File size: 1,929 Bytes
86a2576 |
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 |
# =======================
# IMPORTS
# =======================
import joblib
import re
from urllib.parse import urlparse
import tldextract
from PyPDF2 import PdfReader
# =======================
# LOAD MODEL
# =======================
model = joblib.load("test_model.joblib")
# =======================
# URL FEATURES
# =======================
def extract_url_features(url):
parsed = urlparse(url)
ext = tldextract.extract(url)
return {
"url_length": len(url),
"num_dots": url.count("."),
"has_ip": bool(re.search(r"\d+\.\d+\.\d+\.\d+", url)),
"https": parsed.scheme == "https",
"domain_length": len(ext.domain)
}
# =======================
# PDF TEXT EXTRACTION
# =======================
def extract_pdf_text(pdf_path):
text = ""
reader = PdfReader(pdf_path)
for page in reader.pages:
text += page.extract_text() or ""
return text[:500] # limit for cloud
# =======================
# PREDICTION FUNCTION
# =======================
def predict(data):
"""
Expects JSON input:
{"inputs": {"text": "...", "url": "...", "pdf_path": "..."}}
pdf_path is optional if sending a PDF file
"""
text = data["inputs"].get("text", "")
url = data["inputs"].get("url", "")
pdf_path = data["inputs"].get("pdf_path", "")
# URL features
url_features = extract_url_features(url) if url else {}
# PDF text (optional)
pdf_text = extract_pdf_text(pdf_path) if pdf_path else ""
# Combine text + PDF text
combined_text = text + " " + pdf_text
# ML prediction
pred = model.predict([combined_text])[0]
prob = model.predict_proba([combined_text])[0][1]
return {
"prediction": int(pred),
"probability": float(prob),
"url_features": url_features,
"pdf_text_sample": pdf_text[:100] # sample only
}
|