Docker gunicorn supp and env setup

.dockerignore

@@ -0,0 +1,8 @@
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.env
+venv/
+.envrc
+.git

.gitignore

@@ -0,0 +1,58 @@
+# === Python build artifacts ===
+*.pyc
+*.pyo
+*.pyd
+__pycache__/
+**/__pycache__/
+*.egg-info/
+dist/
+build/
+*.log
+
+# === SQLite & output files ===
+*.sqlite3
+*.db
+output.json
+
+# === Environment variables ===
+.env
+.env.*
+*.env
+
+# === Virtual environments ===
+venv/
+.venv/
+.env/
+
+# === VSCode project settings ===
+.vscode/
+
+# === macOS system files ===
+.DS_Store
+
+# === Pytest and test cache ===
+htmlcov/
+.coverage
+.cache/
+pytest_cache/
+.tox/
+
+# === Jupyter Notebook ===
+.ipynb_checkpoints/
+
+# === Django migration artifacts (optional to ignore) ===
+# Uncomment the lines below if you want to regenerate migrations often
+# **/migrations/*.py
+# **/migrations/*.pyc
+# !**/migrations/__init__.py
+
+# === FastAPI-specific artifacts ===
+fastapi_email/email_db.sqlite3
+
+# === IDE-specific ===
+.idea/
+*.sublime-project
+*.sublime-workspace
+
+# === GitHub Codespaces or devcontainers ===
+.devcontainer/

.vscode/settings.json

@@ -0,0 +1,14 @@
+{
+    "python.analysis.extraPaths": [
+        "./webscraper/ABC"
+    ],
+    "python.testing.unittestArgs": [
+        "-v",
+        "-s",
+        "./webscraper",
+        "-p",
+        "*test*.py"
+    ],
+    "python.testing.pytestEnabled": false,
+    "python.testing.unittestEnabled": true
+}

Dockerfile

@@ -0,0 +1,18 @@
+FROM continuumio/miniconda3
+
+WORKDIR /app
+
+COPY environment.yml .
+
+RUN conda install -n base -c conda-forge mamba && \
+    mamba env update -n base -f environment.yml && \
+    conda clean --all --yes
+
+COPY . .
+
+ENV PYTHONUNBUFFERED=1
+
+EXPOSE 8000
+
+CMD ["gunicorn", "--bind", "0.0.0.0:8000", "wsgi_entry:application"]
+

README.md

@@ -11,7 +11,7 @@ Initial Landing page![Initial Landing page](https://github.com/user-attachments/
 
 -To run the scraper, execute the main.py script by running the command 
 
-python src/main.py
+python main.py
 
 -Make sure you are in the webscraper directory when you run the command  
 
@@ -25,3 +25,15 @@ if __name__ == "__main__":
 ##what file needs to be located and what variables would need to be changed if you wanted to scrape another website?
 
 -If you wanted to scrape another website, you need to locate the file main.py and change the variables “scraper” and “pages” to whatever website you wanted and the new URl paths. As well ensure the website allows scraping.
+
+
+
+Documentation on connecting the database to vscode with the postgres extension
+
+1. Install the PostgreSQL Extension  in VSCode
+2. Make sure PostgreSQL is Running Locally
+3. click the extension on the left sidebar
+4. click the plus button and create a new connection
+5. fill in the needed information, server = localhost, database = cheaper_local, User = postgres, port = 5432 (default), password  = the password you made when installing PostgreSQL
+7. You should be connected now and see a message and see the conencted database in the extension now.
+

accounts/__init__.py

@@ -0,0 +1 @@
+# test

accounts/migrations/0002_remove_product_name_remove_product_source_url_and_more.py

@@ -0,0 +1,55 @@
+# Generated by Django 5.2 on 2025-05-05 19:14
+
+import django.db.models.deletion
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("accounts", "0001_initial"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="product",
+            name="name",
+        ),
+        migrations.RemoveField(
+            model_name="product",
+            name="source_url",
+        ),
+        migrations.RemoveField(
+            model_name="useraccount",
+            name="password",
+        ),
+        migrations.AddField(
+            model_name="product",
+            name="product_name",
+            field=models.CharField(default="Unnamed Product", max_length=255),
+        ),
+        migrations.AddField(
+            model_name="product",
+            name="url",
+            field=models.TextField(default="https://example.com"),
+        ),
+        migrations.AddField(
+            model_name="product",
+            name="user",
+            field=models.ForeignKey(
+                null=True,
+                on_delete=django.db.models.deletion.CASCADE,
+                to="accounts.useraccount",
+            ),
+        ),
+        migrations.AddField(
+            model_name="useraccount",
+            name="password_hash",
+            field=models.CharField(default="defaultpass123", max_length=100),
+        ),
+        migrations.AlterField(
+            model_name="product",
+            name="price",
+            field=models.DecimalField(decimal_places=2, default=0.0, max_digits=10),
+        ),
+    ]

