如何检测页面上的验证码类型并识别它（Python）

py -m venv .venv
.\.venv\Scripts\python.exe -m pip install capskip requests

import base64, html as htmllib, re, time
from types import SimpleNamespace as NS
from urllib.parse import urljoin
import requests

SITEKEY_JS = r"sitekey['\"]?\s*:\s*['\"]([^'\"]+)"   # sitekey: '...' inside a render() call


def grab(pattern, text):  # first capture group that matched, or None
    m = re.search(pattern, text or "", re.I | re.S)
    return next(g for g in m.groups() if g is not None) if m else None

def tag(cls, h):  # opening tag with CSS class cls (and not g-recaptcha-response)
    pat = r'(<\w+[^>]*\sclass\s*=\s*["\'][^"\']*(?<![\w-])%s(?![\w-])[^"\']*["\'][^>]*>)'
    return grab(pat % cls, h)

def attr(t, name):  # attribute value from a tag string, either quote style, HTML-unescaped
    v = grab(r'\s%s\s*=\s*(?:"([^"]*)"|\'([^\']*)\')' % name, t)
    return None if v is None else htmllib.unescape(v)

def render_opts(call, js):  # first 400 characters of the options in call(el, {...})
    return grab(call + r"\([^,]+,\s*\{(.{0,400})", js)

def parse(html, url):
    h = re.sub(r"<!--.*?-->|<style\b.*?</style>", "", html, flags=re.S | re.I)
    srcs = " ".join(re.findall(r'<script\b[^>]*?\ssrc\s*=\s*["\']([^"\']+)', h, re.I))
    js = "\n".join(re.findall(r"<script\b[^>]*>(.*?)</script>", h, re.S | re.I))
    return NS(h=h, srcs=htmllib.unescape(srcs), js=js, url=url)

def hit(kind, method, **args):
    return {"type": kind, "method": method, "args": args}

def browser(kind, method, p, why):  # the static HTML is not enough, so do not guess
    return {"type": kind, "method": method, "args": {"url": p.url}, "needs_browser": why}

UNSUPPORTED = {"arkose": r"arkoselabs\.com/v2/|funcaptcha\.com/fc/", "geetest_v4": r"gt4\.js|initGeetest4"}

def unsupported(p):  # CapSkip cannot solve these: say so instead of misleading the reader
    for kind, pat in UNSUPPORTED.items():
        if re.search(pat, p.srcs + " " + p.js):
            return {"type": kind, "method": None, "args": {}, "unsupported": True}

def cf_challenge(p):  # the full-page "Just a moment..." interstitial, not a widget
    if re.search(r"_cf_chl_opt\s*=\s*\{", p.js):
        why = "data and pagedata (Cloudflare calls them cData and chlPageData) only exist at run time"
        return browser("turnstile_challenge", "turnstile", p, why)

def hcaptcha(p):  # before reCAPTCHA: a site that moved to hCaptcha may keep the g-recaptcha class
    if not re.search(r"hcaptcha\.com/1/api\.js", p.srcs + " " + p.js):
        return None
    if re.search(r"\.setData\s*\(|rqdata", p.js):  # Enterprise rqdata is issued per challenge
        return browser("hcaptcha_enterprise", "hcaptcha", p, "rqdata is issued for one challenge at run time")
    w = tag("h-captcha", p.h) or tag("g-recaptcha", p.h)
    key = attr(w, "data-sitekey") or grab(SITEKEY_JS, render_opts(r"hcaptcha\.render", p.js))
    if not key:
        return browser("hcaptcha", "hcaptcha", p, "no sitekey in the static HTML")
    args = {"sitekey": key, "url": p.url}
    if attr(w, "data-size") == "invisible":
        args["invisible"] = 1
    return hit("hcaptcha", "hcaptcha", **args)

