Avanzado en desarrollo de capturing task. Creado clase GeocodingTask

This commit is contained in:
pablomartincalvo 2018-09-26 22:56:45 +02:00
parent 1d68575fd7
commit 9d947f7e2b
3 changed files with 152 additions and 52 deletions

94
.idea/workspace.xml generated
View file

@ -2,6 +2,7 @@
<project version="4">
<component name="ChangeListManager">
<list default="true" id="6e2fbba0-85ff-42d6-8e70-e4cdef1000c8" name="Default Changelist" comment="">
<change afterPath="$PROJECT_DIR$/capturer/geocoder.py" afterDir="false" />
<change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
<change beforePath="$PROJECT_DIR$/capturer/capturer.py" beforeDir="false" afterPath="$PROJECT_DIR$/capturer/capturer.py" afterDir="false" />
</list>
@ -15,36 +16,36 @@
<session id="1687213926">
<usages-collector id="statistics.lifecycle.project">
<counts>
<entry key="project.closed" value="2" />
<entry key="project.closed" value="3" />
<entry key="project.open.time.0" value="1" />
<entry key="project.open.time.12" value="1" />
<entry key="project.open.time.13" value="2" />
<entry key="project.open.time.14" value="2" />
<entry key="project.open.time.14" value="3" />
<entry key="project.open.time.21" value="1" />
<entry key="project.opened" value="7" />
<entry key="project.opened" value="8" />
</counts>
</usages-collector>
<usages-collector id="statistics.file.extensions.open">
<counts>
<entry key="py" value="14" />
<entry key="py" value="15" />
</counts>
</usages-collector>
<usages-collector id="statistics.file.types.open">
<counts>
<entry key="Python" value="14" />
<entry key="Python" value="15" />
</counts>
</usages-collector>
<usages-collector id="statistics.file.extensions.edit">
<counts>
<entry key="Python Console" value="1519" />
<entry key="py" value="6444" />
<entry key="txt" value="647" />
<entry key="py" value="8493" />
<entry key="txt" value="692" />
</counts>
</usages-collector>
<usages-collector id="statistics.file.types.edit">
<counts>
<entry key="PLAIN_TEXT" value="647" />
<entry key="Python" value="7963" />
<entry key="PLAIN_TEXT" value="692" />
<entry key="Python" value="10012" />
</counts>
</usages-collector>
<usages-collector id="statistics.vcs.git.usages">
@ -64,13 +65,27 @@
<file pinned="false" current-in-tab="true">
<entry file="file://$PROJECT_DIR$/capturer/capturer.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="377">
<caret line="164" column="8" selection-start-line="164" selection-start-column="8" selection-end-line="164" selection-end-column="8" />
<state relative-caret-position="2325">
<caret line="155" lean-forward="true" selection-start-line="155" selection-end-line="155" />
<folding>
<marker date="1537729307226" expanded="true" signature="1206:1207" ph="..." />
<marker date="1537729307226" expanded="true" signature="4143:4296" ph="..." />
<marker date="1537729307226" expanded="true" signature="4911:5209" ph="..." />
<marker date="1537729307226" expanded="true" signature="5383:5398" ph="..." />
<marker date="1537995271039" expanded="true" signature="1249:1250" ph="..." />
<marker date="1537995271039" expanded="true" signature="4109:4257" ph="..." />
<marker date="1537995271039" expanded="true" signature="4640:4938" ph="..." />
<marker date="1537995271039" expanded="true" signature="5089:5094" ph="..." />
</folding>
</state>
</provider>
</entry>
</file>
<file pinned="false" current-in-tab="false">
<entry file="file://$PROJECT_DIR$/capturer/geocoder.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="77">
<caret line="17" column="14" selection-start-line="17" selection-start-column="14" selection-end-line="17" selection-end-column="14" />
<folding>
<marker date="1537995271051" expanded="true" signature="519:524" ph="..." />
<marker date="1537995271051" expanded="true" signature="708:826" ph="..." />
<marker date="1537995271051" expanded="true" signature="1349:1354" ph="..." />
</folding>
</state>
</provider>
@ -152,6 +167,7 @@
<option value="$PROJECT_DIR$/core/task.py" />
<option value="$PROJECT_DIR$/capturer/__init__.py" />
<option value="$PROJECT_DIR$/explorer/explorer.py" />
<option value="$PROJECT_DIR$/capturer/geocoder.py" />
<option value="$PROJECT_DIR$/capturer/capturer.py" />
</list>
</option>
@ -289,7 +305,14 @@
<option name="project" value="LOCAL" />
<updated>1537653361355</updated>
</task>
<option name="localTasksCounter" value="6" />
<task id="LOCAL-00006" summary="Avanzado en desarrollo de capturing task.">
