Cara Menyelesaikan Captchas Ketika Web Scraping dengan Scrapling dan CapSolver

pip install scrapling

pip install "scrapling[fetchers]"
scrapling install

pip install "scrapling[all]"
scrapling install

from scrapling import Fetcher

# Permintaan GET
response = Fetcher.get("https://example.com")

# Permintaan POST dengan data
response = Fetcher.post("https://example.com/api", data={"key": "value"})

# Akses respons
print(response.status)       # Kode status HTTP
print(response.body)         # Byte mentah
print(response.body.decode()) # Teks yang didekripsi

import requests
import time

CAPSOLVER_API_KEY = "YOUR_API_KEY"

def solve_captcha(task_type, website_url, website_key, **kwargs):
    """
    Solver captcha umum menggunakan API CapSolver.

    Args:
        task_type: Jenis tugas captcha (misalnya, "ReCaptchaV2TaskProxyLess")
        website_url: URL halaman dengan captcha
        website_key: Kunci situs untuk captcha
        **kwargs: Parameter tambahan yang spesifik untuk jenis captcha

    Returns:
        dict: Solusi yang mencakup token dan data lainnya
    """
    payload = {
        "clientKey": CAPSOLVER_API_KEY,
        "task": {
            "type": task_type,
            "websiteURL": website_url,
            "websiteKey": website_key,
            **kwargs
        }
    }

    # Buat tugas
    response = requests.post(
        "https://api.capsolver.com/createTask",
        json=payload
    )
    result = response.json()

    if result.get("errorId") != 0:
        raise Exception(f"Gagal membuat tugas: {result.get('errorDescription')}")

    task_id = result.get("taskId")
    print(f"Tugas dibuat: {task_id}")

    # Pantau hasil
    max_attempts = 60  # Maksimum 2 menit pemantauan
    for attempt in range(max_attempts):
        time.sleep(2)

        response = requests.post(
            "https://api.capsolver.com/getTaskResult",
            json={
                "clientKey": CAPSOLVER_API_KEY,
                "taskId": task_id
            }
        )
        result = response.json()

        if result.get("status") == "ready":
            print(f"Captcha selesai dalam {(attempt + 1) * 2} detik")
            return result.get("solution")

        if result.get("errorId") != 0:
            raise Exception(f"Kesalahan: {result.get('errorDescription')}")

        print(f"Menunggu... (percobaan {attempt + 1})")

    raise Exception("Waktu habis: Penyelesaian captcha terlalu lama")

<div class="g-recaptcha" data-sitekey="6LcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxABCD"></div>

<script src="https://www.google.com/recaptcha/api.js?render=6LcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxABCD"></script>

from scrapling import Fetcher

def scrape_with_recaptcha_v2(target_url, site_key, form_url=None):
    """
    Mengambil halaman yang dilindungi ReCaptcha v2.

    Args:
        target_url: URL halaman dengan captcha
        site_key: Kunci ReCaptcha
        form_url: URL untuk mengirimkan formulir (default ke target_url)

    Returns:
        Respons dari halaman yang dilindungi
    """
    # Selesaikan captcha menggunakan CapSolver
    print("Menyelesaikan ReCaptcha v2...")
    solution = solve_captcha(
        task_type="ReCaptchaV2TaskProxyLess",
        website_url=target_url,
        website_key=site_key
    )

    captcha_token = solution["gRecaptchaResponse"]
    print(f"Dapatkan token: {captcha_token[:50]}...")

