如何在 Python 中从 script 标签入手识别 Friendly Captcha

# pip install capskip requests
pip install "capskip>=1.3.0" requests

<!-- v2: the @friendlycaptcha/sdk package -->
<div class="frc-captcha" data-sitekey="YOUR_SITEKEY"></div>
<script type="module" src="https://cdn.jsdelivr.net/npm/@friendlycaptcha/sdk/site.min.js" async defer></script>
<script nomodule src="https://cdn.jsdelivr.net/npm/@friendlycaptcha/sdk/site.compat.min.js" async defer></script>

<!-- v1: the friendly-challenge package -->
<div class="frc-captcha" data-sitekey="YOUR_SITEKEY"></div>
<script type="module" src="https://cdn.jsdelivr.net/npm/friendly-challenge/widget.module.min.js" async defer></script>
<script nomodule src="https://cdn.jsdelivr.net/npm/friendly-challenge/widget.min.js" async defer></script>

# pip install capskip requests
from html.parser import HTMLParser
from urllib.parse import urljoin

import requests


class FriendlyPage(HTMLParser):
    """Collects the frc-captcha element and the page's script tags."""

    def __init__(self, page_url):
        super().__init__()
        self.page_url = page_url
        self.widget = {}
        self.scripts = []

    def handle_starttag(self, tag, attrs):
        a = dict(attrs)
        if "frc-captcha" in (a.get("class") or "").split():
            self.widget = a
        # Skip nomodule fallbacks; keep full addresses, never relative.
        if tag == "script" and a.get("src") and "nomodule" not in a:
            self.scripts.append(urljoin(self.page_url, a["src"]))


session = requests.Session()
page = FriendlyPage("https://example.com/signup")
page.feed(session.get(page.page_url, timeout=30).text)

from urllib.parse import urlparse

V2_FILES = {"site.min.js", "site.compat.min.js"}
V1_FILES = {"widget.module.min.js", "widget.min.js", "widget.polyfilled.min.js"}

def friendly_version(page):
    # Package names are unambiguous, so check them first.
    for src in page.scripts:
        if "@friendlycaptcha/sdk" in src:
            return "v2", src
        if "friendly-challenge" in src:
            return "v1", src
    # Self-hosted builds usually keep the file name. Themes ship their own
    # site.min.js too, so only trust a path that says friendly.
    for src in [s for s in page.scripts if "friendly" in s.lower()]:
        name = urlparse(src).path.rsplit("/", 1)[-1]
        if name in V2_FILES:
            return "v2", src
        if name in V1_FILES:
            return "v1", src
    # Last resort: v2 and v1 name their widget options differently.
    if {"data-api-endpoint", "data-form-field-name"} & page.widget.keys():
        return "v2", None
    if {"data-puzzle-endpoint", "data-solution-field-name"} & page.widget.keys():
        return "v1", None
    raise RuntimeError("v1 or v2? Read the page and set it by hand.")

from capskip import CapSkip

solver = CapSkip(host="127.0.0.1", port=8080)

version, script = friendly_version(page)
result = solver.friendly_captcha(
    page.widget["data-sitekey"],
    "https://example.com/signup",
    version=version,
    module_script=script,
    # data-api-endpoint="eu" (v2) or data-puzzle-endpoint (v1).
    api_server=page.widget.get("data-api-endpoint")
    or page.widget.get("data-puzzle-endpoint"),
)

print(result["token"][:40])   # v2 tokens start with AQQA.

import requests

# A renamed field wins; otherwise the default for the version.
field = (
    page.widget.get("data-form-field-name")          # v2 rename
    or page.widget.get("data-solution-field-name")   # v1 rename
    or ("frc-captcha-response" if version == "v2" else "frc-captcha-solution")
)

# session is the requests.Session that fetched the page.
resp = session.post(
    "https://example.com/signup",
    data={"email": "YOUR_EMAIL", field: result["token"]},
    # Browsers send the page as Referer; some servers refuse a post without it.
    headers={"Referer": page.page_url},
    timeout=30,
)
print(resp.status_code)

import asyncio
from capskip import AsyncCapSkip

solver = AsyncCapSkip(host="127.0.0.1", port=8080)
limit = asyncio.Semaphore(10)   # match Friendly Captcha Max. Threads

async def solve(sitekey, url, version, script):
    async with limit:
        r = await solver.friendly_captcha(
            sitekey, url, version=version, module_script=script)
        return r["token"]

async def main(jobs):
    # jobs: (sitekey, url, version, script) tuples from Step 2
    return await asyncio.gather(*(solve(*j) for j in jobs))

# pip install capskip requests
import os
from html.parser import HTMLParser
from urllib.parse import urljoin, urlparse

import requests
from capskip import CapSkip
from capskip.exceptions import CapSkipError, ValidationException

PAGE_URL = "https://example.com/signup"
V2_FILES = {"site.min.js", "site.compat.min.js"}
V1_FILES = {"widget.module.min.js", "widget.min.js", "widget.polyfilled.min.js"}


class FriendlyPage(HTMLParser):
    def __init__(self, page_url):
        super().__init__()
        self.page_url, self.widget, self.scripts = page_url, {}, []

    def handle_starttag(self, tag, attrs):
        a = dict(attrs)
        if "frc-captcha" in (a.get("class") or "").split():
            self.widget = a
        if tag == "script" and a.get("src") and "nomodule" not in a:
            self.scripts.append(urljoin(self.page_url, a["src"]))


def friendly_version(page):
    for src in page.scripts:
        if "@friendlycaptcha/sdk" in src:
            return "v2", src
        if "friendly-challenge" in src:
            return "v1", src
    for src in [s for s in page.scripts if "friendly" in s.lower()]:
        name = urlparse(src).path.rsplit("/", 1)[-1]
        if name in V2_FILES or name in V1_FILES:
            return ("v2" if name in V2_FILES else "v1"), src
    keys = page.widget.keys()
    if {"data-api-endpoint", "data-form-field-name"} & keys:
        return "v2", None
    if {"data-puzzle-endpoint", "data-solution-field-name"} & keys:
        return "v1", None
    raise SystemExit("v1 or v2? Read the page and set it by hand.")


solver = CapSkip(
    apiKey=os.getenv("CAPSKIP_API_KEY", "capskip"),
    host=os.getenv("CAPSKIP_HOST", "127.0.0.1"),
    port=int(os.getenv("CAPSKIP_PORT", "8080")),
)
session = requests.Session()

page = FriendlyPage(PAGE_URL)
page.feed(session.get(PAGE_URL, timeout=30).text)
if not page.widget.get("data-sitekey"):
    raise SystemExit("No frc-captcha widget in the HTML; it may be built by JS.")

version, script = friendly_version(page)
try:
    result = solver.friendly_captcha(
        page.widget["data-sitekey"], PAGE_URL,
        version=version, module_script=script,
        api_server=page.widget.get("data-api-endpoint")
        or page.widget.get("data-puzzle-endpoint"),
    )
except ValidationException as exc:
    raise SystemExit(f"not sent: {exc}")
except CapSkipError as exc:
    raise SystemExit(f"solve failed: {exc!r}")

field = (page.widget.get("data-form-field-name")
         or page.widget.get("data-solution-field-name")
         or ("frc-captcha-response" if version == "v2" else "frc-captcha-solution"))

# Post wherever the form's action points, with its other fields.
# Browsers send the page as Referer; some servers refuse a post without it.
resp = session.post(PAGE_URL, data={"email": "YOUR_EMAIL", field: result["token"]},
                    headers={"Referer": PAGE_URL}, timeout=30)
print(resp.status_code, version, field)