<created>1537729440310</created>
<option name="number" value="00006" />
<option name="presentableId" value="LOCAL-00006" />
<option name="project" value="LOCAL" />
<updated>1537729440311</updated>
</task>
<option name="localTasksCounter" value="7" />
<servers />
</component>
<component name="TodoView" selected-index="1">
@ -305,8 +328,8 @@
<frame x="0" y="-2" width="1920" height="1082" extended-state="6" />
<editor active="true" />
<layout>
<window_info content_ui="combo" id="Project" order="0" sideWeight="0.48826292" visible="true" weight="0.14918292" />
<window_info id="Structure" order="1" sideWeight="0.5117371" side_tool="true" visible="true" weight="0.14918292" />
<window_info content_ui="combo" id="Project" order="0" sideWeight="0.48669797" visible="true" weight="0.14918292" />
<window_info id="Structure" order="1" sideWeight="0.513302" side_tool="true" visible="true" weight="0.14918292" />
<window_info id="Favorites" order="2" sideWeight="0.5015674" side_tool="true" weight="0.14918292" />
<window_info active="true" id="Repositories" order="3" sideWeight="0.49529782" visible="true" weight="0.32999474" />
<window_info anchor="bottom" id="Message" order="0" />
@ -361,7 +384,8 @@
<MESSAGE value="Refactorizado Explorer para que el Explorer, y no el exploring_task, se encargue de postear las tareas de captura.&#10;&#10;Creado una funcion independiente de creacion de capturas para que sea compartida entre todos aquellos servicios que las creen." />
<MESSAGE value="Corregidos pequeños errores y type tras primer test del servicio." />
<MESSAGE value="Iniciadas clases de capturing_task y scraptargetfield." />
<option name="LAST_COMMIT_MESSAGE" value="Iniciadas clases de capturing_task y scraptargetfield." />
<MESSAGE value="Avanzado en desarrollo de capturing task." />
<option name="LAST_COMMIT_MESSAGE" value="Avanzado en desarrollo de capturing task." />
</component>
<component name="editorHistoryManager">
<entry file="file://$PROJECT_DIR$/explorer/test_explorer.py" />
@ -383,6 +407,16 @@
<entry file="file://$PROJECT_DIR$/capturer/__init__.py">
<provider selected="true" editor-type-id="text-editor" />
</entry>
<entry file="file://$PROJECT_DIR$/explorer/explorer.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="75">
<caret line="5" selection-start-line="5" selection-end-line="5" selection-end-column="22" />
<folding>
<marker date="1537653289735" expanded="true" signature="5088:5540" ph="..." />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/core/mysql_wrapper.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="540">
@ -400,25 +434,27 @@
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/explorer/explorer.py">
<entry file="file://$PROJECT_DIR$/capturer/geocoder.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="75">
<caret line="5" selection-start-line="5" selection-end-line="5" selection-end-column="22" />
<state relative-caret-position="77">
<caret line="17" column="14" selection-start-line="17" selection-start-column="14" selection-end-line="17" selection-end-column="14" />
<folding>
<marker date="1537653289735" expanded="true" signature="5088:5540" ph="..." />
<marker date="1537995271051" expanded="true" signature="519:524" ph="..." />
<marker date="1537995271051" expanded="true" signature="708:826" ph="..." />
<marker date="1537995271051" expanded="true" signature="1349:1354" ph="..." />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/capturer/capturer.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="377">
<caret line="164" column="8" selection-start-line="164" selection-start-column="8" selection-end-line="164" selection-end-column="8" />
<state relative-caret-position="2325">
<caret line="155" lean-forward="true" selection-start-line="155" selection-end-line="155" />
<folding>
<marker date="1537729307226" expanded="true" signature="1206:1207" ph="..." />
<marker date="1537729307226" expanded="true" signature="4143:4296" ph="..." />
<marker date="1537729307226" expanded="true" signature="4911:5209" ph="..." />
<marker date="1537729307226" expanded="true" signature="5383:5398" ph="..." />
<marker date="1537995271039" expanded="true" signature="1249:1250" ph="..." />
<marker date="1537995271039" expanded="true" signature="4109:4257" ph="..." />
<marker date="1537995271039" expanded="true" signature="4640:4938" ph="..." />
<marker date="1537995271039" expanded="true" signature="5089:5094" ph="..." />
</folding>
</state>
</provider>