    # Kirim formulir dengan token captcha menggunakan Scrapling
    # Catatan: Gunakan Fetcher.post() sebagai metode kelas (bukan metode instans)
    submit_url = form_url or target_url
    response = Fetcher.post(
        submit_url,
        data={
            "g-recaptcha-response": captcha_token,
            # Tambahkan bidang formulir lainnya yang diperlukan situs
        }
    )

    return response

# Contoh penggunaan
if __name__ == "__main__":
    url = "https://example.com/protected-page"
    site_key = "6LcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxABCD"

    result = scrape_with_recaptcha_v2(url, site_key)
    print(f"Status: {result.status}")
    print(f"Panjang konten: {len(result.body)}")  # Gunakan .body untuk byte mentah

solution = solve_captcha(
    task_type="ReCaptchaV2TaskProxyLess",
    website_url=target_url,
    website_key=site_key,
    isInvisible=True
)

solution = solve_captcha(
    task_type="ReCaptchaV2EnterpriseTaskProxyLess",
    website_url=target_url,
    website_key=site_key,
    enterprisePayload={
        "s": "nilai_s_payload jika diperlukan"
    }
)

grecaptcha.execute('6LcxxxxxxxxxxxxxxxxABCD', {action: 'submit'})

from scrapling import Fetcher

def scrape_with_recaptcha_v3(target_url, site_key, page_action="submit", min_score=0.7):
    """
    Mengambil halaman yang dilindungi ReCaptcha v3.

    Args:
        target_url: URL halaman dengan captcha
        site_key: Kunci ReCaptcha
        page_action: Parameter aksi (ditemukan dalam grecaptcha.execute)
        min_score: Skor minimum yang diminta (0.1-0.9)

    Returns:
        Respons dari halaman yang dilindungi
    """
    print(f"Menyelesaikan ReCaptcha v3 (aksi: {page_action})...")

    solution = solve_captcha(
        task_type="ReCaptchaV3TaskProxyLess",
        website_url=target_url,
        website_key=site_key,
        pageAction=page_action
    )

    captcha_token = solution["gRecaptchaResponse"]
    print(f"Dapatkan token dengan skor: {solution.get('score', 'Tidak tersedia')}")

    # Kirim permintaan dengan token menggunakan metode kelas Scrapling
    response = Fetcher.post(
        target_url,
        data={
            "g-recaptcha-response": captcha_token,
        },
        headers={
            "User-Agent": solution.get("userAgent", "Mozilla/5.0")
        }
    )

    return response

# Contoh penggunaan
if __name__ == "__main__":
    url = "https://example.com/api/data"
    site_key = "6LcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxABCD"

    result = scrape_with_recaptcha_v3(url, site_key, page_action="getData")
    print(f"Respons: {result.body.decode()[:200]}")  # Gunakan .body untuk konten

solution = solve_captcha(
    task_type="ReCaptchaV3EnterpriseTaskProxyLess",
    website_url=target_url,
    website_key=site_key,
    pageAction=page_action,
    enterprisePayload={
        "s": "parameter s opsional"
    }
)

<div class="cf-turnstile" data-sitekey="0x4xxxxxxxxxxxxxxxxxxxxxxxxxx"></div>

turnstile.render('#container', {
    sitekey: '0x4xxxxxxxxxxxxxxxxxxxxxxxxxx',
    callback: function(token) { ... }
});

from scrapling import Fetcher

def scrape_with_turnstile(target_url, site_key, action=None, cdata=None):
    """
    Mengambil halaman yang dilindungi Cloudflare Turnstile.

    Args:
        target_url: URL halaman dengan captcha
        site_key: Kunci Turnstile (dimulai dengan 0x4...)
        action: Parameter aksi opsional
        cdata: Parameter cdata opsional

    Returns:
        Respons dari halaman yang dilindungi
    """
    print("Menyelesaikan Cloudflare Turnstile...")

    # Bangun metadata jika tersedia
    metadata = {}
    if action:
        metadata["action"] = action
    if cdata:
        metadata["cdata"] = cdata

    task_params = {
        "task_type": "AntiTurnstileTaskProxyLess",
        "website_url": target_url,
        "website_key": site_key,
    }

    if metadata:
        task_params["metadata"] = metadata

    solution = solve_captcha(**task_params)

    turnstile_token = solution["token"]
    user_agent = solution.get("userAgent", "")

    print(f"Dapatkan token Turnstile: {turnstile_token[:50]}...")

