import os
import json
import logging
import re
import requests
import hashlib
import PyPDF2
import numpy as np
import pandas as pd
from io import BytesIO
from typing import List, Dict, Optional
from urllib.parse import urlparse, urljoin
from concurrent.futures import ThreadPoolExecutor, as_completed
from bs4 import BeautifulSoup
from pathlib import Path
from datetime import datetime
from collections import defaultdict

import gradio as gr
import matplotlib.pyplot as plt
from sklearn.feature_extractioimport json
import logging
import re
import requests
import hashlib
import PyPDF2
import numpy as np
import pandas as pd
from io import BytesIO
from typing import List, Dict, Optional
from urllib.parse import urlparse, urljoin
from concurrent.futures import ThreadPoolExecutor, as_completed
from bs4 import BeautifulSoup
from pathlib import Path
from datetime import datetime
from collections import defaultdict

import gradio as gr
import matplotlib.pyplot as plt
from sklearn.feature_extraction.text import TfidfVectorizer
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry
from transformers import pipeline, AutoModelForQuestionAnswering, AutoTokenizer
from sentence_transformers import SentenceTransformer
import spacy
import torch

# Configuración inicial
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

class SEOSpaceAnalyzer:
    def __init__(self):
        self.session = self._configure_session()
        self.models = self._load_models()
        self.base_dir = Path("content_storage")
        self.link_analysis = defaultdict(list)
        self.documents = []
        self.current_analysis = {}
        
    def _configure_session(self):
        """Configuración avanzada de sesión HTTP con reintentos"""
        session = requests.Session()
        retry = Retry(
            total=3,
            backoff_factor=1,
            status_forcelist=[500, 502, 503, 504]
        )
        adapter = HTTPAdapter(max_retries=retry)
        session.mount('https://', adapter)
        session.headers.update({
            'User-Agent': 'Mozilla/5.0 (compatible; SEOBot/1.0)',
            'Accept-Language': 'es-ES,es;q=0.9'
        })
        return session
    
    def _load_models(self):
        """Carga modelos de Hugging Face optimizados"""
        device = 0 if torch.cuda.is_available() else -1
        return {
            'summarizer': pipeline("summarization", 
                                 model="facebook/bart-large-cnn",
                                 device=device),
            'ner': pipeline("ner", 
                           model="dslim/bert-base-NER",
                           aggregation_strategy="simple",
                           device=device),
            'qa': pipeline("question-answering",
                         model="deepset/roberta-base-squad2",
                         device=device),
            'semantic': SentenceTransformer('paraphrase-multilingual-MiniLM-L12-v2'),
            'spacy': spacy.load("es_core_news_lg")
        }
    
    def _process_url(self, url):
        """Procesa una URL y extrae su contenido"""
        try:
            response = self.session.get(url, timeout=15)
            response.raise_for_status()
            
            content_type = response.headers.get('Content-Type', '')
            result = {'url': url, 'links': []}
            
            if 'application/pdf' in content_type:
                result.update(self._process_pdf(response.content))
            elif 'text/html' in content_type:
                result.update(self._process_html(response.text, url))
                
            self._save_content(url, response.content)
            return result
            
        except Exception as e:
            logger.error(f"Error procesando {url}: {str(e)}")
            return {'url': url, 'error': str(e)}
    
    def _process_html(self, html, base_url):
        """Procesa contenido HTML"""
        soup = BeautifulSoup(html, 'lxml')
        return {
            'content': self._clean_text(soup.get_text()),
            'type': 'html',
            'metadata': self._extract_metadata(soup),
            'links': self._extract_links(soup, base_url)
        }
    
    def _process_pdf(self, content):
        """Procesa documentos PDF"""
        text = ""
        with BytesIO(content) as pdf_file:
            reader = PyPDF2.PdfReader(pdf_file)
            for page in reader.pages:
                text += page.extract_text()
                
        return {
            'content': self._clean_text(text),
            'type': 'pdf',
            'metadata': {'pages': len(reader.pages)}
        }
    
    def _extract_links(self, soup, base_url):
        """Extrae y clasifica enlaces"""
        links = []
        for tag in soup.find_all('a', href=True):
            href = tag['href']
            full_url = urljoin(base_url, href)
            link_type = 'internal' if urlparse(full_url).netloc == urlparse(base_url).netloc else 'external'
            
            links.append({
                'url': full_url,
                'type': link_type,
                'anchor': self._clean_text(tag.text),
                'file_type': self._get_file_type(href)
            })
        return links
    