def recaptcha(p):  # Enterprise flag first, then v3 (render=KEY), then v2
    m = re.search(r"/recaptcha/(api|enterprise)\.js(\?\S*)?", p.srcs)
    if not m:
        return None
    ent = {"enterprise": 1} if m.group(1) == "enterprise" else {}
    render = grab(r"[?&]render=([^&\s]+)", m.group(2))  # a v3 sitekey, or "explicit" (a v2 page)
    t, o = tag("g-recaptcha", p.h), render_opts(r"\.render", p.js)
    button, action = (t or "").lower().startswith("<button"), attr(t, "data-action")
    v3 = bool(render and render != "explicit") or bool(button and action)
    key = render if render != "explicit" else None
    key = key or attr(t, "data-sitekey") or grab(SITEKEY_JS, o)
    if not key:
        return browser("recaptcha", "recaptcha", p, "no sitekey in the static HTML (set by JavaScript)")
    small = attr(t, "data-size") == "invisible" or grab(r"size['\"]?\s*:\s*['\"](invisible)", o)
    invisible = not v3 and bool(button or small)
    action = action or grab(r"execute\(\s*[^,)]+,\s*\{\s*['\"]?action['\"]?\s*:\s*['\"]([^'\"]+)", p.js)
    args = {"sitekey": key, "url": p.url, **ent}
    if v3:
        args.update(version="v3", **({"action": action} if action else {}))
    if invisible:
        args["invisible"] = 1
    kind = "recaptcha_" + ("v3" if v3 else "v2_invisible" if invisible else "v2")
    return hit(kind + ("_enterprise" if ent else ""), "recaptcha", **args)

def turnstile(p):  # widget only: implicit (div.cf-turnstile) or explicit (turnstile.render)
    if "challenges.cloudflare.com/turnstile/v0/api.js" not in p.srcs:
        return None
    t, o = tag("cf-turnstile", p.h), render_opts(r"turnstile\.render", p.js)
    key = attr(t, "data-sitekey") or grab(SITEKEY_JS, o)
    if not key:
        return browser("turnstile", "turnstile", p, "no sitekey in the static HTML")
    action = attr(t, "data-action") or grab(r"\baction['\"]?\s*:\s*['\"]([^'\"]+)", o)
    cdata = attr(t, "data-cdata") or grab(r"\bcData['\"]?\s*:\s*['\"]([^'\"]+)", o)
    extra = {k: v for k, v in (("action", action), ("data", cdata)) if v}
    return hit("turnstile", "turnstile", sitekey=key, url=p.url, **extra)

def geetest(p):  # v3 only: gt is static, challenge comes from the register endpoint
    if not (re.search(r"initGeetest\s*\(", p.js) or re.search(r"/gt(\.[\d.]+)?\.js", p.srcs)):
        return None
    gt = grab(r"\bgt['\"]?\s*:\s*['\"]([0-9a-f]{32})", p.js)
    challenge = grab(r"\bchallenge['\"]?\s*:\s*['\"]([0-9a-f]{32,34})", p.js)
    if not (gt and challenge):
        return browser("geetest", "geetest", p, "gt and challenge come from the register endpoint")
    return hit("geetest", "geetest", gt=gt, challenge=challenge, url=p.url)

def altcha(p):  # challengeurl / challengejson (v1, v2) or challenge (v3+)
    t = grab(r"(<altcha-widget\b[^>]*>)", p.h)
    if not t:
        return None
    c = attr(t, "challenge")
    as_json = attr(t, "challengejson") or (c if (c or "").lstrip().startswith("{") else None)
    as_url = attr(t, "challengeurl") or (None if as_json else c)
    if as_json:
        return hit("altcha", "altcha", url=p.url, challenge_json=as_json)
    if as_url:
        return hit("altcha", "altcha", url=p.url, challenge_url=urljoin(p.url, as_url))
    return browser("altcha", "altcha", p, "no challenge attribute")

def capy(p):  # the widget script is .../puzzle/get_js/?k=PUZZLE_...
    m = re.search(r"((?:https?:)?//[^\s\"']+?)/puzzle/get_js/\S*?(PUZZLE_[\w-]+)", p.srcs)
    if m:
        host = m.group(1) if m.group(1).startswith("http") else "https:" + m.group(1)
        more = {} if host == "https://jp.api.capy.me" else {"api_server": host}
        return hit("capy", "capy", sitekey=m.group(2), url=p.url, **more)

