Add database migration scripts and update models for JSON support

admin_tools.py

@@ -0,0 +1,26 @@
+from sqlalchemy.orm import sessionmaker
+from crawler_db_model import WebsPorVisitar, WebsVisitadas, engine
+
+# Crear sesión de base de datos
+Session = sessionmaker(bind=engine)
+session = Session()
+
+def limpiar_base_datos():
+    """Elimina todos los registros de las tablas webs_por_visitar y webs_visitadas."""
+    try:
+        # Eliminar todos los registros de WebsPorVisitar
+        session.query(WebsPorVisitar).delete()
+        # Eliminar todos los registros de WebsVisitadas
+        session.query(WebsVisitadas).delete()
+
+        # Confirmar cambios
+        session.commit()
+        print("La base de datos ha sido limpiada completamente.")
+    except Exception as e:
+        print(f"Error al limpiar la base de datos: {e}")
+        session.rollback()
+
+if __name__ == "__main__":
+    # Limpiar la base de datos cuando se ejecuta este script directamente
+    # limpiar_base_datos()
+    pass

alembic.ini

@@ -0,0 +1,117 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+script_location = alembic
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python>=3.9 or backports.zoneinfo library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to alembic/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:alembic/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+# version_path_separator = newline
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+sqlalchemy.url = postgresql://postgres:oL2YGslA8BlnDqEzgg1k6fF82kkibA@localhost:5432/webpages
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

alembic/README

@@ -0,0 +1 @@
+Generic single-database configuration.

alembic/env.py

@@ -0,0 +1,81 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+
+from crawler_db_model import Base
+
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+target_metadata = Base.metadata
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

alembic/script.py.mako

@@ -0,0 +1,26 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

alembic/versions/71e5651bf6a8_add_detalles_json_column.py

@@ -0,0 +1,32 @@
+"""Add detalles_json column
+
+Revision ID: 71e5651bf6a8
+Revises: 
+Create Date: 2024-12-19 23:54:41.284998
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = '71e5651bf6a8'
+down_revision: Union[str, None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('webs_visitadas', sa.Column('detalles_json', sa.JSON(), nullable=True))
+    op.drop_column('webs_visitadas', 'es_dinamico')
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('webs_visitadas', sa.Column('es_dinamico', sa.BOOLEAN(), autoincrement=False, nullable=True))
+    op.drop_column('webs_visitadas', 'detalles_json')
+    # ### end Alembic commands ###

crawler.py

@@ -62,14 +62,18 @@ def generate_summary(soup):
     # Extraer texto de párrafos principales
     paragraphs = [p.get_text(strip=True) for p in soup.find_all('p')][:5]
 
+    # Generar un resumen en texto plano
+    resumen_texto = f"Título: {titulo}. Descripción: {descripcion}. Encabezados: {', '.join(headers['h1'][:3])}."
+
     # Resumen estructurado
-    summary = {
+    summary_json = {
         "titulo": titulo,
         "descripcion": descripcion,
         "encabezados": headers,
         "parrafos": paragraphs
     }
-    return summary
+
+    return resumen_texto, summary_json
 
 def process_url(url):
     """Procesa una URL: extrae datos y las inserta en las tablas correspondientes."""
@@ -86,7 +90,7 @@ def process_url(url):
 
         soup = BeautifulSoup(response.text, 'html.parser')
         dominio = urlparse(url).netloc
-        summary = generate_summary(soup)
+        resumen_texto, resumen_json = generate_summary(soup)
         ip = requests.get(f"https://api.ipify.org?domain={dominio}&format=json").json().get('ip', "")
         contenido_hash = hash_content(response.text)
 
@@ -94,8 +98,8 @@ def process_url(url):
         visitada = WebsVisitadas(
             url=url,
             dominio=dominio,
-            titulo=summary['titulo'],
-            resumen=f"Descripción: {summary['descripcion']}, Encabezados: {summary['encabezados']}, Párrafos: {summary['parrafos']}",
+            titulo=resumen_json['titulo'],
+            resumen=resumen_texto,  # Resumen en texto plano
             ip=ip,
             codigo_http=status_code,
             contenido_hash=contenido_hash
@@ -133,7 +137,7 @@ def crawl():
 
 if __name__ == "__main__":
     # URL inicial
-    url_inicial = "http://example.com"
+    url_inicial = "https://datos.bancomundial.org/"
 
     # Insertar URL inicial si no existe
     if not session.query(WebsPorVisitar).filter_by(url=url_inicial).first():

crawler_db_model.py

@@ -1,6 +1,7 @@
 from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime, Boolean
 from sqlalchemy.ext.declarative import declarative_base
 from sqlalchemy.orm import sessionmaker
+from sqlalchemy import JSON
 from datetime import datetime
 from dotenv import load_dotenv
 import os
@@ -22,12 +23,12 @@ class WebsVisitadas(Base):
     url = Column(String(2048), unique=True, nullable=False)
     dominio = Column(String(255), nullable=False)
     titulo = Column(String(255), nullable=True)
-    resumen = Column(Text, nullable=True)
-    ip = Column(String(45), nullable=True)  # IPv4 o IPv6
+    resumen = Column(Text, nullable=True)  # Resumen en texto plano
+    detalles_json = Column(JSON, nullable=True)  # JSON estructurado
+    ip = Column(String(45), nullable=True)
     fecha_creacion = Column(DateTime, default=datetime.utcnow, nullable=False)
-    codigo_http = Column(Integer, nullable=True)  # Código de respuesta HTTP
-    contenido_hash = Column(String(64), nullable=True)  # Hash del contenido para detectar cambios
-    es_dinamico = Column(Boolean, default=False)  # Si es una página generada dinámicamente
+    codigo_http = Column(Integer, nullable=True)
+    contenido_hash = Column(String(64), nullable=True)
 
 # Cargar variables de entorno desde el archivo .env
 load_dotenv()