from urllib.parse import urlparse


from utils.webTextExtractor import WebTextExtractor

class TextData:
    def __init__(self, url: str = "",text: str = "",result: str = "", is_fake_news: bool = False, provider: str = "") -> None:
        self.url = url
        self.text = text
        self.result = result
        self.is_fake_news = is_fake_news
        self.provider = provider
        self.confidence = None
        self._extractor = None

    def set_url(self, url: str) -> None:
        self.url = url
        self.text = ""  # Reset text when URL changes
        self._extractor = None  # Reset extractor when URL changes

    def text_from_url(self)-> bool:
        if not self.url:
            return False

        if not self.text:
            print("Extrahiere Text von URL...")
            self._extractor = WebTextExtractor(self.url)
            self._extractor.fetch_content()
            self._extractor.extract_text()
            self.text = self._extractor.get_text()
            return True
    
    def get_output(self):
        
        if self.confidence != None:
            output = f"Prediction: {self.result}" + f"   Confidence: {self.confidence:.4f}"
            return output

    def get_provider(self)-> str:
        self.extract_provider()
        return self.provider
    
    def extract_provider(self):
        """
        Extract the domain (anbieter) from a given URL.

        :param url: The URL to process
        :return: The extracted domain or None if the URL is invalid
        """
        if not self._is_valid_url(self.url):
            self.provider = "Unknown"
        parsed_url = urlparse(self.url)
        domain_parts = parsed_url.netloc.split('.')
        self.provider = f"{domain_parts[-2]}.{domain_parts[-1]}" if len(domain_parts) >= 2 else "Unknown" 

    def _is_valid_url(self, url: str) -> bool:
        """
        Check if a given URL is valid.

        :param url: The URL to validate
        :return: True if the URL is valid, False otherwise
        """
        try:
            result = urlparse(url)
            return all([result.scheme, result.netloc])
        except ValueError:
            return False