MAM = "mampkg/@mamdev/core.frontend.libs.captchafox"

def captchafox(p):  # plain build from cdn.captchafox.com, or the bundled build from s.uicdn.com
    t, key = tag("captchafox", p.h), grab(r"captchafox[^\"']*/api\.js\?key=([^\"'&]+)", p.srcs)
    if t or key:
        more = {"api_server": "https://s.uicdn.com/" + MAM + "/"} if MAM in p.srcs else {}
        sitekey = attr(t, "data-sitekey") or key
        if not sitekey:
            return browser("captchafox", "captchafox", p, "no sitekey in the static HTML")
        return hit("captchafox", "captchafox", sitekey=sitekey, url=p.url, **more)

def friendly(p):  # v2 loads @friendlycaptcha/sdk (site.min.js), v1 loads friendly-challenge
    t = tag("frc-captcha", p.h)
    if not t:
        return None
    v2_end, v1_end = attr(t, "data-api-endpoint"), attr(t, "data-puzzle-endpoint")
    server = v2_end or v1_end
    v2 = v2_end is not None or re.search(r"friendlycaptcha/sdk|site(\.compat)?\.min\.js", p.srcs)
    v1 = v1_end is not None or re.search(r"friendly-challenge|widget(\.module)?\.min\.js", p.srcs)
    if bool(v2) == bool(v1):
        return browser("friendly_captcha", "friendly_captcha", p, "cannot tell v1 from v2 in the HTML")
    if not attr(t, "data-sitekey"):
        return browser("friendly_captcha", "friendly_captcha", p, "no sitekey in the static HTML")
    more = {"api_server": server} if server else {}
    return hit("friendly_captcha_" + ("v2" if v2 else "v1"), "friendly_captcha",
               sitekey=attr(t, "data-sitekey"), url=p.url, version="v2" if v2 else "v1", **more)

def image(p):  # a guess: an <img> that says captcha, next to a text box that says captcha
    box = r"<input\b(?![^>]*type\s*=\s*[\"']?(?:hidden|checkbox|submit))[^>]*(?:captcha|security.?code)"
    for img in re.findall(r"<img\b[^>]*>", p.h, re.I):
        if re.search(box, p.h, re.I) and re.search(r"captcha", img, re.I) and attr(img, "src"):
            return hit("image", "normal", image=urljoin(p.url, attr(img, "src")))

CHECKS = [unsupported, cf_challenge, hcaptcha, recaptcha, turnstile, geetest, altcha, capy, captchafox, friendly]

def detect_all(html, page_url):
    p = parse(html, page_url)
    return [r for r in (check(p) for check in CHECKS) if r] or [r for r in [image(p)] if r]

def detect(html, page_url):
    found = detect_all(html, page_url)
    if len(found) > 1:
        found[0]["also"] = [r["type"] for r in found[1:]]
    return found[0] if found else None

def solve_hcaptcha(args, api, key=None):  # no SDK call yet: post to in.php, poll res.php
    form = {"method": "hcaptcha", "sitekey": args["sitekey"], "pageurl": args["url"],
            "invisible": args.get("invisible", 0), "data": args.get("data"), "key": key, "json": 1}
    job = requests.post(api + "/in.php", data=form, timeout=30).json()
    if job["status"] != 1:
        raise RuntimeError(job["request"])
    for _ in range(36):  # a solve takes 10 to 30 seconds, so give up after 3 minutes
        time.sleep(5)
        q = {"key": key, "action": "get", "id": job["request"], "json": 1}
        r = requests.get(api + "/res.php", params=q, timeout=30).json()
        if r["request"] != "CAPCHA_NOT_READY":
            if r["status"] != 1:
                raise RuntimeError(r["request"])
            return {"code": r["request"], "userAgent": r.get("useragent")}
    raise TimeoutError("hCaptcha was not solved within 3 minutes")

