Python爬虫模拟登录并跳过二次验证

import requests
from bs4 import BeautifulSoup
# 代理配置
proxyHost = "www.16yun.cn"
proxyPort = "5445"
proxyUser = "16QMSOML"
proxyPass = "280651"
# 代理格式：http://用户名:密码@代理地址:端口
proxyMeta = f"http://{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}"
proxies = {
    "http": proxyMeta,
    "https": proxyMeta,
}
# 目标网站的登录URL
login_url = "https://example.com/login"
# 登录表单数据
login_data = {
    "username": "your_username",
    "password": "your_password"
}
# 创建一个会话对象，用于保持Cookie
session = requests.Session()
# 发送POST请求，模拟登录（携带代理）
try:
    response = session.post(
        login_url,
        data=login_data,
        proxies=proxies,  # 设置代理
        timeout=10  # 设置超时时间（可选）
    )
    # 检查是否登录成功
    if response.status_code == 200:
        print("登录成功")
        # 打印返回的Cookie
        print("Cookies:", session.cookies.get_dict())
    else:
        print(f"登录失败，状态码: {response.status_code}")
except requests.exceptions.RequestException as e:
    print(f"请求异常: {e}")

import pytesseract
from PIL import Image
from io import BytesIO
# 获取验证码图片
captcha_url = "https://example.com/captcha"
captcha_response = session.get(captcha_url)
captcha_image = Image.open(BytesIO(captcha_response.content))
# 使用OCR识别验证码
captcha_text = pytesseract.image_to_string(captcha_image)
print("识别的验证码:", captcha_text)
# 将验证码添加到登录表单数据中
login_data["captcha"] = captcha_text
# 再次发送登录请求
response = session.post(login_url, data=login_data)
# 检查是否登录成功
if response.status_code == 200:
    print("登录成功")
else:
    print("登录失败")

# 获取登录页面的HTML
login_page_response = session.get("https://example.com/login")
soup = BeautifulSoup(login_page_response.text, "html.parser")
# 找到验证码问题
captcha_question = soup.find("div", {"class": "captcha-question"}).text
print("验证码问题:", captcha_question)
# 解析验证码问题并计算答案
# 假设问题是“1+2=？”
if "+" in captcha_question:
    num1, num2 = captcha_question.split("+")
    captcha_answer = int(num1.strip()) + int(num2.split("=")[0].strip())
else:
    num1, num2 = captcha_question.split("-")
    captcha_answer = int(num1.strip()) - int(num2.split("=")[0].strip())
print("验证码答案:", captcha_answer)
# 将验证码答案添加到登录表单数据中
login_data["captcha"] = captcha_answer
# 再次发送登录请求
response = session.post(login_url, data=login_data)
# 检查是否登录成功
if response.status_code == 200:
    print("登录成功")
else:
    print("登录失败")

# 假设目标网站的API接口是https://example.com/api/data
api_url = "https://example.com/api/data"
# 使用登录后的会话发送请求
response = session.get(api_url)
# 检查是否获取到数据
if response.status_code == 200:
    print("获取数据成功")
    print(response.json())
else:
    print("获取数据失败")

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
import time
# 启动Chrome浏览器
driver = webdriver.Chrome()
# 打开目标网站的登录页面
driver.get("https://example.com/login")
# 输入用户名和密码
username_input = driver.find_element(By.NAME, "username")
password_input = driver.find_element(By.NAME, "password")
username_input.send_keys("your_username")
password_input.send_keys("your_password")
# 模拟用户行为，例如滑动鼠标
time.sleep(2)
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
# 点击登录按钮
login_button = driver.find_element(By.NAME, "login")
login_button.click()
# 等待页面加载
time.sleep(5)
# 获取登录后的Cookie
cookies = driver.get_cookies()
print(cookies)
# 关闭浏览器
driver.quit()