v2ex 摸鱼 刷dau脚本

v2ex_catch_fish.py

import os
import sys
import json
import argparse
from time import sleep
from random import randint, shuffle
from selenium import webdriver

site_url = "https://www.v2ex.com"
driver_dumpfile = 'cookie.txt'

try:
    target_score = int(sys.argv[1])
except IndexError:
    target_score = 2018


def dump_cookie(d: webdriver.Chrome, dumpfile):
    with open(dumpfile, 'w', encoding='utf8') as f:
        cookies = json.dumps(d.get_cookies(), indent=2)
        f.write(cookies)
        # f.write(d.get_cookies())


def load_cookie(d: webdriver.Chrome, dumpfile: str) -> webdriver.Chrome:
    with open(dumpfile, 'r', encoding='utf8') as f:
        cookies = json.loads(f.read())

    for cookie in cookies:
        # print(cookie)
        d.add_cookie(cookie)
    print("读取cookie完成")
    return d


def login(d: webdriver.Chrome, user, passwd, dumpfile) -> webdriver.Chrome:
    # d.get("https://www.v2ex.com")
    # sleep(3)
    d.get("https://www.v2ex.com/signin")
    # 输入账号和密码
    d.find_element_by_xpath('//*[@id="Main"]/div[2]/div[2]/form/table/tbody/tr[1]/td[2]/input').send_keys(user)
    d.find_element_by_xpath('//*[@id="Main"]/div[2]/div[2]/form/table/tbody/tr[2]/td[2]/input').send_keys(passwd)
    # 定位到验证码输入框
    d.find_element_by_xpath('//*[@id="Main"]/div[2]/div[2]/form/table/tbody/tr[3]/td[2]/input').click()
    print("在网页中输入验证码")

    # 10s内手动输入验证码，然后回车
    sleep(10)

    # 检查是否登录成功
    if user == d.find_element_by_xpath('//*[@id="Top"]/div/div/table/tbody/tr/td[3]/a[2]').text:
        print("login success")
        print(d.get_cookies())
        dump_cookie(d, dumpfile)

    else:
        print("login failed")
        exit(1)

    return d


def water(d: webdriver.Chrome, user, target):
    d.get(site_url)
    urls = d.find_elements_by_xpath('//*[@id="Main"]/div[2]/div/table/tbody/tr/td[3]/span[1]/a')
    # print(urls)
    urls = [item.get_attribute("href") for item in urls]
    print(urls)
    if len(urls) < 1:
        print("error")
        return "error"

    # 开始划水
    count = 0
    seed = randint(1, 4)  # 预生成一个seed
    while True:
        shuffle(urls)
        for url in urls:
            count += 1
            d.get(url)
            wait_time = randint(3, 15)
            print("第{}次刷新, 等待{}s".format(count, wait_time))
            sleep(wait_time)

            # 检查dau
            seed -= 1
            if not seed:
                order, current_dau = check_dau(d, user)
                print("当前活跃度排名 {}, 分数 {}".format(order, current_dau))
                sleep(randint(5, 9))
                seed = randint(4, 15)  # 更新seed
                if target - current_dau < 20:
                    print("积分接近 {}, 自动退出".format(target))
                    exit(0)

        if count > 1000:
            break
    return count


def check_dau(d: webdriver.Chrome, user):
    d.get('https://www.v2ex.com/member/{}'.format(user))
    order = d.find_element_by_xpath('//*[@id="Main"]/div[2]/div[1]/table/tbody/tr/td[3]/span[2]/a').text
    order = int(order)

    current_dau = 0
    if order < 11:
        # 位于前十
        d.get('https://www.v2ex.com/top/dau')
        dau_list = d.find_elements_by_xpath('//*[@id="Main"]/div[2]/div[2]/table/tbody/tr/td[3]/div')
        dau_list = [int(item.text) for item in dau_list]
        print(dau_list)
        current_dau = dau_list[order - 1]

    return order, current_dau


if __name__ == "__main__":
    username = "e"
    password = "A"
    # 如果文件不存在，则重新登录
    driver = webdriver.Chrome()
    driver.get(site_url)
    sleep(1)
    if os.path.isfile(driver_dumpfile) and os.path.getsize(driver_dumpfile):
        driver = load_cookie(d=driver, dumpfile=driver_dumpfile)
    else:
        driver = login(d=driver, user=username, passwd=password, dumpfile=driver_dumpfile)

    sleep(randint(1, 4))
    fish = water(d=driver, user=username, target=target_score)

0. 配置selenium和chrome webdriver,将chrome webdriver放置于当前目录，然后export PATH=$PATH:./

---

• if 本地运行：

1. 运行程序，打开登录页面之后会自动输入账号和密码，手动输入验证码，手动回车

• if 挂远程运行:

1. 本地运行程序,登录完成之后停掉程序，目录下面会生成一个cookie.txt， 将本程序和cookie.txt放到远程， 运行程序

---

2. 开始自动化摸鱼，该干啥干啥去，想起来的时候去刷一下dau看看自己的排名

脚本自动显示dau

• 验证码不好处理，可以本地人工输入验证码登录成功之后保存下来，放到远程运行

• 如果远程没有桌面环境，加一行headless关掉窗口

• 可以设定目标积分，快到达目标积分时停止脚本