View file

@ -5,7 +5,7 @@ from time import sleep
from core.mysql_wrapper import get_anunciosdb, get_tasksdb
from core.scrapping_utils import UrlAttack
from core.alerts import alert_master
from capturer.geocoder import GeocodingTask
ads_root = 'https://www.idealista.com/inmueble/'
@ -40,7 +40,8 @@ class CapturingTask:
self.uuid = parameters['uuid']
self.ad_url = parameters['ad_url']
self.uuid_exploring = parameters['uuid_exploring']
self.request_failures = 0
self.request_failures = 1
self.geocode_status = "Pending"
self.tasksdb = get_tasksdb()
@ -76,15 +77,12 @@ class CapturingTask:
self._read_fields()
while self.request_failures < 4:
while self.request_failures < 3:
attack = UrlAttack(self.ad_url)
attack.attack()
if attack.success():
self.html = attack.get_text()
if not self._html_is_valid():
alert_master('ERROR CAPTURER',
'El HTML de una pagina de anuncio es invalido')
with self._fields_not_present() as missing_fields:
if missing_fields:
@ -107,6 +105,9 @@ class CapturingTask:
#Geocodear
self.geocode()
#TODO Lidiar con el resultado del geocoding
#TODO Manejar tema cache
else:
self.request_failures += 1
self._update_status('Fail {}'.format(self.request_failures))
@ -121,18 +122,6 @@ class CapturingTask:
for field_parameters in ad_fields_parameters:
self.fields.append(ScrapTargetField(field_parameters))
def _html_is_valid(self, 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, html=self.html):
"""
Lee el HTML y devuelve los campos que no esten presentes
@ -161,14 +150,35 @@ class CapturingTask:
for field in self.fields:
self.ad_data[field.name] = field.get_value(self.html)
def geocode(self):
#TODO Construir metodo de Geocoding. Quizas en otra clase?
pass
def get_ad_data(self):
return self.ad_data
def geocode(self):
# Construir direccion con formato adecuado
geocode_tries = 0
geo_task = GeocodingTask(formated_address)
while geocode_tries < 3:
geo_task.geocode()
if geo_task.get_request_status() == 200:
google_status = geo_task.success_surrender_retry()
if google_status == 'Success':
self.geocode_status = 'Success'
self.geocode_results = geo_task.get_results()
return
elif google_status == 'Surrender':
self.geocode_status = 'Surrender'
return
elif google_status == 'Retry':
geocode_tries += 1
self.geocode_status = 'Surrender'
return
class ScrapTargetField:

54
capturer/geocoder.py Normal file
View file

@ -0,0 +1,54 @@
import requests
class GeocodingTask:
url = 'https://maps.googleapis.com/maps/api/geocode/json'
request_parameters = {'region': 'es',
'key': 'AIzaSyCnKj0WnsxVZcaoxeAYkuRw3cKRNGiISYA'}
geocoding_status_success = ['OK']
geocoding_status_surrender = ['ZERO_RESULTS']
geocoding_status_retry = ['OVER_QUERY_LIMIT',
'REQUEST_DENIED',
'INVALID_REQUEST',
'UNKNOWN_ERROR']
def __init__(self, address):
request_paremeters['address'] = address
def geocode(self):
"""
Lanza la peticion de gecoding al servicio de google
"""
self.response = requests.get(url, request_parameters)
self.response_json = self.response.json()
def get_request_status(self):
"""
Devuelve el status HTTP de la request
"""
return self.response.status_code
def success_surrender_retry(self):
"""
Devuelve el estado del resultado desde el punto de vista de Google
"""
if self.response_json['status'] in geocoding_status_success:
return "Success"
elif self.response_json['status'] in geocoding_status_surrender:
return "Surrender"
else:
return "Retry"
def get_results(self):
"""
Extrae los resultados del JSON de respuesta y los devuelve
"""
results = {'latitude': self.response_json['results'][0]['geometry']['location']['lat'],
'longitude': self.response_json['results'][0]['geometry']['location']['lon'],
'precision': self.response_json['results'][0]['geometry']['location_type']}
return results