Method get_url_input

cli/cli_interface.py:366–432

Enhanced URL input with validation

(self)

            return file_path

    def get_url_input(self) -> str:
        """Enhanced URL input with validation"""
        self.print_separator("─", 79, Colors.GREEN)
        print(f"{Colors.BOLD}{Colors.GREEN}🌐 URL Input Interface{Colors.ENDC}")
        print(
            f"{Colors.CYAN}Enter a research paper URL from supported platforms:{Colors.ENDC}"
        )
        print(
            f"{Colors.CYAN}• arXiv (arxiv.org)        • IEEE Xplore (ieeexplore.ieee.org){Colors.ENDC}"
        )
        print(
            f"{Colors.CYAN}• ACM Digital Library      • SpringerLink • Nature • Science{Colors.ENDC}"
        )
        print(
            f"{Colors.CYAN}• Direct PDF links         • Academic publisher websites{Colors.ENDC}"
        )
        self.print_separator("─", 79, Colors.GREEN)

        while True:
            print(f"\n{Colors.BOLD}{Colors.OKCYAN}🔗 URL: {Colors.ENDC}", end="")
            url = input().strip()

            if not url:
                self.print_status(
                    "Empty URL entered. Please try again or press Ctrl+C to cancel.",
                    "warning",
                )
                continue

            if not url.startswith(("http://", "https://")):
                self.print_status("URL must start with http:// or https://", "error")
                retry = (
                    input(f"{Colors.YELLOW}Try again? (y/n): {Colors.ENDC}")
                    .strip()
                    .lower()
                )
                if retry != "y":
                    return ""
                continue

            academic_domains = [
                "arxiv.org",
                "ieeexplore.ieee.org",
                "dl.acm.org",
                "link.springer.com",
                "nature.com",
                "science.org",
                "scholar.google.com",
                "researchgate.net",
                "semanticscholar.org",
            ]

            is_academic = any(domain in url.lower() for domain in academic_domains)
            if not is_academic and not url.lower().endswith(".pdf"):
                self.print_status(
                    "URL doesn't appear to be from a known academic platform", "warning"
                )
                proceed = (