def solve(info, solver, session=None, api="http://127.0.0.1:8080", key=None):
    if info.get("unsupported") or info.get("needs_browser"):
        raise RuntimeError(info.get("needs_browser") or info["type"] + " is not supported by CapSkip")
    args = dict(info["args"])
    if info["method"] == "hcaptcha":
        return solve_hcaptcha(args, api, key)
    if info["method"] == "normal":  # fetch the image with YOUR session so the cookie matches it
        src = args.pop("image")
        if not src.startswith("data:"):
            r = (session or requests).get(src, timeout=30)
            r.raise_for_status()
            src = "data:image/png;base64," + base64.b64encode(r.content).decode()
        args["file"] = src
    return getattr(solver, info["method"])(**args)

import requests
from capskip import CapSkip
from detect import detect, solve

URL = "https://example.com/login"   # a page of yours with a CAPTCHA
HOST, PORT = "127.0.0.1", 8080      # from CapSkip's connection settings
session = requests.Session()
html = session.get(URL, timeout=30).text

info = detect(html, URL)
print(info)

if info and info["method"] and not info.get("needs_browser"):
    solver = CapSkip(host=HOST, port=PORT)
    result = solve(info, solver, session, api=f"http://{HOST}:{PORT}")
    print(result)

(() => {
  const iframes = [...document.querySelectorAll('iframe')].map((f) => f.src);
  const urls = performance.getEntriesByType('resource').map((r) => r.name).concat(iframes);
  const found = new Map(), add = (o) => found.set(JSON.stringify(o), o);
  for (const u of urls) {
    let m;
    if ((m = u.match(/recaptcha\/(?:api2|(enterprise))\/anchor\?.*?\bk=([\w-]+)/)))
      add({ type: 'recaptcha', sitekey: m[2], enterprise: !!m[1], invisible: /size=invisible/.test(u) });
    else if ((m = u.match(/recaptcha\/(?:api|enterprise)\.js\?.*?\brender=([\w-]+)/)) && m[1] !== 'explicit')
      add({ type: 'recaptcha v3', sitekey: m[1], enterprise: /enterprise\.js/.test(u) });
    else if ((m = u.match(/challenges\.cloudflare\.com\/.*turnstile\/.*\/(0x4[\w-]+|[123]x0+[A-Za-z]+)\//)))
      add({ type: 'turnstile', sitekey: m[1] });
    else if ((m = u.match(/hcaptcha\.com\/captcha\/.*[#&?]sitekey=([\w-]+)/))) add({ type: 'hcaptcha', sitekey: m[1] });
    else if (/arkoselabs\.com\/fc\//.test(u)) add({ type: 'arkose: CapSkip cannot solve' });
  }
  if (window._cf_chl_opt) add({ type: 'cloudflare challenge page' });
  document.querySelectorAll('altcha-widget').forEach((e) => add({ type: 'altcha', challenge: e.getAttribute('challenge') || e.getAttribute('challengeurl') }));
  document.querySelectorAll('.h-captcha[data-sitekey]').forEach((e) => add({ type: 'hcaptcha', sitekey: e.dataset.sitekey }));
  document.querySelectorAll('.frc-captcha, .captchafox').forEach((e) => add({ type: e.classList.contains('captchafox') ? 'captchafox' : 'frc-captcha', sitekey: e.dataset.sitekey }));
  const v3 = [...found.values()].filter((o) => o.type === 'recaptcha v3').map((o) => o.sitekey);  // a v3 badge also adds an invisible anchor frame
  const res = [...found.values()].filter((o) => !(o.type === 'recaptcha' && v3.includes(o.sitekey)));
  return res.length ? res : 'no known CAPTCHA found (GeeTest, Capy and CaptchaFox scripts are not checked)';
})();