Hooking up models to the browser connection

requirements.txt

@@ -4,3 +4,4 @@ requests
 lxml
 django
 django-rest-framework
+psycopg2

restscrape/models.py

@@ -1,10 +1,13 @@
-import datetime
 from urllib.parse import quote_plus
+import datetime
 
 from django.core.files.base import ContentFile
 from django.db import models
+import django.contrib.postgres.fields as extended_fields
 import pytz
 
+from restscrape.scraping.browser import BrowserConnection
+
 # Create your models here.
 
 
@@ -38,3 +41,23 @@ class Page(models.Model):
     def delete(self):
         self.page_content.delete()
         super().delete()
+
+
+class Browser(models.Model):
+    address = models.CharField(max_length=None)
+    proxy = models.URLField(max_length=None)
+    use_adblock = models.BooleanField()
+
+    def delete(self):
+        try:
+            browser_handle = BrowserConnection(self.address)
+            browser_handle.close()
+        except Exception:
+            pass
+        super().delete()
+
+
+class ScrapeRequet(models.Model):
+    xpath_labels = extended_fields.HStoreField()
+    blocking = models.BooleanField()
+    submit_time = models.DateTimeField(auto_now=True)

restscrape/utils.py

@@ -0,0 +1,15 @@
+from restscrape.models import Browser
+from restscrape.scraping.browser import start_browser, BrowserConnection
+
+
+def get_tab(proxy, use_adblock=True):
+    try:
+        matching_browser = Browser.objects.get(proxy=proxy, use_adblock=use_adblock)
+        browser_connection = BrowserConnection(address=matching_browser.address)
+    except Browser.DoesNotExist:
+        browser_connection = start_browser(proxy=proxy, use_adblock=use_adblock)
+        created_browser = Browser(
+            address=browser_connection.address, proxy=proxy, use_adblock=use_adblock
+        )
+        created_browser.save()
+    return browser_connection.create_tab()