Update app.py
Browse files
app.py
CHANGED
@@ -15,13 +15,52 @@ def setup_spacy_model():
|
|
15 |
"""Carga o descarga el modelo spaCy necesario."""
|
16 |
try:
|
17 |
spacy.load("es_core_news_lg")
|
|
|
18 |
except OSError:
|
19 |
logger.info("Descargando spaCy model es_core_news_lg...")
|
20 |
subprocess.run([sys.executable, "-m", "spacy", "download", "es_core_news_lg"], check=True)
|
21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
def create_interface() -> gr.Blocks:
|
23 |
analyzer = SEOSpaceAnalyzer()
|
24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
with gr.Blocks(title="SEO Analyzer Pro", theme=gr.themes.Soft()) as demo:
|
26 |
gr.Markdown("""
|
27 |
# 🧠 SEO Analyzer Pro
|
@@ -30,16 +69,13 @@ def create_interface() -> gr.Blocks:
|
|
30 |
- Títulos y meta descripciones SEO
|
31 |
- Alertas por lenguaje de riesgo
|
32 |
""")
|
33 |
-
|
34 |
with gr.Row():
|
35 |
sitemap_input = gr.Textbox(label="📍 URL del Sitemap", placeholder="https://ejemplo.com/sitemap.xml")
|
36 |
analyze_btn = gr.Button("🔍 Analizar")
|
37 |
clear_btn = gr.Button("🧹 Limpiar")
|
38 |
download_json_btn = gr.Button("📥 Descargar JSON")
|
39 |
download_csv_btn = gr.Button("📤 Descargar CSV")
|
40 |
-
|
41 |
-
status_output = gr.Textbox(label="Estado del análisis")
|
42 |
-
|
43 |
with gr.Tabs():
|
44 |
with gr.Tab("📊 Resumen"):
|
45 |
stats_output = gr.JSON(label="Estadísticas")
|
@@ -53,27 +89,24 @@ def create_interface() -> gr.Blocks:
|
|
53 |
details_output = gr.JSON(label="Detalles por página")
|
54 |
with gr.Tab("🧠 SEO y Temas"):
|
55 |
seo_tags_output = gr.JSON(label="Metadatos SEO generados")
|
|
|
56 |
topics_output = gr.JSON(label="Temas inferidos")
|
57 |
flags_output = gr.JSON(label="Términos prohibidos detectados")
|
58 |
with gr.Tab("🔗 Similitud"):
|
59 |
similarity_output = gr.JSON(label="Similitud entre URLs")
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
return [None]*8 + [f"❌ Error: {e}"]
|
67 |
-
|
68 |
-
def export_json():
|
69 |
if analyzer.current_analysis:
|
70 |
path = Path("content_storage/seo_report.json")
|
71 |
with open(path, "w", encoding="utf-8") as f:
|
72 |
-
json.dump(analyzer.current_analysis, f,
|
73 |
return str(path)
|
74 |
return ""
|
75 |
-
|
76 |
-
def export_csv():
|
77 |
if not analyzer.current_analysis:
|
78 |
return ""
|
79 |
path = Path("content_storage/seo_summary.csv")
|
@@ -89,15 +122,15 @@ def create_interface() -> gr.Blocks:
|
|
89 |
})
|
90 |
pd.DataFrame(data).to_csv(path, index=False)
|
91 |
return str(path)
|
92 |
-
|
93 |
analyze_btn.click(
|
94 |
-
fn=
|
95 |
inputs=sitemap_input,
|
96 |
outputs=[
|
97 |
stats_output, recommendations_output, content_output,
|
98 |
links_output, details_output, similarity_output,
|
99 |
seo_tags_output, status_output
|
100 |
-
]
|
|
|
101 |
)
|
102 |
clear_btn.click(fn=lambda: [None]*8, outputs=[
|
103 |
stats_output, recommendations_output, content_output,
|
@@ -109,7 +142,8 @@ def create_interface() -> gr.Blocks:
|
|
109 |
links_output.change(fn=analyzer.plot_internal_links, inputs=links_output, outputs=links_plot)
|
110 |
seo_tags_output.change(fn=lambda: analyzer.current_analysis.get("topics", {}), outputs=topics_output)
|
111 |
seo_tags_output.change(fn=lambda: analyzer.current_analysis.get("flags", {}), outputs=flags_output)
|
112 |
-
|
|
|
113 |
return demo
|
114 |
|
115 |
if __name__ == "__main__":
|
|
|
15 |
"""Carga o descarga el modelo spaCy necesario."""
|
16 |
try:
|
17 |
spacy.load("es_core_news_lg")
|
18 |
+
logger.info("Modelo spaCy 'es_core_news_lg' cargado correctamente.")
|
19 |
except OSError:
|
20 |
logger.info("Descargando spaCy model es_core_news_lg...")
|
21 |
subprocess.run([sys.executable, "-m", "spacy", "download", "es_core_news_lg"], check=True)
|
22 |
|
23 |
+
def list_content_storage_files() -> list:
|
24 |
+
"""Devuelve la lista de archivos en la carpeta content_storage."""
|
25 |
+
base_dir = Path("content_storage")
|
26 |
+
if not base_dir.exists():
|
27 |
+
return []
|
28 |
+
return [str(file.relative_to(base_dir)) for file in base_dir.glob("**/*") if file.is_file()]
|
29 |
+
|
30 |
+
def download_storage_file(selected_file: str) -> str:
|
31 |
+
"""Dado el nombre del archivo (relativo a content_storage), devuelve la ruta para descarga."""
|
32 |
+
if not selected_file:
|
33 |
+
return ""
|
34 |
+
file_path = Path("content_storage") / selected_file
|
35 |
+
return str(file_path) if file_path.exists() else ""
|
36 |
+
|
37 |
+
def refresh_file_list() -> list:
|
38 |
+
"""Actualiza la lista de archivos disponibles en content_storage."""
