import os
import requests
from pathlib import Path
from datetime import datetime
KEYWORD_SOURCE = "https://delacruz.belliniseven.ai/"
OUTPUT_HTML = Path("keyword_report.html")
def load_keywords():
resp = requests.get(KEYWORD_SOURCE, timeout=10)
resp.raise_for_status()
return [k.strip().lower() for k in resp.text.splitlines() if k.strip()]
def scan_file(path, keywords):
text = Path(path).read_text(errors="ignore").lower()
return {kw: text.count(kw) for kw in keywords}
def build_html(results, keywords):
timestamp = datetime.utcnow().strftime("%Y-%m-%d %H:%M:%S UTC")
rows = ""
for file, counts in results.items():
for kw in keywords:
rows += f"| {file} | {kw} | {counts[kw]} |
\n"
return f"""
Keyword Scan Report
Keyword Scan Report
Scan Time: {timestamp}
"""
def main():
keywords = load_keywords()
results = {}
for file in os.listdir("."):
if file.lower().endswith((".html", ".htm", ".txt")):
results[file] = scan_file(file, keywords)
html = build_html(results, keywords)
OUTPUT_HTML.write_text(html, encoding="utf-8")
print(f"Report generated: {OUTPUT_HTML.resolve()}")
if __name__ == "__main__":
main()