mirror of
https://github.com/Dvorinka/facr-scraper.git
synced 2026-06-03 20:12:57 +00:00
ed61d8ab8e
Integrate CloakBrowser to improve success rates against Cloudflare challenges and implement more robust request handling in the Go backend. - Add CloakBrowser integration to Dockerfile and requirements - Implement domain-specific request semaphores in Go to prevent rate-limiting - Add shared HTTP client with cookie jar and header preservation for better session management - Enhance request headers in Go to include modern client hints (Sec-Ch-Ua) - Add benchmarking scripts to compare fetch methods (urllib vs Scrapling vs CloakBrowser) - Update docker-compose to support CloakBrowser environment variables - Optimize Docker image by pre-downloading patched Chromium binaries
139 lines
4.2 KiB
Python
139 lines
4.2 KiB
Python
#!/usr/bin/env python3
|
|
|
|
import argparse
|
|
import contextlib
|
|
import logging
|
|
import ssl
|
|
import sys
|
|
import urllib.request
|
|
|
|
|
|
BROWSER_UA = (
|
|
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
|
|
"AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0 Safari/537.36"
|
|
)
|
|
|
|
CF_SIGNS = [
|
|
b"<title>just a moment...</title>",
|
|
b"attention required!",
|
|
b"enable javascript and cookies to continue",
|
|
b"checking if the site connection is secure",
|
|
b"cf-browser-verification",
|
|
b"/cdn-cgi/challenge-platform/",
|
|
]
|
|
|
|
|
|
def looks_like_cloudflare_block(body: bytes) -> bool:
|
|
if not body:
|
|
return False
|
|
low = body.lower()
|
|
for sig in CF_SIGNS:
|
|
if sig in low:
|
|
return True
|
|
return False
|
|
|
|
|
|
def response_body_bytes(response) -> bytes:
|
|
body = getattr(response, "body", None)
|
|
if isinstance(body, (bytes, bytearray)):
|
|
return bytes(body)
|
|
if isinstance(body, str):
|
|
return body.encode("utf-8")
|
|
|
|
text = getattr(response, "text", None)
|
|
if isinstance(text, str):
|
|
return text.encode("utf-8")
|
|
|
|
return str(response).encode("utf-8")
|
|
|
|
|
|
def lightweight_fetch(url: str, referer: str = "", timeout: float = 15.0) -> bytes:
|
|
"""Try a lightweight urllib fetch with browser headers first."""
|
|
req = urllib.request.Request(
|
|
url,
|
|
headers={
|
|
"User-Agent": BROWSER_UA,
|
|
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8",
|
|
"Accept-Language": "cs-CZ,cs;q=0.9,en;q=0.8",
|
|
"Accept-Encoding": "identity",
|
|
"Connection": "keep-alive",
|
|
**({"Referer": referer} if referer else {}),
|
|
},
|
|
)
|
|
ctx = ssl.create_default_context()
|
|
ctx.check_hostname = False
|
|
ctx.verify_mode = ssl.CERT_NONE
|
|
with urllib.request.urlopen(req, timeout=timeout, context=ctx) as resp:
|
|
body = resp.read()
|
|
if looks_like_cloudflare_block(body):
|
|
raise RuntimeError(" lightweight fetch returned Cloudflare challenge")
|
|
return body
|
|
|
|
|
|
def scrapling_fetch(url: str, referer: str = "", timeout_ms: int = 30000, wait_ms: int = 500) -> bytes:
|
|
try:
|
|
from scrapling.fetchers import StealthyFetcher
|
|
except Exception as exc:
|
|
raise RuntimeError(f"Scrapling import failed: {exc}") from exc
|
|
|
|
logging.getLogger().setLevel(logging.ERROR)
|
|
|
|
extra_headers = {}
|
|
if referer:
|
|
extra_headers["Referer"] = referer
|
|
|
|
# Increase challenge-solving timeout; network_idle can interfere with
|
|
# ongoing Cloudflare polling so we disable it.
|
|
fetch_kwargs = {
|
|
"headless": True,
|
|
"network_idle": False,
|
|
"google_search": False,
|
|
"solve_cloudflare": True,
|
|
"timeout": timeout_ms,
|
|
"wait": wait_ms,
|
|
}
|
|
if extra_headers:
|
|
fetch_kwargs["extra_headers"] = extra_headers
|
|
|
|
with contextlib.redirect_stdout(sys.stderr):
|
|
response = StealthyFetcher.fetch(url, **fetch_kwargs)
|
|
|
|
status = getattr(response, "status", None)
|
|
if isinstance(status, int) and status >= 400:
|
|
raise RuntimeError(f"Scrapling returned HTTP {status}")
|
|
|
|
body = response_body_bytes(response)
|
|
if not body:
|
|
raise RuntimeError("Scrapling returned an empty body")
|
|
return body
|
|
|
|
|
|
def main() -> int:
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("--url", required=True)
|
|
parser.add_argument("--referer", default="")
|
|
parser.add_argument("--timeout-ms", type=int, default=30000)
|
|
parser.add_argument("--wait-ms", type=int, default=500)
|
|
args = parser.parse_args()
|
|
|
|
# 1) Try lightweight urllib fetch first (no browser, instant)
|
|
try:
|
|
body = lightweight_fetch(args.url, args.referer, timeout=min(args.timeout_ms / 1000.0, 15.0))
|
|
sys.stdout.buffer.write(body)
|
|
return 0
|
|
except Exception as exc:
|
|
print(f"Lightweight fetch failed: {exc}", file=sys.stderr)
|
|
|
|
# 2) Fall back to Scrapling / Playwright only if lightweight failed
|
|
try:
|
|
body = scrapling_fetch(args.url, args.referer, args.timeout_ms, args.wait_ms)
|
|
sys.stdout.buffer.write(body)
|
|
return 0
|
|
except Exception as exc:
|
|
print(f"Scrapling fetch failed: {exc}", file=sys.stderr)
|
|
return 1
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|