h-point / hcaptcha_solver.py
zhou12189108's picture
Upload 4 files
49afc47
raw
history blame
No virus
4.65 kB
from pathlib import Path
import os
from loguru import logger
import get_all_model
from playwright.async_api import BrowserContext as ASyncContext, async_playwright
import hcaptcha_challenger as solver
from hcaptcha_challenger.agents import AgentT, Malenia
get_all_model.download_all()
# Init local-side of the ModelHub
solver.install(upgrade=True)
# Save dataset to current working directory
tmp_dir = Path(__file__).parent.joinpath("tmp_dir")
@logger.catch
async def hit_challenge(context: ASyncContext, host, sitekey, user_data_dir, times: int = 8):
await context.route('**/*', lambda route, request: route_continuation(route, request, host, sitekey))
page = context.pages[0]
agent = AgentT.from_page(page=page, tmp_dir=tmp_dir)
await page.goto(f"https://{host}")
await agent.handle_checkbox()
for pth in range(1, times):
result = await agent()
print(f">> {pth} - Challenge Result: {result}")
match result:
case agent.status.CHALLENGE_BACKCALL:
await page.wait_for_timeout(500)
fl = page.frame_locator(agent.HOOK_CHALLENGE)
await fl.locator("//div[@class='refresh button']").click()
case agent.status.CHALLENGE_SUCCESS:
rqdata = agent.cr.__dict__
print(os.system(f"rm -rf {tmp_dir}"))
print(os.system(f"rm -rf {user_data_dir}"))
return rqdata["generated_pass_UUID"]
async def route_continuation(route, request, host, sitekey):
# 检查请求的URL,只拦截特定网站的请求
if request.url == f"https://{host}/":
print("start to solve")
# 修改DNS解析结果
await route.fulfill(status=200,
body="""
<!DOCTYPE html>
<html lang="en">
<head>
<title>hCAPTCHA 演示</title>
<meta http-equiv="X-UA-Compatible" content="IE=edge">
<meta name="viewport" content="width=device-width, user-scalable=yes">
<script src="https://js.hcaptcha.com/1/api.js" type="text/javascript" async defer></script>
</head>
<body>
<br><br>
<div class="sample-form">
<form id="hcaptcha-demo-form" method="POST">
<div id="hcaptcha-demo" class="h-captcha" data-sitekey="%%%%%%%%%%%" data-callback="onSuccess" data-expired-callback="onExpire"></div>
<script>
// success callback
var onSuccess = function(response) {
var errorDivs = document.getElementsByClassName("hcaptcha-error");
if (errorDivs.length) {
errorDivs[0].className = "";
}
var errorMsgs = document.getElementsByClassName("hcaptcha-error-message");
if (errorMsgs.length) {
errorMsgs[0].parentNode.removeChild(errorMsgs[0]);
}
var logEl = document.querySelector(".hcaptcha-success");
logEl.innerHTML = "挑战成功!"
};
var onExpire = function(response) {
var logEl = document.querySelector(".hcaptcha-success");
logEl.innerHTML = "令牌已过期。"
};
</script>
<div class="hcaptcha-success smsg" aria-live="polite"></div>
</body>
<script type="text/javascript">
// beacon example
function addEventHandler(object,szEvent,cbCallback){
if(!!object.addEventListener){ // for modern browsers or IE9+
return object.addEventListener(szEvent,cbCallback);
}
if(!!object.attachEvent){ // for IE <=8
return object.attachEvent(szEvent,cbCallback);
}
};
// Ex: triggers pageview beacon
addEventHandler(window,'load',function(){b();});
// Ex: triggers event beacon without pageview
addEventHandler(window,'load',function(){b({"vt": "e", "ec": "test_cat", "ea": "test_action"});});
</script>
</html>
""".replace("%%%%%%%%%%%", sitekey))
else:
# 对于其他网站的请求,不做修改
await route.continue_()
async def bytedance(host, sitekey, user_data_dirs):
# playwright install firefox --with-deps
async with async_playwright() as p:
context = await p.firefox.launch_persistent_context(
user_data_dir=Path(__file__).parent.joinpath(user_data_dirs),
headless=True,
locale="en-US"
)
await Malenia.apply_stealth(context)
token = await hit_challenge(context, host, sitekey, Path(__file__).parent.joinpath(user_data_dirs))
return token