Spaces:
Sleeping
Sleeping
File size: 14,268 Bytes
dad3f62 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 | """hCaptcha Playwright automation wrapper.
Runs on your local machine. Detects hCaptcha on faucet pages,
screenshots tiles, calls the vision model API to classify them,
and clicks matching tiles with human-like delays.
Usage:
python scripts/hcaptcha_bot.py https://faucet-wave.online/tron-faucet/
Or import and use in your existing claimer scripts:
from scripts.hcaptcha_bot import solve_hcaptcha
await solve_hcaptcha(page, "https://faucet-wave.online/tron-faucet/")
"""
from __future__ import annotations
import asyncio
import base64
import io
import os
import random
import sys
import time
from typing import Optional
import httpx
try:
from playwright.async_api import async_playwright, Page, ElementHandle
except ImportError:
print("ERROR: playwright not installed. Run: pip install playwright && playwright install chromium")
sys.exit(1)
# Config
API_URL = os.environ.get("CAPTCHA_SOLVER_URL", "http://localhost:8765")
HF_SPACE_URL = os.environ.get("HF_SPACE_URL", "") # Set this for HF Spaces deployment
SOLVER_URL = HF_SPACE_URL or API_URL
TILE_DELAY_MIN = 0.8 # Min seconds between tile clicks
TILE_DELAY_MAX = 2.5 # Max seconds between tile clicks
CLICK_DELAY_MIN = 0.3
CLICK_DELAY_MAX = 0.8
async def _call_classify_api(
image_bytes: bytes,
instruction: str,
client: httpx.AsyncClient,
) -> dict:
"""Call POST /classify with a tile image."""
b64 = base64.b64encode(image_bytes).decode("ascii")
payload = {
"image_base64": b64,
"instruction": instruction,
}
try:
r = await client.post(f"{SOLVER_URL}/classify", json=payload, timeout=30)
r.raise_for_status()
return r.json()
except Exception as exc:
return {"match": False, "confidence": 0.0, "caption": "", "error": str(exc)}
def _extract_instruction(modal_content: str) -> str:
"""Extract hCaptcha instruction text from the challenge header."""
# Common hCaptcha patterns
patterns = [
r"(?:click|find|select|choose)\s+all\s+[^.]+",
r"(?:click|find|select|choose)\s+the\s+[^.]+",
r"(?:which|what)\s+[^?]+\?",
]
text_lower = modal_content.lower()
for pattern in patterns:
import re
match = re.search(pattern, text_lower, re.IGNORECASE)
if match:
return match.group(0).strip()
return modal_content.strip()
async def _human_like_mouse_move(page: Page, x: float, y: float) -> None:
"""Move mouse to (x, y) with human-like curve."""
await page.mouse.move(x, y, steps=random.randint(10, 25))
await asyncio.sleep(random.uniform(CLICK_DELAY_MIN, CLICK_DELAY_MAX))
async def _click_with_human_delay(page: Page, selector: str) -> None:
"""Click an element with random human-like delay."""
await asyncio.sleep(random.uniform(TILE_DELAY_MIN, TILE_DELAY_MAX))
element = await page.query_selector(selector)
if element:
box = await element.bounding_box()
if box:
# Click slightly off-center for realism
x = box["x"] + box["width"] * random.uniform(0.3, 0.7)
y = box["y"] + box["height"] * random.uniform(0.3, 0.7)
await _human_like_mouse_move(page, x, y)
await asyncio.sleep(random.uniform(0.1, 0.3))
await page.mouse.click(x, y)
async def _screenshot_tile(page: Page, tile_index: int, grid_selector: str = ".task-image") -> Optional[bytes]:
"""Screenshot a specific tile from the hCaptcha grid."""
tiles = await page.query_selector_all(grid_selector)
if tile_index >= len(tiles):
return None
tile = tiles[tile_index]
screenshot = await tile.screenshot()
return screenshot
async def solve_hcaptcha(
page: Page,
max_retries: int = 3,
verbose: bool = True,
) -> bool:
"""Solve hCaptcha on the current page.