    # Kirim dengan token menggunakan metode kelas Scrapling
    headers = {}
    if user_agent:
        headers["User-Agent"] = user_agent

    response = Fetcher.post(
        target_url,
        data={
            "cf-turnstile-response": turnstile_token,
        },
headers=headers
    )

    return response

# Contoh penggunaan
if __name__ == "__main__":
    url = "https://example.com/terlindungi"
    site_key = "0x4AAAAAAAxxxxxxxxxxxxxx"

    result = scrape_with_turnstile(url, site_key)
    print(f"Berhasil! Mendapatkan {len(result.body)} byte")  # Gunakan .body untuk konten

### Turnstile dengan Action dan CData

Beberapa implementasi memerlukan parameter tambahan:

```python
solution = solve_captcha(
    task_type="AntiTurnstileTaskProxyLess",
    website_url=target_url,
    website_key=site_key,
    metadata={
        "action": "login",
        "cdata": "session_id_atau_data_kustom"
    }
)

from scrapling import StealthyFetcher
import asyncio

async def scrape_with_stealth_and_recaptcha(target_url, site_key, captcha_type="v2"):
    """
    Menggabungkan fitur anti-bot StealthyFetcher dengan CapSolver untuk ReCaptcha.

    Args:
        target_url: URL yang ingin di-scrape
        site_key: Kunci captcha
        captcha_type: "v2" atau "v3"

    Returns:
        Konten halaman setelah menyelesaikan captcha
    """

    # Pertama, selesaikan captcha menggunakan CapSolver
    print(f"Menyelesaikan ReCaptcha {captcha_type}...")

    if captcha_type == "v2":
        solution = solve_captcha(
            task_type="ReCaptchaV2TaskProxyLess",
            website_url=target_url,
            website_key=site_key
        )
        token = solution["gRecaptchaResponse"]

    elif captcha_type == "v3":
        solution = solve_captcha(
            task_type="ReCaptchaV3TaskProxyLess",
            website_url=target_url,
            website_key=site_key,
            pageAction="submit"
        )
        token = solution["gRecaptchaResponse"]

    else:
        raise ValueError(f"Jenis captcha tidak dikenal: {captcha_type}")

    print(f"Dapatkan token: {token[:50]}...")

    # Gunakan StealthyFetcher untuk perilaku seperti browser
    fetcher = StealthyFetcher()

    # Navigasi ke halaman
    page = await fetcher.async_fetch(target_url)

    # Sisipkan solusi ReCaptcha menggunakan JavaScript
    await page.page.evaluate(f'''() => {{
        // Cari bidang g-recaptcha-response dan atur nilainya
        let field = document.querySelector('textarea[name="g-recaptcha-response"]');
        if (!field) {{
            field = document.createElement('textarea');
            field.name = "g-recaptcha-response";
            field.style.display = "none";
            document.body.appendChild(field);
        }}
        field.value = "{token}";
    }}''')

    # Cari dan klik tombol submit
    submit_button = page.css('button[type="submit"], input[type="submit"]')
    if submit_button:
        await submit_button[0].click()
        # Tunggu navigasi
        await page.page.wait_for_load_state('networkidle')

    # Dapatkan konten halaman akhir
    content = await page.page.content()

    return content

# Wrapper sinkron untuk penggunaan yang lebih mudah
def scrape_stealth(target_url, site_key, captcha_type="v2"):
    """Wrapper sinkron untuk scraper stealth asinkron."""
    return asyncio.run(
        scrape_with_stealth_and_recaptcha(target_url, site_key, captcha_type)
    )

# Contoh penggunaan
if __name__ == "__main__":
    url = "https://example.com/halaman-terlindungi-tinggi"
    site_key = "6LcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxABCD"

    content = scrape_stealth(url, site_key, captcha_type="v2")
    print(f"Dapatkan {len(content)} byte konten")

from scrapling import StealthyFetcher
import asyncio

class StealthScraper:
    """Pengambil data yang mempertahankan sesi di beberapa halaman."""

    def __init__(self, api_key):
