diff --git a/Dockerfile b/Dockerfile
index ada29f9..bdb3b87 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -16,7 +16,7 @@ COPY /requirements/* /app/requirements/
 RUN pip install -r /app/requirements/dev.txt
 
 # pyppeteer deps (https://stackoverflow.com/a/71935536)
-RUN xargs apt-get install -y --no-install-recommends < /app/requirements/pyppeteer_deps.txt
+# RUN xargs apt-get install -y --no-install-recommends < /app/requirements/pyppeteer_deps.txt
 
 
 #
diff --git a/articles/migrations/0001_initial.py b/articles/migrations/0001_initial.py
index 4395ec6..3a6252d 100644
--- a/articles/migrations/0001_initial.py
+++ b/articles/migrations/0001_initial.py
@@ -1,4 +1,4 @@
-# Generated by Django 5.0.1 on 2024-02-18 12:41
+# Generated by Django 5.0.1 on 2024-02-26 20:25
 
 import django.db.models.deletion
 import django.db.models.functions.text
@@ -24,7 +24,7 @@ class Migration(migrations.Migration):
                     ),
                 ),
                 (
-                    "name",
+                    "title",
                     models.CharField(
                         help_text="The name of the source", max_length=128, unique=True
                     ),
@@ -97,7 +97,7 @@ class Migration(migrations.Migration):
                 ),
             ],
             options={
-                "ordering": [django.db.models.functions.text.Lower("name")],
+                "ordering": [django.db.models.functions.text.Lower("title")],
             },
         ),
         migrations.CreateModel(
diff --git a/articles/models.py b/articles/models.py
index 0c37f29..9c4c00a 100644
--- a/articles/models.py
+++ b/articles/models.py
@@ -74,7 +74,7 @@ class Source(models.Model):
     Metadata about the source of articles
 
     Fields:
-        name (models.CharField): name of the source
+        title (models.CharField): name of the source
         slug (models.SlugField): slug of the source
         publication_type (models.CharField): the type of publication of the
             source (newspaper, journal, blog...)
@@ -97,7 +97,7 @@ class Source(models.Model):
             scraper
     """
 
-    name = models.CharField(
+    title = models.CharField(
         max_length=128,
         unique=True,
         blank=False,
@@ -164,11 +164,11 @@ class Source(models.Model):
 
     class Meta:
         ordering = [
-            Lower("name"),
+            Lower("title"),
         ]
 
     def __str__(self):
-        return f"{self.name}"
+        return f"{self.title}"
 
     def to_dict(self):
         sitemap = {
diff --git a/articles/tasks.py b/articles/tasks.py
index ee5c151..49bcbd2 100644
--- a/articles/tasks.py
+++ b/articles/tasks.py
@@ -10,8 +10,8 @@
 
 
 @shared_task
-def get_articles_for_source(source_title: str):
-    source: Source = Source.objects.get(name=source_title)
+def get_articles_for_source(source_title: str) -> None:
+    source: Source = Source.objects.get(title=source_title)
     sitemap = source.to_dict()
     starting_urls = [
         sitemap["base_url"] + path for path in sitemap["paths"]
@@ -19,18 +19,18 @@ def get_articles_for_source(source_title: str):
 
     spider = scraper.Spider(starting_urls, sitemap)
     spider.run()
-    data = [json.loads(article) for article in spider.articles]
+    articles = [json.loads(article) for article in spider.articles]
 
     Article.objects.bulk_create([
         Article(
             headline=article_data["headline"],
             slug=article_data["slug"],
-            source=Source.objects.get(link=article_data["source_link"]),
+            source=Source.objects.get(url=article_data["source_link"]),
             summary=article_data["summary"],
             language=article_data["language"],
             url=article_data["url"],
             created_at=timezone.now(),
-        ) for article_data in data
+        ) for article_data in articles
     ], ignore_conflicts=True)
 
