#现代网络爬虫中的模拟登录技术

import requests

# 推荐：传字典形式的 Cookie，清晰易维护
cookies = {
    "sessionid": "abc123def456...",
    "csrftoken": "xyz789..."
}

response = requests.get(
    "https://example.com/protected-page",
    cookies=cookies
)
print(response.status_code)  # 200 即为成功

import requests

# 正确做法：创建 Session 贯穿始终
session = requests.Session()
# GET 请求拿隐藏参数（Session 会自动保存服务器返回的 Cookie）
login_page = session.get("https://example.com/login")
# POST 提交登录（Session 会自动带上之前的 Cookie）
response = session.post("https://example.com/api/login", data={...})

from playwright.sync_api import sync_playwright

def github_login_playwright(username, password):
    with sync_playwright() as p:
        # 启动浏览器
        # headless=False 可以看到浏览器操作过程，方便调试
        # slow_mo=100 给每个操作加 100ms 延迟，模拟真人速度
        browser = p.chromium.launch(headless=False, slow_mo=100)
        page = browser.new_page(
            user_agent=(
                "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
                "AppleWebKit/537.36 (KHTML, like Gecko) "
                "Chrome/124.0.0.0 Safari/537.36"
            )
        )

        # 导航到登录页
        page.goto("https://github.com/login")

        # 填写表单 —— Playwright 会自动等待元素出现
        page.fill("#login_field", username)
        page.fill("#password", password)
        page.click("input[type='submit']")

        # 验证登录是否成功
        try:
            page.wait_for_selector(
                "button[aria-label='View profile and more']",
                timeout=10000
            )
            print("✅ 登录成功！")
            # 把 Cookie 保存下来，下次可以直接复用
            cookies = page.context.cookies()
            return cookies
        except Exception:
            print("❌ 登录失败！")
            return None
        finally:
            browser.close()

import requests
from bs4 import BeautifulSoup

def github_login_requests(username, password):
    # 必须使用 Session！
    session = requests.Session()
    session.headers.update({
        "User-Agent": (
            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
            "AppleWebKit/537.36 (KHTML, like Gecko) "
            "Chrome/124.0.0.0 Safari/537.36"
        ),
        "Referer": "https://github.com/"
    })

    try:
        # 第一步：访问登录页，获取 CSRF Token
        login_page = session.get(
            "https://github.com/login",
            timeout=10
        )
        login_page.raise_for_status()
        soup = BeautifulSoup(login_page.text, "html.parser")

        # GitHub 的 CSRF Token 字段叫 authenticity_token
        token_input = soup.find("input", {"name": "authenticity_token"})
        if not token_input:
            raise ValueError("未找到 authenticity_token，页面结构可能已变更")
        authenticity_token = token_input["value"]

        # 第二步：构造登录数据并提交
        login_data = {
            "commit": "Sign in",
            "authenticity_token": authenticity_token,
            "login": username,
            "password": password,
            "trusted_device": "",
            "webauthn-support": "supported",
        }

        response = session.post(
            "https://github.com/session",
            data=login_data,
            timeout=10,
            allow_redirects=True
        )
        response.raise_for_status()

        # 第三步：验证登录结果
        if "Sign out" in response.text:
            print("✅ 登录成功！")
            return session
        else:
            print("❌ 登录失败！请检查账号密码，或确认是否需要二步验证。")
            return None

    except requests.RequestException as e:
        print(f"❌ 网络请求出错：{e}")
        return None
    except Exception as e:
        print(f"❌ 发生未知错误：{e}")
        return None

# 实战中的常见做法示例
import time
import random
from fake_useragent import UserAgent

# 随机 User-Agent
ua = UserAgent()
headers = {
    "User-Agent": ua.random,
    "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
    "Referer": "https://previous-page.com/",
}

# 每次请求前随机等待 1~3 秒
time.sleep(random.uniform(1, 3))