新等待页面加载
time.sleep(3)
# 提取产品信息
print("正在提取旅游产品信息...")
products = extract_tour_products(driver)
# 保存数据
if products:
df = pd.DataFrame(products)
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
filename = f"12306_tours_{timestamp}.csv"
df.to_csv(filename, index=False, encoding='utf-8-sig')
print(f"成功提取 {len(products)} 个旅游产品，已保存到 {filename}")
# 同时保存JSON格式
json_filename = f"12306_tours_{timestamp}.json"
with open(json_filename, 'w', encoding='utf-8') as f:
json.dump(products, f, ensure_ascii=False, indent=2)
print(f"JSON数据已保存到 {json_filename}")
else:
print("未找到旅游产品信息")
return products
except Exception as e:
print(f"爬取过程中发生错误: {e}")
return []
finally:
# 关闭浏览器
driver.quit()
print("浏览器已关闭")
# 执行爬虫
if __name__ == "__main__":
crawl_12306_tours()道德与法律考量
在使用Selenium爬取12306数据时，必须注意以下道德和法律问题：
遵守robots.txt：检查目标网站的爬虫政策
控制请求频率：避免对服务器造成过大压力
数据使用限制：仅将数据用于个人学习和研究目的
用户隐私保护：不收集、存储或分享任何用户个人信息
版权尊重：遵守12306网站上内容的版权声明
待会儿见
K哥馆
mayun
文鼎_应老师
课课家运营团队
liangchsh
启程软考