 
diff --git a/articles/templates/articles/index.html b/articles/templates/articles/index.html
index ae695cf..6ec749d 100644
--- a/articles/templates/articles/index.html
+++ b/articles/templates/articles/index.html
@@ -9,7 +9,7 @@
   <div class="row">
     {% for source in sources %}
       <div class="col-md-12 col-lg-6 col-xl-4 container-articles-outer">
-	<div class="source"><a class="source-link" href="{{ source.url }}"><h5 class="source-name">{{ source.name }}</h5></a></div>
+	<div class="source"><a class="source-link" href="{{ source.url }}"><h5 class="source-title">{{ source.title }}</h5></a></div>
 	<div class="container-articles-inner">
 	<ul class="article-list">
 	  {% for article in source.articles.all|slice:":10" %}
diff --git a/articles/templates/articles/search_results.html b/articles/templates/articles/search_results.html
index 89d8c89..2c15433 100644
--- a/articles/templates/articles/search_results.html
+++ b/articles/templates/articles/search_results.html
@@ -12,11 +12,11 @@ <h3>Search Results for: "{{ query }}"</h3>
   <div class="row">
     {% for source in sources %}
       <div class="col-md-12 col-lg-6 col-xl-4 container-articles-outer">
-	<div><a class="source-link" href="{{ source.url }}"><h5 class="source-name">{{ source.name }}</h5></a></div>
+	<div><a class="source-link" href="{{ source.url }}"><h5 class="source-title">{{ source.title }}</h5></a></div>
 	<div class="container-articles-inner container-scrolling">
 	<ul>
 	  {% for article in article_list %}
-	    {% if article.source.name == source.name %}
+	    {% if article.source.title == source.title %}
 	    <li>
 	      <div class="article-headline">
 		<a class="article-link main-text"
diff --git a/articles/tests/conftest.py b/articles/tests/conftest.py
index 1b99852..c80344c 100644
--- a/articles/tests/conftest.py
+++ b/articles/tests/conftest.py
@@ -1,3 +1,6 @@
+from datetime import datetime
+from typing import Dict, Union
+
 import pytest
 from django.test import Client
 from django.utils import timezone
@@ -6,13 +9,10 @@
 from ..models import Article, Source
 
 
-#
-# Test fixtures
-#
 @pytest.fixture
 def source_values():
     return {
-        "name": "Fake News",
+        "title": "Fake News",
         "slug": "fake-news",
         "url": "https://www.hocusbogus.com/",
         "publication_type": PublicationType.newspaper,
@@ -33,7 +33,7 @@ def source_instance(source_values):
 @pytest.fixture
 def source_values_2():
     return {
-        "name": "Alternative Facts",
+        "title": "Alternative Facts",
         "slug": "alternative-facts",
         "url": "https://www.nonsensical.org/",
         "publication_type": PublicationType.newspaper,
@@ -52,7 +52,7 @@ def source_instance_2(source_values_2):
 
 
 @pytest.fixture
-def article_values(source_instance):
+def article_values(source_instance) -> Dict[str, Union[datetime, str]]:
     return {
         "headline": "A cow jumps over the moon",
         "slug": "a-cow-jumps-over-the-moon",
@@ -64,7 +64,7 @@ def article_values(source_instance):
 
 
 @pytest.fixture
-def article_values_m(source_values):
+def article_values_m(source_values) -> Dict[str, Union[Source, datetime, str]]:
     return {
         "headline": "A cow jumps over the moon",
         "slug": "a-cow-jumps-over-the-moon",
@@ -81,7 +81,7 @@ def article_instance(article_values):
 
 
 @pytest.fixture
-def article_values_2(source_instance):
+def article_values_2(source_instance) -> Dict[str, Union[datetime, str]]:
     return {
         "headline": "The moon is made of cheese",
         "slug": "the-moon-is-made-of-cheese",
@@ -98,5 +98,5 @@ def article_instance_2(article_values_2):
 
 
 @pytest.fixture
-def client():
+def client() -> Client:
     return Client()
diff --git a/articles/tests/test_models.py b/articles/tests/test_models.py
index 4453b39..40563cf 100644
--- a/articles/tests/test_models.py
+++ b/articles/tests/test_models.py
@@ -6,14 +6,14 @@
 #
 # Test Source
 #
-def test_create_source(source_values):
+def test_create_source(source_values) -> None:
     source = Source(**source_values)
 
     for attr_name in source_values:
         assert getattr(source, attr_name) == source_values.get(attr_name)
 
 
-def test_source_to_dict(source_values):
+def test_source_to_dict(source_values) -> None:
     source = Source(**source_values)
     sitemap = source.to_dict()
 
@@ -30,7 +30,7 @@ def test_source_to_dict(source_values):
     assert regex.compile(source.regex) == sitemap["filter"]
 
