Actualización del 2025-06-18 a las 17:42:26
This commit is contained in:
jlimolina
parent
78c01fd61b
commit
e7c3433f0d
2 changed files with 2 additions and 78 deletions
77
app.py
77
app.py
|
|
@ -4,7 +4,7 @@ import hashlib
|
|||
import csv
|
||||
import math
|
||||
from io import StringIO, BytesIO
|
||||
from datetime import datetime, timedelta
|
||||
from datetime import datetime
|
||||
import logging
|
||||
import atexit
|
||||
import zipfile
|
||||
|
|
@ -91,10 +91,8 @@ def home():
|
|||
continentes = cursor.fetchall()
|
||||
cursor.execute("SELECT id, nombre, continente_id FROM paises ORDER BY nombre")
|
||||
paises = cursor.fetchall()
|
||||
|
||||
sql_params, conditions = [], []
|
||||
sql_base = "SELECT n.fecha, n.titulo, n.resumen, n.url, n.imagen_url, n.fuente_nombre, c.nombre AS categoria, p.nombre AS pais, co.nombre AS continente FROM noticias n LEFT JOIN categorias c ON n.categoria_id = c.id LEFT JOIN paises p ON n.pais_id = p.id LEFT JOIN continentes co ON p.continente_id = co.id"
|
||||
|
||||
if q:
|
||||
search_query = " & ".join(q.split())
|
||||
conditions.append("n.tsv @@ to_tsquery('spanish', %s)")
|
||||
|
|
@ -109,26 +107,20 @@ def home():
|
|||
sql_params.append(fecha_obj.date())
|
||||
except ValueError:
|
||||
flash("Formato de fecha no válido. Use AAAA-MM-DD.", "error")
|
||||
|
||||
if conditions: sql_base += " WHERE " + " AND ".join(conditions)
|
||||
|
||||
order_clause = " ORDER BY n.fecha DESC NULLS LAST"
|
||||
if q:
|
||||
search_query_ts = " & ".join(q.split())
|
||||
order_clause = " ORDER BY ts_rank(n.tsv, to_tsquery('spanish', %s)) DESC, n.fecha DESC"
|
||||
sql_params.append(search_query_ts)
|
||||
|
||||
sql_final = sql_base + order_clause + " LIMIT 50"
|
||||
cursor.execute(sql_final, tuple(sql_params))
|
||||
noticias = cursor.fetchall()
|
||||
|
||||
except psycopg2.Error as db_err:
|
||||
app.logger.error(f"[DB ERROR] Al leer noticias: {db_err}", exc_info=True)
|
||||
flash("Error de base de datos al cargar las noticias.", "error")
|
||||
|
||||
if request.headers.get('X-Requested-With') == 'XMLHttpRequest':
|
||||
return render_template('_noticias_list.html', noticias=noticias)
|
||||
|
||||
return render_template("noticias.html",
|
||||
noticias=noticias, categorias=categorias, continentes=continentes, paises=paises,
|
||||
cat_id=int(cat_id) if cat_id else None, cont_id=int(cont_id) if cont_id else None,
|
||||
|
|
@ -151,9 +143,6 @@ def dashboard():
|
|||
flash("Error al conectar con la base de datos.", "error")
|
||||
return render_template("dashboard.html", stats=stats)
|
||||
|
||||
|
||||
# --- GESTIÓN DE FEEDS ---
|
||||
|
||||
@app.route("/feeds/manage")
|
||||
def manage_feeds():
|
||||
page = request.args.get('page', 1, type=int)
|
||||
|
|
@ -191,7 +180,6 @@ def add_feed():
|
|||
app.logger.error(f"[DB ERROR] Al agregar feed: {db_err}", exc_info=True)
|
||||
flash(f"Error al añadir el feed: {db_err}", "error")
|
||||
return redirect(url_for("manage_feeds"))
|
||||
|
||||
categorias, paises = [], []
|
||||
try:
|
||||
with get_conn() as conn:
|
||||
|
|
@ -221,7 +209,6 @@ def edit_feed(feed_id):
|
|||
app.logger.error(f"[DB ERROR] Al actualizar feed: {db_err}", exc_info=True)
|
||||