Args:
page: Playwright page with hCaptcha loaded.
max_retries: Number of attempts before giving up.
verbose: Print progress info.
Returns:
True if captcha was solved successfully, False otherwise.
"""
for attempt in range(max_retries):
if verbose:
print(f"[hCaptcha] Attempt {attempt + 1}/{max_retries}")
try:
# Wait for hCaptcha iframe to appear
hcaptcha_frame = None
for frame in page.frames:
if "hcaptcha" in frame.url.lower():
hcaptcha_frame = frame
break
if not hcaptcha_frame:
# Try clicking the checkbox first
checkbox = await page.query_selector(".h-captcha iframe, iframe[src*='hcaptcha']")
if checkbox:
await checkbox.click()
await asyncio.sleep(2)
# Re-check frames
for frame in page.frames:
if "hcaptcha" in frame.url.lower():
hcaptcha_frame = frame
break
if not hcaptcha_frame:
if verbose:
print("[hCaptcha] No hCaptcha iframe found")
return False
# Wait for challenge to load (if checkbox was already solved)
await asyncio.sleep(1)
# Check if already solved (checkbox is green)
checkbox_frame = None
for frame in page.frames:
if "hcaptcha" in frame.url.lower() and "checkbox" in frame.url.lower():
checkbox_frame = frame
break
if checkbox_frame:
is_checked = await checkbox_frame.query_selector(".check")
if is_checked:
if verbose:
print("[hCaptcha] Already solved!")
return True
# Look for the challenge iframe (separate from checkbox iframe)
challenge_frame = None
for frame in page.frames:
if "hcaptcha" in frame.url.lower() and "challenge" in frame.url.lower():
challenge_frame = frame
break
if not challenge_frame:
# Challenge might be in the main frame's modal
challenge_frame = page
# Extract instruction text
instruction = ""
try:
header = await challenge_frame.query_selector(".challenge-header, .prompt-text, [class*='header']")
if header:
instruction = await header.inner_text()
else:
# Try getting all visible text in the challenge
body = await challenge_frame.query_selector("body")
if body:
all_text = await body.inner_text()
instruction = _extract_instruction(all_text)
except Exception:
pass
if not instruction:
if verbose:
print("[hCaptcha] Could not extract instruction")
continue
if verbose:
print(f"[hCaptcha] Instruction: {instruction}")
# Screenshot all tiles
tiles = await challenge_frame.query_selector_all(".task-image, [class*='tile'], [class*='image']")
if not tiles:
if verbose:
print("[hCaptcha] No tiles found in challenge")
continue
if verbose:
print(f"[hCaptcha] Found {len(tiles)} tiles")
# Classify each tile via API
matches = []
async with httpx.AsyncClient() as client:
for i, tile in enumerate(tiles):
try:
tile_screenshot = await tile.screenshot()
result = await _call_classify_api(tile_screenshot, instruction, client)
if result.get("match"):
matches.append(i)
if verbose:
status = "MATCH" if result.get("match") else "skip"
caption = result.get("caption", "")
conf = result.get("confidence", 0)
print(f" Tile {i + 1}: {status} (conf={conf:.2f}) caption={caption}")
except Exception as exc:
if verbose:
print(f" Tile {i + 1}: error - {exc}")
if not matches:
if verbose:
print("[hCaptcha] No matches found, skipping")
# Click "Get a new challenge" button
try:
refresh_btn = await challenge_frame.query_selector(
".refresh-button, [class*='refresh'], button[aria-label*='refresh']"
)
if refresh_btn:
await refresh_btn.click()
await asyncio.sleep(2)
continue
except Exception:
pass
continue
if verbose:
print(f"[hCaptcha] Clicking tiles: {[m + 1 for m in matches]}")
# Click matching tiles with human-like delays
for idx in matches:
