"url": "https://xnexx.hot", "final_url": "https://xnexx.hot/", "status_code": 200, "title": "XNEXX – Free Adult Videos", "meta_description": "Watch the latest adult videos on XNEXX...", "og_title": "XNEXX", "og_description": "Free adult video streaming", "keywords": "porn, xxx, free videos", "is_adult_content": true, "content_length_bytes": 84231
return report
# Gather all visible text for a quick adult‑content heuristic visible_text = " ".join( s.get_text(separator=" ", strip=True) for s in soup.find_all(string=True) if s.parent.name not in "script", "style", "noscript" ) adult_flag = is_adult_content(visible_text) xnexx hot
def main(): if len(sys.argv) != 2: print("Usage: python quick_site_overview.py <URL>", file=sys.stderr) sys.exit(1) "url": "https://xnexx
def extract_meta(soup: BeautifulSoup, name: str) -> str: """Return the content of a meta tag (name or property).""" tag = soup.find("meta", attrs="name": name) or soup.find( "meta", attrs="property": name ) return (tag["content"] if tag and tag.has_attr("content") else "") "title": "XNEXX – Free Adult Videos"
report = build_report(raw_url) print(json.dumps(report, indent=2, ensure_ascii=False))
raw_url = sys.argv[1] # Ensure we have a scheme – requests needs it. parsed = urlparse(raw_url) if not parsed.scheme: raw_url = "https://" + raw_url