flash(f"Error al actualizar el feed: {db_err}", "error")
|
||||
return redirect(url_for("manage_feeds"))
|
||||
|
||||
feed, categorias, paises = None, [], []
|
||||
try:
|
||||
with get_conn() as conn:
|
||||
|
|
@ -260,9 +247,6 @@ def reactivar_feed(feed_id):
|
|||
flash(f"Error al reactivar feed: {db_err}", "error")
|
||||
return redirect(url_for("manage_feeds"))
|
||||
|
||||
|
||||
# --- GESTIÓN DE FUENTES URL ---
|
||||
|
||||
@app.route("/urls/manage")
|
||||
def manage_urls():
|
||||
fuentes = []
|
||||
|
|
@ -295,7 +279,6 @@ def add_url_source():
|
|||
app.logger.error(f"[DB ERROR] Al agregar fuente URL: {db_err}", exc_info=True)
|
||||
flash(f"Error al añadir la fuente URL: {db_err}", "error")
|
||||
return redirect(url_for("manage_urls"))
|
||||
|
||||
categorias, paises = [], []
|
||||
try:
|
||||
with get_conn() as conn:
|
||||
|
|
@ -324,7 +307,6 @@ def edit_url_source(url_id):
|
|||
app.logger.error(f"[DB ERROR] Al actualizar fuente URL: {db_err}", exc_info=True)
|
||||
flash(f"Error al actualizar la fuente URL: {db_err}", "error")
|
||||
return redirect(url_for("manage_urls"))
|
||||
|
||||
fuente, categorias, paises = None, [], []
|
||||
try:
|
||||
with get_conn() as conn:
|
||||
|
|
@ -351,23 +333,13 @@ def delete_url_source(url_id):
|
|||
flash(f"Error al eliminar la fuente URL: {db_err}", "error")
|
||||
return redirect(url_for("manage_urls"))
|
||||
|
||||
|
||||
# --- TAREA DE FONDO (CORREGIDA Y REFACTORIZADA) ---
|
||||
|
||||
def fetch_and_store_all():
|
||||
"""
|
||||
Tarea de fondo única y cohesiva que recolecta noticias tanto de Feeds RSS como de Fuentes URL,
|
||||
y luego actualiza la base de datos en una sola transacción.
|
||||
"""
|
||||
with app.app_context():
|
||||
logging.info("--- INICIANDO CICLO DE CAPTURA GLOBAL (RSS y URL) ---")
|
||||
|
||||
todas_las_noticias = []
|
||||
feeds_fallidos = []
|
||||
feeds_exitosos = []
|
||||
feeds_para_actualizar_headers = []
|
||||
|
||||
# --- 1. PROCESAR FEEDS RSS ---
|
||||
logging.info("=> Parte 1: Procesando Feeds RSS...")
|
||||
feeds_to_process = []
|
||||
try:
|
||||
|
|
@ -379,7 +351,6 @@ def fetch_and_store_all():
|
|||
except psycopg2.Error as db_err:
|
||||
logging.error(f"Error de BD al obtener feeds RSS: {db_err}")
|
||||
return
|
||||
|
||||
if feeds_to_process:
|
||||
with ThreadPoolExecutor(max_workers=MAX_WORKERS) as executor:
|
||||
future_to_feed = {executor.submit(process_single_feed, dict(feed)): feed for feed in feeds_to_process}
|
||||
|
|
@ -400,11 +371,8 @@ def fetch_and_store_all():
|
|||
except Exception as exc:
|
||||
logging.error(f"Excepción en feed {original_feed_data['url']} (ID: {feed_id}): {exc}")
|
||||
feeds_fallidos.append(feed_id)
|
||||
|
||||
noticias_desde_rss_count = len(todas_las_noticias)
|
||||
logging.info(f"=> Parte 1 Finalizada. Noticias desde RSS: {noticias_desde_rss_count}. Éxitos: {len(feeds_exitosos)}. Fallos: {len(feeds_fallidos)}.")
|
||||
|
||||
# --- 2. PROCESAR FUENTES URL ---
|
||||
logging.info("=> Parte 2: Procesando Fuentes URL...")
|
||||
urls_to_process = []
|
||||
try:
|
||||
|
|
@ -415,7 +383,6 @@ def fetch_and_store_all():
|
|||
logging.info(f"Encontradas {len(urls_to_process)} fuentes URL para scrapear.")