        self.api_key = api_key
        self.fetcher = None

    async def __aenter__(self):
        self.fetcher = StealthyFetcher()
        return self

    async def __aexit__(self, *args):
        if self.fetcher:
            await self.fetcher.close()

    async def solve_and_access(self, url, site_key, captcha_type="v2"):
        """Selesaikan ReCaptcha dan akses halaman."""
        global CAPSOLVER_API_KEY
        CAPSOLVER_API_KEY = self.api_key

        # Selesaikan ReCaptcha
        task_type = f"ReCaptcha{captcha_type.upper()}TaskProxyLess"
        solution = solve_captcha(
            task_type=task_type,
            website_url=url,
            website_key=site_key
        )
        token = solution["gRecaptchaResponse"]

        # Navigasi dan sisipkan token
        page = await self.fetcher.async_fetch(url)
        # ... lanjutkan dengan interaksi halaman

        return page

# Penggunaan
async def main():
    async with StealthScraper("kunci_api_anda") as scraper:
        page1 = await scraper.solve_and_access(
            "https://example.com/login",
            "kunci_site_here",
            "v2"
        )
        # Sesi dipertahankan untuk permintaan berikutnya
        page2 = await scraper.solve_and_access(
            "https://example.com/dashboard",
            "kunci_site_lain",
            "v3"
        )

asyncio.run(main())

import time
import random

def scrape_yang_sopan(urls, min_delay=2, max_delay=5):
    """Mengambil data dengan jeda acak untuk terlihat lebih manusia."""
    results = []
    for url in urls:
        result = scrape_page(url)
        results.append(result)

        # Jeda acak antara permintaan
        delay = random.uniform(min_delay, max_delay)
        time.sleep(delay)

    return results

def solve_captcha_yang_kuat(task_type, website_url, website_key, max_retries=3, **kwargs):
    """Menyelesaikan captcha dengan retry otomatis."""
    for attempt in range(max_retries):
        try:
            return solve_captcha(task_type, website_url, website_key, **kwargs)
        except Exception as e:
            print(f"Uji coba {attempt + 1} gagal: {e}")
            if attempt < max_retries - 1:
                time.sleep(5)  # Tunggu sebelum retry
            else:
                raise

from urllib.robotparser import RobotFileParser

def bisa_scrape(url):
    """Periksa apakah mengambil data diizinkan oleh robots.txt."""
    rp = RobotFileParser()
    rp.set_url(f"{url}/robots.txt")
    rp.read()
    return rp.can_fetch("*", url)

# CapSolver mendukung tugas dengan proxy
solution = solve_captcha(
    task_type="ReCaptchaV2Task",  # Perhatikan: tidak ada "ProxyLess"
    website_url=target_url,
    website_key=site_key,
    proxy="http://user:pass@proxy.example.com:8080"
)

import time

class CacheCaptcha:
    def __init__(self, ttl=120):  # TTL default 2 menit
        self.cache = {}
        self.ttl = ttl

    def get_or_solve(self, key, solve_func):
        """Dapatkan token yang disimpan atau selesaikan yang baru."""
        if key in self.cache:
            token, timestamp = self.cache[key]
            if time.time() - timestamp < self.ttl:
                return token

        token = solve_func()
        self.cache[key] = (token, time.time())
        return token

import asyncio

async def async_solve_captcha(*args, **kwargs):
    loop = asyncio.get_event_loop()
    return await loop.run_in_executor(
        None,
        lambda: solve_captcha(*args, **kwargs)
    )

# Selesaikan beberapa ReCaptchas
solution_v2 = solve_captcha("ReCaptchaV2TaskProxyLess", url, key1)
solution_v3 = solve_captcha("ReCaptchaV3TaskProxyLess", url, key2, pageAction="submit")

# Kirim token menggunakan metode kelas Scrapling
response = Fetcher.post(url, data={
    "g-recaptcha-response": solution_v2["gRecaptchaResponse"],
    "g-recaptcha-response-v3": solution_v3["gRecaptchaResponse"],
})