accounts/models.py

@@ -14,18 +14,21 @@ def validate_email(value):
 
 class UserAccount(models.Model):
     email = models.EmailField(max_length=50, unique=True)
-    password = models.CharField(max_length=100)  
+    password_hash = models.CharField(max_length=100)
+    # password_hash = models.CharField(max_length=100, default='defaultpass123')  # added default
 
     def clean(self):
         validate_email(self.email)
 
     def __str__(self):
         return self.email
 
+
 class Product(models.Model):
-    name = models.CharField(max_length=200)
-    price = models.CharField(max_length=10)
-    source_url = models.URLField(max_length=150)
+    product_name = models.CharField(max_length=255, default='Unnamed Product')
+    price = models.DecimalField(max_digits=10, decimal_places=2, default=0.00)
+    url = models.TextField(default='https://example.com')
+    user = models.ForeignKey(UserAccount, on_delete=models.CASCADE, null=True)  
 
     def __str__(self):
-        return self.name
+        return self.product_name

accounts/views.py

@@ -1,3 +1,10 @@
 from django.shortcuts import render
+from django.http import JsonResponse
+from .models import Product
+
+def product_list(request):
+    products = Product.objects.all()
+    data = [{"name": p.product_name, "price": float(p.price), "url": p.url} for p in products]
+    return JsonResponse(data, safe=False)
 
 # Create your views here.

cheaper/urls.py

@@ -16,7 +16,9 @@
 """
 from django.contrib import admin
 from django.urls import path
+from accounts.views import product_list
 
 urlpatterns = [
     path('admin/', admin.site.urls),
+    path('', product_list, name='product_list'),  # This sets the homepage
 ]

dockerREADME.md

@@ -0,0 +1,77 @@
+# Docker Deployment Guide
+
+### 1. Prerequisites
+
+- Install [Docker Desktop](https://www.docker.com/products/docker-desktop)
+- Make sure Docker Engine is running
+
+### 2. Project Structure (Relevant Parts)
+
+```
+cheaper/
+├── cheaper/
+│   └── wsgi.py
+├── environment.yml
+├── Dockerfile
+├── .dockerignore
+├── main.py
+├── setup.py
+└── ...
+```
+
+---
+
+### 3. Dockerfile
+
+We're using Miniconda and `environment.yml` (not `requirements.txt`) for dependency management.
+
+```dockerfile
+FROM continuumio/miniconda3:latest
+
+WORKDIR /app
+
+COPY environment.yml .
+
+RUN conda install -n base -c conda-forge mamba && \
+    mamba env update -n base -f environment.yml && \
+    conda clean --all --yes
+
+COPY . .
+
+# ⏱️ Gunicorn timeout is increased to handle long scraping time
+CMD ["gunicorn", "--timeout", "120", "cheaper.wsgi:application", "-b", "0.0.0.0:8000"]
+```
+
+---
+
+### 4. .dockerignore
+
+```dockerignore
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+env/
+venv/
+.git
+```
+
+---
+
+### 5. Build and Run
+
+```bash
+# Build the Docker image
+docker build -t cheaper-app .
+
+# Run the container on port 8000
+docker run --rm -p 8000:8000 cheaper-app
+```
+
+Open [http://localhost:8000](http://localhost:8000) — you should see:
+
+```
+Scraping complete.
+```
+
+---

environment.yml

@@ -12,3 +12,4 @@ dependencies:
   - pip:
     - beautifulsoup4
     - lxml
+    - gunicorn

setup.py

@@ -0,0 +1,29 @@
+from setuptools import setup, find_packages
+
+setup(
+    name='cheaper',
+    version='0.1',
+    packages=find_packages(exclude=["tests", "*.tests", "*.tests.*", "tests.*"]),
+    include_package_data=True,
+    install_requires=[
+        "beautifulsoup4",
+        "lxml",
+        "flask",
+        "pandas",
+        "numpy",
+        "requests",
+        "gunicorn",
+    ],
+    entry_points={
+        'console_scripts': [
+            'cheaper=webscraper.main:main',
+        ],
+    },
+
+    description='cheaper for now',
+    classifiers=[
+        'Programming Language :: Python :: 3',
+        'Operating System :: OS Independent',
+    ],
+    python_requires='>=3.10',
+)

webscraper/ABC/Ebay_API.py

@@ -0,0 +1,15 @@
+from abc import ABC,abstractmethod
+
+class EbayApi(ABC):
+
+    @abstractmethod
+    def retrieve_access_token() -> str:
+        """ retrieves the user access token for sandbox environment it's a long line
+            of text, numbers, symbols
+        """
+        pass
+
+    @abstractmethod
+    def retrieve_ebay_response(httprequest:str,query:str) -> dict:
+        """ retrieves a json of large data with category ids, names, parentcategorynodes """
+        pass