|
||||
except Exception as e:
|
||||
logging.error(f"Error de BD al obtener fuentes URL: {e}")
|
||||
|
||||
if urls_to_process:
|
||||
for source in tqdm(urls_to_process, desc="Procesando Fuentes URL"):
|
||||
try:
|
||||
|
|
@ -427,17 +394,13 @@ def fetch_and_store_all():
|
|||
todas_las_noticias.extend(noticias_encontradas)
|
||||
except Exception as e:
|
||||
logging.error(f"Fallo al procesar la fuente URL {source['nombre']}: {e}")
|
||||
|
||||
noticias_desde_urls_count = len(todas_las_noticias) - noticias_desde_rss_count
|
||||
logging.info(f"=> Parte 2 Finalizada. Noticias encontradas desde URLs: {noticias_desde_urls_count}.")
|
||||
|
||||
# --- 3. ACTUALIZAR BD ---
|
||||
logging.info("=> Parte 3: Actualizando la base de datos...")
|
||||
if not any([todas_las_noticias, feeds_fallidos, feeds_exitosos, feeds_para_actualizar_headers]):
|
||||
logging.info("No se encontraron nuevas noticias ni cambios en los feeds. Nada que actualizar.")
|
||||
logging.info("--- CICLO DE CAPTURA GLOBAL FINALIZADO ---")
|
||||
return
|
||||
|
||||
try:
|
||||
with get_conn() as conn:
|
||||
with conn.cursor() as cursor:
|
||||
|
|
@ -448,7 +411,6 @@ def fetch_and_store_all():
|
|||
if feeds_exitosos:
|
||||
cursor.execute("UPDATE feeds SET fallos = 0 WHERE id IN %s", (tuple(feeds_exitosos),))
|
||||
logging.info(f"Reseteado contador de fallos para {len(feeds_exitosos)} feeds.")
|
||||
|
||||
if feeds_para_actualizar_headers:
|
||||
psycopg2.extras.execute_values(
|
||||
cursor,
|
||||
|
|
@ -456,7 +418,6 @@ def fetch_and_store_all():
|
|||
[(f['id'], f['etag'], f['modified']) for f in feeds_para_actualizar_headers]
|
||||
)
|
||||
logging.info(f"Actualizados headers para {len(feeds_para_actualizar_headers)} feeds.")
|
||||
|
||||
if todas_las_noticias:
|
||||
logging.info(f"Intentando insertar/ignorar {len(todas_las_noticias)} noticias en total.")
|
||||
insert_query = """
|
||||
|
|
@ -466,16 +427,11 @@ def fetch_and_store_all():
|
|||
"""
|
||||
psycopg2.extras.execute_values(cursor, insert_query, todas_las_noticias, page_size=200)
|
||||
logging.info(f"Inserción de noticias finalizada. {cursor.rowcount} filas podrían haber sido afectadas.")
|
||||
|
||||
logging.info("=> Parte 3 Finalizada. Base de datos actualizada correctamente.")
|
||||
except Exception as e:
|
||||
logging.error(f"Error de BD en la actualización masiva final: {e}", exc_info=True)
|
||||
|
||||
logging.info("--- CICLO DE CAPTURA GLOBAL FINALIZADO ---")
|
||||
|
||||
|
||||
# --- SECCIÓN DE BACKUPS Y RESTAURACIÓN ---
|
||||
|
||||
@app.route("/backup_feeds")
|
||||
def backup_feeds():
|
||||
try:
|
||||
|
|
@ -486,7 +442,6 @@ def backup_feeds():
|
|||
if not feeds_:
|
||||
flash("No hay feeds para exportar.", "warning")
|
||||
return redirect(url_for("dashboard"))
|
||||
|
||||
fieldnames = list(feeds_[0].keys())
|
||||
output = StringIO()
|
||||
writer = csv.DictWriter(output, fieldnames=fieldnames)
|
||||
|
|
@ -511,17 +466,14 @@ def backup_urls():
|
|||
ORDER BY f.id
|
||||
""")
|
||||
fuentes = cursor.fetchall()
|
||||
|
||||
if not fuentes:
|
||||
flash("No hay fuentes URL para exportar.", "warning")
|
||||
return redirect(url_for("dashboard"))
|
||||
|
||||
fieldnames = list(fuentes[0].keys())
|
||||
output = StringIO()
|
||||
writer = csv.DictWriter(output, fieldnames=fieldnames)
|
||||
writer.writeheader()
|
||||
writer.writerows([dict(fuente) for fuente in fuentes])
|
||||
|
||||
return Response(
|
||||
output.getvalue(),
|
||||
mimetype="text/csv",
|
||||
|
|
@ -542,7 +494,6 @@ def backup_noticias():
|
|||
if not noticias:
|
||||
