| import gradio as gr | |
| import json | |
| import pandas as pd | |
| import spacy | |
| import subprocess | |
| import sys | |
| import logging | |
| from pathlib import Path | |
| from seo_analyzer import SEOSpaceAnalyzer | |
| logging.basicConfig(level=logging.INFO) | |
| logger = logging.getLogger(__name__) | |
| def setup_spacy_model(): | |
| """Carga o descarga el modelo spaCy necesario.""" | |
| try: | |
| spacy.load("es_core_news_lg") | |
| except OSError: | |
| logger.info("Descargando spaCy model es_core_news_lg...") | |
| subprocess.run([sys.executable, "-m", "spacy", "download", "es_core_news_lg"], check=True) | |
| def create_interface() -> gr.Blocks: | |
| analyzer = SEOSpaceAnalyzer() | |
| with gr.Blocks(title="SEO Analyzer Pro", theme=gr.themes.Soft()) as demo: | |
| gr.Markdown(""" | |
| # 🧠 SEO Analyzer Pro | |
| Este espacio analiza contenido web orientado a normativa bancaria y genera: | |
| - Temas inferidos automáticamente | |
| - Títulos y meta descripciones SEO | |
| - Alertas por lenguaje de riesgo | |
| """) | |
| with gr.Row(): | |
| sitemap_input = gr.Textbox(label="📍 URL del Sitemap", placeholder="https://ejemplo.com/sitemap.xml") | |
| analyze_btn = gr.Button("🔍 Analizar") | |
| clear_btn = gr.Button("🧹 Limpiar") | |
| download_json_btn = gr.Button("📥 Descargar JSON") | |
| download_csv_btn = gr.Button("📤 Descargar CSV") | |
| status_output = gr.Textbox(label="Estado del análisis") | |
| with gr.Tabs(): | |
| with gr.Tab("📊 Resumen"): | |
| stats_output = gr.JSON(label="Estadísticas") | |
| recommendations_output = gr.JSON(label="Recomendaciones SEO") | |
| with gr.Tab("📝 Contenido"): | |
| content_output = gr.JSON(label="Análisis de contenido") | |
| with gr.Tab("🔗 Enlaces"): | |
| links_output = gr.JSON(label="Análisis de enlaces") | |
| links_plot = gr.Plot(label="Visualización de enlaces internos") | |
| with gr.Tab("📄 Detalles"): | |
| details_output = gr.JSON(label="Detalles por página") | |
| with gr.Tab("🧠 SEO y Temas"): | |
| seo_tags_output = gr.JSON(label="Metadatos SEO generados") | |
| topics_output = gr.JSON(label="Temas inferidos") | |
| flags_output = gr.JSON(label="Términos prohibidos detectados") | |
| with gr.Tab("🔗 Similitud"): | |
| similarity_output = gr.JSON(label="Similitud entre URLs") | |
| def analyze_with_status(sitemap_url): | |
| try: | |
| result = analyzer.analyze_sitemap(sitemap_url) | |
| return (*result, "✅ Análisis completado") | |
| except Exception as e: | |
| return [None]*8 + [f"❌ Error: {e}"] | |
| def export_json(): | |
| if analyzer.current_analysis: | |
| path = Path("content_storage/seo_report.json") | |
| with open(path, "w", encoding="utf-8") as f: | |
| json.dump(analyzer.current_analysis, f, ensure_ascii=False, indent=2) | |
| return str(path) | |
| return "" | |
| def export_csv(): | |
| if not analyzer.current_analysis: | |
| return "" | |
| path = Path("content_storage/seo_summary.csv") | |
| data = [] | |
| for url, seo in analyzer.current_analysis.get("seo_tags", {}).items(): | |
| data.append({ | |
| "url": url, | |
| "title": seo.get("title", ""), | |
| "meta_description": seo.get("meta_description", ""), | |
| "flags": ", ".join(seo.get("flags", [])), | |
| "topics": ", ".join(analyzer.current_analysis.get("topics", {}).get(url, [])), | |
| "summary": analyzer.current_analysis.get("summaries", {}).get(url, "") | |
| }) | |
| pd.DataFrame(data).to_csv(path, index=False) | |
| return str(path) | |
| analyze_btn.click( | |
| fn=analyze_with_status, | |
| inputs=sitemap_input, | |
| outputs=[ | |
| stats_output, recommendations_output, content_output, | |
| links_output, details_output, similarity_output, | |
| seo_tags_output, status_output | |
| ] | |
| ) | |
| clear_btn.click(fn=lambda: [None]*8, outputs=[ | |
| stats_output, recommendations_output, content_output, | |
| links_output, details_output, similarity_output, | |
| seo_tags_output, status_output | |
| ]) | |
| download_json_btn.click(fn=export_json, outputs=status_output) | |
| download_csv_btn.click(fn=export_csv, outputs=status_output) | |
| links_output.change(fn=analyzer.plot_internal_links, inputs=links_output, outputs=links_plot) | |
| seo_tags_output.change(fn=lambda: analyzer.current_analysis.get("topics", {}), outputs=topics_output) | |
| seo_tags_output.change(fn=lambda: analyzer.current_analysis.get("flags", {}), outputs=flags_output) | |
| return demo | |
| if __name__ == "__main__": | |
| setup_spacy_model() | |
| app = create_interface() | |
| app.launch(server_name="0.0.0.0", server_port=7860) | |