tile = tiles[idx]
try:
box = await tile.bounding_box()
if box:
x = box["x"] + box["width"] * random.uniform(0.3, 0.7)
y = box["y"] + box["height"] * random.uniform(0.3, 0.7)
await _human_like_mouse_move(page, x, y)
await asyncio.sleep(random.uniform(0.1, 0.3))
await page.mouse.click(x, y)
await asyncio.sleep(random.uniform(TILE_DELAY_MIN, TILE_DELAY_MAX))
except Exception as exc:
if verbose:
print(f" Failed to click tile {idx + 1}: {exc}")
# Click Verify button
await asyncio.sleep(random.uniform(1.0, 2.0))
try:
verify_btn = await challenge_frame.query_selector(
".verify-button, button[type='submit'], [class*='verify']"
)
if verify_btn:
await verify_btn.click()
await asyncio.sleep(3)
# Check if solved
for frame in page.frames:
if "hcaptcha" in frame.url.lower() and "checkbox" in frame.url.lower():
is_checked = await frame.query_selector(".check")
if is_checked:
if verbose:
print("[hCaptcha] Solved successfully!")
return True
# If we get here, might need another attempt
if verbose:
print("[hCaptcha] Verification pending, checking...")
except Exception as exc:
if verbose:
print(f"[hCaptcha] Verify click failed: {exc}")
except Exception as exc:
if verbose:
print(f"[hCaptcha] Attempt {attempt + 1} error: {exc}")
# Wait before retry
await asyncio.sleep(random.uniform(2.0, 4.0))
if verbose:
print(f"[hCaptcha] Failed after {max_retries} attempts")
return False
async def main():
"""CLI entry point: solve hCaptcha on a given URL."""
import argparse
parser = argparse.ArgumentParser(description="Solve hCaptcha on a faucet page")
parser.add_argument("url", help="URL of the page with hCaptcha")
parser.add_argument("--address", help="FaucetPay address to fill in")
parser.add_argument("--api", default=SOLVER_URL, help="Captcha solver API URL")
parser.add_argument("--headless", action="store_true", help="Run headless (no browser window)")
args = parser.parse_args()
global SOLVER_URL
SOLVER_URL = args.api
async with async_playwright() as p:
browser = await p.chromium.launch(
headless=args.headless,
args=[
"--disable-blink-features=AutomationControlled",
"--no-sandbox",
],
)
context = await browser.new_context(
viewport={"width": 1280, "height": 800},
user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36",
)
page = await context.new_page()
print(f"[bot] Navigating to {args.url}")
await page.goto(args.url, wait_until="networkidle")
await asyncio.sleep(2)
# Fill in address if provided
if args.address:
addr_input = await page.query_selector("#fp-address, input[name='address']")
if addr_input:
await addr_input.fill(args.address)
print(f"[bot] Address filled: {args.address}")
# Click Claim button to open modal
claim_btn = await page.query_selector("#faucet-claim-btn, .faucet-btn")
if claim_btn:
await claim_btn.click()
print("[bot] Claim button clicked, modal opened")
await asyncio.sleep(2)
# Solve hCaptcha
solved = await solve_hcaptcha(page, max_retries=3, verbose=True)
if solved:
# Click Submit
submit_btn = await page.query_selector("#faucet-submit-btn, button.faucet-btn")
if submit_btn:
await submit_btn.click()
print("[bot] Submit clicked!")
await asyncio.sleep(5)
# Check for success message
success = await page.query_selector(".faucet-success, [class*='success']")
if success:
msg = await success.inner_text()
print(f"[bot] SUCCESS: {msg}")
else:
print("[bot] Claim submitted, check results")
else:
print("[bot] Failed to solve hCaptcha")
await browser.close()
if __name__ == "__main__":
asyncio.run(main())
|