File size: 1,510 Bytes
aaa4ec9 | 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 | import hashlib
import re
import logging
from urllib.parse import urlparse
logger = logging.getLogger(__name__)
def get_namespace_id(url: str) -> str:
"""
Generates a collision-resistant namespace ID.
Format: clean_name_MD5hash
"""
clean_name = re.sub(r"https?://(www\.)?", "", url)
clean_name = re.sub(r"[^a-zA-Z0-9]", "_", clean_name)
clean_name = clean_name.strip("_")[:30]
url_hash = hashlib.md5(url.encode("utf-8")).hexdigest()[:6]
return f"{clean_name}_{url_hash}"
def is_valid_url(url: str, base_domain: str) -> bool:
"""
Enforces strict crawl scope.
"""
try:
parsed = urlparse(url)
base_parsed = urlparse(base_domain)
# 1. Scheme Check
if parsed.scheme not in ["http", "https"]:
return False
# 2. Strict Domain Check (Ends with pattern to prevent 'google.com.evil.com')
# We allow subdomains (e.g. portal.batstateu.edu.ph)
if not parsed.netloc.endswith(base_parsed.netloc):
return False
# 3. File Extension Check
ignored_exts = [
".pdf",
".jpg",
".png",
".gif",
".css",
".js",
".docx",
".xlsx",
".xml",
".zip",
".rar",
".mp4",
]
if any(parsed.path.lower().endswith(ext) for ext in ignored_exts):
return False
return True
except Exception:
return False
|