flash("No hay noticias para exportar.", "warning")
|
||||
return redirect(url_for("dashboard"))
|
||||
|
||||
fieldnames_noticias = list(noticias[0].keys())
|
||||
output = StringIO()
|
||||
writer = csv.DictWriter(output, fieldnames=fieldnames_noticias)
|
||||
|
|
@ -569,7 +520,6 @@ def backup_completo():
|
|||
writer_feeds.writeheader()
|
||||
writer_feeds.writerows([dict(f) for f in feeds_data])
|
||||
zipf.writestr("feeds.csv", output_feeds.getvalue())
|
||||
|
||||
cursor.execute("SELECT * FROM fuentes_url ORDER BY id")
|
||||
fuentes_data = cursor.fetchall()
|
||||
if fuentes_data:
|
||||
|
|
@ -578,7 +528,6 @@ def backup_completo():
|
|||
writer_fuentes.writeheader()
|
||||
writer_fuentes.writerows([dict(f) for f in fuentes_data])
|
||||
zipf.writestr("fuentes_url.csv", output_fuentes.getvalue())
|
||||
|
||||
cursor.execute("SELECT * FROM noticias ORDER BY fecha DESC")
|
||||
noticias_data = cursor.fetchall()
|
||||
if noticias_data:
|
||||
|
|
@ -587,7 +536,6 @@ def backup_completo():
|
|||
writer_noticias.writeheader()
|
||||
writer_noticias.writerows([dict(n) for n in noticias_data])
|
||||
zipf.writestr("noticias.csv", output_noticias.getvalue())
|
||||
|
||||
memory_buffer.seek(0)
|
||||
return Response(memory_buffer, mimetype="application/zip", headers={"Content-Disposition": "attachment;filename=rss_backup_completo.zip"})
|
||||
except Exception as e:
|
||||
|
|
@ -649,7 +597,6 @@ def restore_urls():
|
|||
if not file or not file.filename.endswith(".csv"):
|
||||
flash("Archivo no válido. Sube un .csv.", "error")
|
||||
return redirect(url_for("restore_urls"))
|
||||
|
||||
try:
|
||||
file_stream = StringIO(file.read().decode("utf-8", errors='ignore'))
|
||||
reader = csv.DictReader(file_stream)
|
||||
|
|
@ -685,37 +632,15 @@ def restore_urls():
|
|||
cursor.execute("ROLLBACK TO SAVEPOINT restore_url_row")
|
||||
n_err += 1
|
||||
app.logger.error(f"Error procesando fila de fuente URL (se omite): {row} - Error: {e}")
|
||||
|
||||
flash(f"Restauración de Fuentes URL completada. Procesadas: {n_ok}. Errores: {n_err}.", "success" if n_err == 0 else "warning")
|
||||
except Exception as e:
|
||||
app.logger.error(f"Error al restaurar fuentes URL desde CSV: {e}", exc_info=True)
|
||||
flash(f"Ocurrió un error general al procesar el archivo: {e}", "error")
|
||||
|
||||
return redirect(url_for("dashboard"))
|
||||
|
||||
return render_template("restore_urls.html")
|
||||
|
||||
|
||||
# --- RUTA DE UTILIDAD PARA PRUEBAS ---
|
||||
# MOVIDA FUERA DEL BLOQUE if __name__ == '__main__' PARA QUE GUNICORN LA RECONOZCA
|
||||
@app.route("/run-fetch")
|
||||
def run_fetch_now():
|
||||
"""Ejecuta la tarea de recolección manualmente para pruebas."""
|
||||
try:
|
||||
# Idealmente, esto debería correr en un hilo separado para no bloquear la respuesta
|
||||
# pero para una ejecución manual simple, está bien así.
|
||||
fetch_and_store_all()
|
||||
flash("Tarea de fondo de recolección ejecutada manualmente.", "info")
|
||||
except Exception as e:
|
||||
flash(f"Error al ejecutar la tarea de fondo: {e}", "error")
|
||||
app.logger.error(f"Error en la ejecución manual de la tarea de fondo: {e}", exc_info=True)
|
||||
return redirect(url_for('dashboard'))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
if not db_pool:
|
||||
app.logger.error("La aplicación no puede arrancar sin una conexión a la base de datos.")
|
||||
sys.exit(1)
|
||||
|
||||
# El app.run solo se usa para el desarrollo local. Gunicorn no ejecuta esta parte.
|
||||
app.run(host="0.0.0.0", port=8000, debug=True)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue