#现代 Web 爬虫技术：Session + Cookie 认证的模拟登录

import requests
from bs4 import BeautifulSoup

LOGIN_URL = "https://login2.scrape.center/login"
INDEX_URL = "https://login2.scrape.center/"
USERNAME = "admin"
PASSWORD = "admin"

# 1. 发送登录请求，禁止自动重定向（否则拿不到 Set-Cookie 响应）
login_resp = requests.post(
    LOGIN_URL,
    data={"username": USERNAME, "password": PASSWORD},
    allow_redirects=False
)

# 2. 手动提取 Cookie
cookies = login_resp.cookies

# 3. 再用这些 Cookie 去请求首页
index_resp = requests.get(INDEX_URL, cookies=cookies)

# 验证登录是否成功
soup = BeautifulSoup(index_resp.text, "html.parser")
print(soup.find("h2", class_="mb-3"))  # 正常应输出：<h2>欢迎回来，admin</h2>

import requests
from bs4 import BeautifulSoup

LOGIN_URL = "https://login2.scrape.center/login"
INDEX_URL = "https://login2.scrape.center/"
USERNAME = "admin"
PASSWORD = "admin"

# 1. 创建一个持久会话
session = requests.Session()

# 2. 为整个会话设置一个通用的 User-Agent（避免底层默认 UA）
session.headers.update({
    "User-Agent": (
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
        "AppleWebKit/537.36 (KHTML, like Gecko) "
        "Chrome/128.0.0.0 Safari/537.36"
    )
})

# 3. 用 Session 发送 POST 请求（不需要禁止重定向，Session 会自动处理）
login_resp = session.post(
    LOGIN_URL,
    data={"username": USERNAME, "password": PASSWORD}
)
print("登录后首页状态码：", login_resp.status_code)  # 正常为 200

# 4. 继续使用同一个 Session 请求首页（Cookie 自动携带）
index_resp = session.get(INDEX_URL)
soup = BeautifulSoup(index_resp.text, "html.parser")
print(soup.find("h2", class_="mb-3"))

import time
import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from webdriver_manager.chrome import ChromeDriverManager

LOGIN_URL = "https://login2.scrape.center/login"
INDEX_URL = "https://login2.scrape.center/"
USERNAME = "admin"
PASSWORD = "admin"

# ========== 第一步：Selenium 登录并导出 Cookie ==========
driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()))
driver.maximize_window()

try:
    driver.get(LOGIN_URL)
    time.sleep(1)  # 等待页面完全加载

    # 模拟输入与点击
    driver.find_element(By.CSS_SELECTOR, 'input[name="username"]').send_keys(USERNAME)
    driver.find_element(By.CSS_SELECTOR, 'input[name="password"]').send_keys(PASSWORD)
    driver.find_element(By.CSS_SELECTOR, 'button[type="submit"]').click()
    time.sleep(2)  # 等待跳转完成

    if driver.current_url == INDEX_URL:
        print("Selenium 模拟登录成功！")
        selenium_cookies = driver.get_cookies()
    else:
        print("Selenium 模拟登录失败！")
        selenium_cookies = []
finally:
    driver.quit()

# ========== 第二步：将 Cookie 倒入 Requests Session ==========
if selenium_cookies:
    session = requests.Session()
    session.headers.update({
        "User-Agent": (
            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
            "AppleWebKit/537.36 (KHTML, like Gecko) "
            "Chrome/128.0.0.0 Safari/537.36"
        )
    })

    # 逐个注入 Cookie
    for cookie in selenium_cookies:
        session.cookies.set(
            name=cookie["name"],
            value=cookie["value"],
            domain=cookie.get("domain", ""),
            path=cookie.get("path", "/")
        )

    # 验证 + 抓取首页前 3 个电影标题
    index_resp = session.get(INDEX_URL)
    soup = BeautifulSoup(index_resp.text, "html.parser")
    print("首页前 3 个电影：")
    for i, movie in enumerate(soup.find_all("h5", class_="card-title"), 1):
        print(f"{i}. {movie.text.strip()}")