    def _get_file_type(self, url):
        """Determina el tipo de archivo por extensión"""
        ext = Path(urlparse(url).path).suffix.lower()
        return ext[1:] if ext else 'html'
    
    def _clean_text(self, text):
        """Limpieza avanzada de texto"""
        text = re.sub(r'\s+', ' ', text)
        return re.sub(r'[^\w\sáéíóúñÁÉÍÓÚÑ]', ' ', text).strip()
    
    def _save_content(self, url, content):
        """Almacena el contenido descargado"""
        path = urlparse(url).path.lstrip('/')
        save_path = self.base_dir / urlparse(url).netloc / path
        save_path.parent.mkdir(parents=True, exist_ok=True)
        
        with open(save_path.with_suffix(self._get_file_type(url)), 'wb') as f:
            f.write(content)
    
    def analyze_sitemap(self, sitemap_url):
        """Analiza todo el sitemap y genera reportes"""
        urls = self._parse_sitemap(sitemap_url)
        results = []
        
        with ThreadPoolExecutor(max_workers=4) as executor:
            futures = [executor.submit(self._process_url, url) for url in urls]
            for future in as_completed(futures):
                results.append(future.result())
                progress(len(results)/len(urls))
        
        self.current_analysis = {
            'basic_stats': self._calculate_stats(results),
            'content_analysis': self._analyze_content(results),
            'link_analysis': self._analyze_links(results),
            'seo_recommendations': self._generate_recommendations(results)
        }
        
        return self.current_analysis
    
    def _parse_sitemap(self, sitemap_url):
        """Parsea sitemaps XML incluyendo sitemaps indexados"""
        # Implementación de parsing de sitemap (similar a versiones anteriores)
        return []
    
    def _calculate_stats(self, results):
        """Calcula estadísticas básicas del análisis"""
        return {
            'total_urls': len(results),
            'content_types': pd.Series([r.get('type', 'unknown') for r in results]).value_counts().to_dict(),
            'avg_content_length': np.mean([len(r.get('content', '')) for r in results])
        }
    
    def create_report(self):
        """Crea un reporte descargable en múltiples formatos"""
        report = {
            'timestamp': datetime.now().isoformat(),
            'analysis': self.current_analysis
        }
        
        # Guardar en JSON
        json_path = self.base_dir / 'seo_report.json'
        with open(json_path, 'w') as f:
            json.dump(report, f)
            
        # Crear CSV con enlaces
        df = pd.DataFrame([link for result in self.current_analysis['link_analysis'] for link in result['links']])
        csv_path = self.base_dir / 'links_analysis.csv'
        df.to_csv(csv_path, index=False)
        
        return [str(json_path), str(csv_path)]
    
    def create_visualization(self):
        """Genera visualizaciones interactivas"""
        fig, ax = plt.subplots()
        pd.Series(self.current_analysis['basic_stats']['content_types']).plot.pie(
            ax=ax, 
            title='Distribución de Tipos de Contenido',
            ylabel=''
        )
        return fig

# Interface Gradio
def create_interface():
    analyzer = SEOSpaceAnalyzer()
    
    with gr.Blocks(title="SEO Analyzer Pro", theme=gr.themes.Soft()) as interface:
        gr.Markdown("# 🕵️ SEO Analyzer Pro")
        
        with gr.Row():
            sitemap_url = gr.Textbox(label="URL del Sitemap", placeholder="https://www.ing.es/ennaranja/sitemap.xml")
            analyze_btn = gr.Button("Analizar", variant="primary")
        
        with gr.Tab("Resultados"):
            json_output = gr.JSON(label="Análisis Completo")
            plot_output = gr.Plot(label="Visualización")
            
        with gr.Tab("Enlaces"):
            internal_links = gr.Dataframe(label="Enlaces Internos")
            external_links = gr.Dataframe(label="Enlaces Externos")
            
        with gr.Tab("Descargas"):
            report_download = gr.Files(label="Descargar Reporte")
            download_btn = gr.Button("Generar Reporte", variant="secondary")
        
        analyze_btn.click(
            fn=analyzer.analyze_sitemap,
            inputs=sitemap_url,
            outputs=[json_output, plot_output, internal_links, external_links]
        )
        
        download_btn.click(
            fn=analyzer.create_report,
            outputs=report_download
        )
        
    return interface

if __name__ == "__main__":
    interface = create_interface()
    interface.launch(server_name="0.0.0.0", server_port=7860)