Iniciadas clases de capturing_task y scraptargetfield.

capturer/capturer.py

@@ -1,7 +1,13 @@
+import sys
+sys.path.append('..')
 import uuid
+from core.mysql_wrapper import get_anunciosdb, get_tasksdb
+from core.scrapping_utils import UrlAttack
 
 ads_root = 'https://www.idealista.com/inmueble/'
 
+#TODO Crear la lista de campos
+
 
 def create_capturing_task(referencia, db_wrapper, uuid_exploring=None):
 
@@ -19,6 +25,98 @@ def create_capturing_task(referencia, db_wrapper, uuid_exploring=None):
                             (uuid,  write_time, status, url, fk_uuid_exploring)
                             VALUES (%(uuid)s, NOW(), %(status)s, %(ad_url)s, %(uuid_exploring)s)"""
 
-
     db_wrapper.query(query_statement, query_parameters)
 
+class CapturingTask:
+
+    def __init__(self, parameters):
+        self.uuid = parameters['uuid']
+        self.status = 'Loading'
+        self.ad_url = parameters['ad_url']
+        self.uuid_exploring = parameters['uuid_exploring']
+
+        self.tasksdb = get_tasksdb()
+
+        self._log_in_tasksdb()
+
+    def _update_status(self, new_status):
+        self.status = new_status
+        self._log_in_tasksdb()
+
+    def _log_in_tasksdb(self):
+        """
+        Graba en la base de datos de tareas un registro con el UUID de la tarea,
+        un timestamp y el status
+        """
+
+        query_statement = """INSERT INTO capturing_tasks_logs
+                            (uuid, write_time, status, ad_url, fk_uuid_exploring)
+                            VALUES (%(uuid)s, NOW(), %(status)s, %(ad_url)s, %(fk_uuid_exploring)s)"""
+
+        query_parameters = {'uuid': self.uuid,
+                            'status': self.status,
+                            'ad_url': self.ad_url,
+                            'fk_uuid_exploring': self.uuid_exploring}
+
+        self.tasksdb.query(query_statement, query_parameters)
+
+    def capture(self):
+        """
+        Metodo principal que contiene el flujo de captura
+        """
+        #TODO Desarrollar flujo de captura
+
+
+    def _html_is_valid(selfself, html=self.html):
+        """
+        Lee el HTML y aplica normas de validación del contenido
+        """
+
+        #TODO Comprobar si HTML es pagina de bloqueo
+
+
+        #TODO Check de longitud
+        pass
+
+    def _fields_not_present(self, field_list, html=self.html):
+        """
+        Lee el HTML y devuelve los campos que no esten presentes
+        """
+        fields_not_present = []
+        for field_parameters in field_list:
+            field = ScrapTargetField(field_parameters)
+        if not field.exists(html):
+            fields_not_present.append(field.name)
+
+        return fields_not_present
+
+
+class ScrapTargetField:
+
+    def __init__(self, target_parameters):
+        self.name = target_parameters['name']
+        self.search_method = target_parameters['search_method']
+        self.validation_method = target_parameters['validation_method']
+
+    def exists(self, html):
+        """
+        Busca el dato en un HTML
+        """
+        if self.search_method(html) is None:
+            return False
+        else:
+            return True
+
+    def validate_value(self, dato):
+        """
+        Comprueba el valor y valida con la norma respectiva que sea lo esperado
+        """
+        return self.validation_method(dato)
+
+    def get_value(self, html):
+        """
+        Busca en un HTML el dato
+        """
+        return self.search_method(html)
+
+