|
39 |
+
return list_content_storage_files()
|
40 |
+
|
41 |
+
# Creamos la interfaz
|
42 |
def create_interface() -> gr.Blocks:
|
43 |
analyzer = SEOSpaceAnalyzer()
|
44 |
|
45 |
+
# Definimos una función envoltorio para incluir callbacks de estado
|
46 |
+
def analyze_with_callbacks(sitemap_url: str):
|
47 |
+
status_msgs = []
|
48 |
+
|
49 |
+
def status_callback(msg: str):
|
50 |
+
status_msgs.append(msg)
|
51 |
+
logger.info(msg)
|
52 |
+
|
53 |
+
def progress_callback(current: int, total: int):
|
54 |
+
logger.info(f"Batch {current} de {total} procesado.")
|
55 |
+
|
56 |
+
# Se llama al método modificado que procesa en lotes de 5
|
57 |
+
results = analyzer.analyze_sitemap(sitemap_url, progress_callback=progress_callback, status_callback=status_callback)
|
58 |
+
final_status = "\n".join(status_msgs) if status_msgs else "Análisis completado."
|
59 |
+
# 'results' es una tupla de 7 elementos:
|
60 |
+
# (stats, recommendations, content_analysis, links, details, similarities, seo_tags)
|
61 |
+
# Devolvemos esos 7 outputs más el mensaje final en estado (total 8)
|
62 |
+
return (*results, final_status)
|
63 |
+
|
64 |
with gr.Blocks(title="SEO Analyzer Pro", theme=gr.themes.Soft()) as demo:
|
65 |
gr.Markdown("""
|
66 |
# 🧠 SEO Analyzer Pro
|
|
|
69 |
- Títulos y meta descripciones SEO
|
70 |
- Alertas por lenguaje de riesgo
|
71 |
""")
|
|
|
72 |
with gr.Row():
|
73 |
sitemap_input = gr.Textbox(label="📍 URL del Sitemap", placeholder="https://ejemplo.com/sitemap.xml")
|
74 |
analyze_btn = gr.Button("🔍 Analizar")
|
75 |
clear_btn = gr.Button("🧹 Limpiar")
|
76 |
download_json_btn = gr.Button("📥 Descargar JSON")
|
77 |
download_csv_btn = gr.Button("📤 Descargar CSV")
|
78 |
+
status_output = gr.Textbox(label="Estado del análisis", interactive=False)
|
|
|
|
|
79 |
with gr.Tabs():
|
80 |
with gr.Tab("📊 Resumen"):
|
81 |
stats_output = gr.JSON(label="Estadísticas")
|
|
|
89 |
details_output = gr.JSON(label="Detalles por página")
|
90 |
with gr.Tab("🧠 SEO y Temas"):
|
91 |
seo_tags_output = gr.JSON(label="Metadatos SEO generados")
|
92 |
+
# Los siguientes se actualizan vía change en seo_tags_output
|
93 |
topics_output = gr.JSON(label="Temas inferidos")
|
94 |
flags_output = gr.JSON(label="Términos prohibidos detectados")
|
95 |
with gr.Tab("🔗 Similitud"):
|
96 |
similarity_output = gr.JSON(label="Similitud entre URLs")
|
97 |
+
with gr.Tab("📁 Archivos"):
|
98 |
+
file_dropdown = gr.Dropdown(label="Archivos en content_storage", choices=list_content_storage_files())
|
99 |
+
refresh_btn = gr.Button("Actualizar lista")
|
100 |
+
download_file_btn = gr.Button("Descargar Archivo Seleccionado", variant="secondary")
|
101 |
+
file_download = gr.File(label="Archivo Seleccionado")
|
102 |
+
def export_json() -> str:
|
|
|
|
|
|
|
103 |
if analyzer.current_analysis:
|
104 |
path = Path("content_storage/seo_report.json")
|
105 |
with open(path, "w", encoding="utf-8") as f:
|
106 |
+
json.dump(analyzer.current_analysis, f, indent=2, ensure_ascii=False)
|
107 |
return str(path)
|
108 |
return ""
|
109 |
+
def export_csv() -> str:
|
|
|
110 |
if not analyzer.current_analysis:
|
111 |
return ""
|
112 |
path = Path("content_storage/seo_summary.csv")
|
|
|
122 |
})
|
123 |
pd.DataFrame(data).to_csv(path, index=False)
|
124 |
return str(path)
|
|
|
125 |
analyze_btn.click(
|
126 |
+
fn=analyze_with_callbacks,
|
127 |
inputs=sitemap_input,
|
128 |
outputs=[
|
129 |
stats_output, recommendations_output, content_output,
|
130 |
links_output, details_output, similarity_output,
|
131 |
seo_tags_output, status_output
|
132 |
+
],
|
133 |
+
show_progress=True
|
134 |
)
|
135 |
clear_btn.click(fn=lambda: [None]*8, outputs=[
|
136 |
stats_output, recommendations_output, content_output,
|
|
|
142 |
links_output.change(fn=analyzer.plot_internal_links, inputs=links_output, outputs=links_plot)
|
143 |
seo_tags_output.change(fn=lambda: analyzer.current_analysis.get("topics", {}), outputs=topics_output)
|
144 |
seo_tags_output.change(fn=lambda: analyzer.current_analysis.get("flags", {}), outputs=flags_output)
|
145 |
+
refresh_btn.click(fn=refresh_file_list, outputs=file_dropdown)
|
146 |
+
download_file_btn.click(fn=download_storage_file, inputs=file_dropdown, outputs=file_download)
|
147 |
return demo
|
148 |
|
149 |
if __name__ == "__main__":
|