 
-def test_source_str_representation(source_values):
+def test_source_str_representation(source_values) -> None:
     source = Source(**source_values)
 
     assert str(source) == "Fake News"
@@ -39,14 +39,14 @@ def test_source_str_representation(source_values):
 #
 # Test Article
 #
-def test_create_article(article_values_m):
+def test_create_article(article_values_m) -> None:
     article = Article(**article_values_m)
 
     for attr_name in article_values_m:
         assert getattr(article, attr_name) == article_values_m.get(attr_name)
 
 
-def test_article_representation(article_values_m):
+def test_article_representation(article_values_m) -> None:
     article = Article(**article_values_m)
 
     assert str(article) == (f"{article.source}: {article.headline}")
diff --git a/articles/tests/test_views.py b/articles/tests/test_views.py
index d662691..af14260 100644
--- a/articles/tests/test_views.py
+++ b/articles/tests/test_views.py
@@ -9,7 +9,7 @@
 # Test IndexView
 #
 @pytest.mark.django_db
-def test_index_view(client, source_instance, article_instance):
+def test_index_view(client, source_instance, article_instance) -> None:
     response = client.get(reverse("index"))
 
     assert response.status_code == 200
@@ -18,12 +18,12 @@ def test_index_view(client, source_instance, article_instance):
     doc = pq(html)
 
     # assert that details of source are present in response content
-    source_name = doc.find(".source-name").text()
+    source_title = doc.find(".source-title").text()
     source_link = doc.find(".source-link")
     source_link_href = source_link.attr("href")
 
 
-    assert source_name == source_instance.name
+    assert source_title == source_instance.title
     assert source_link.is_("a")
     assert source_link_href == source_instance.url
 
@@ -50,7 +50,7 @@ def test_search_results_view(
     article_values,
     article_instance,
     article_instance_2,
-):
+) -> None:
     query_params = {"q": article_values["headline"][:5]}
     response = client.get(reverse("search"), query_params)
     html = response.content.decode("utf-8")
@@ -59,11 +59,11 @@ def test_search_results_view(
     assert response.status_code == 200
 
     # assert that details of source matching query are present in response content
-    source_name = doc.find(".source-name").text()
+    source_title = doc.find(".source-title").text()
     source_link = doc.find(".source-link")
     source_link_href = source_link.attr("href")
 
-    assert source_name == source_instance.name
+    assert source_title == source_instance.title
     assert source_link.is_("a")
     assert source_link_href == source_instance.url
 
@@ -80,7 +80,7 @@ def test_search_results_view(
     assert article_instance.summary in article_link_title
 
     # assert that details of non-matching source are not found
-    assert source_instance_2.name not in html
+    assert source_instance_2.title not in html
     assert source_instance_2.url not in html
 
     # assert that details of non-matching article are not found
@@ -96,7 +96,7 @@ def test_search_result_not_found(
     source_instance_2,
     article_instance,
     article_instance_2,
-):
+) -> None:
     query_params = {"q": "test"}
     response = client.get(reverse("search"), query_params)
     html = response.content.decode("utf-8")
@@ -104,7 +104,7 @@ def test_search_result_not_found(
     assert response.status_code == 200
 
     # assert that details of non-matching source are not found
-    assert source_instance.name not in html
+    assert source_instance.title not in html
     assert source_instance.url not in html
 
     # assert that details of non-matching article are not found
@@ -119,7 +119,7 @@ def test_search_result_substring(
     source_instance,
     article_instance,
     article_values,
-):
+) -> None:
     query_params = {"q": article_values["headline"][2:7]}
     response = client.get(reverse("search"), query_params)
     html = response.content.decode("utf-8")
@@ -127,7 +127,7 @@ def test_search_result_substring(
     assert response.status_code == 200
 
     # assert that details of non-matching source are not found
-    assert source_instance.name not in html
+    assert source_instance.title not in html
     assert source_instance.url not in html
 
     # assert that details of non-matching article are not found
diff --git a/articles/urls.py b/articles/urls.py
index 04fb78a..5a7c07c 100644
--- a/articles/urls.py
+++ b/articles/urls.py
@@ -1,8 +1,11 @@
+from typing import List
+
 from django.urls import path
+from django.urls.resolvers import URLPattern
 
 from . import views
 
-urlpatterns = [
+urlpatterns: List[URLPattern] = [
     path("", views.index, name="index"),
     path("search", views.SearchResultsView.as_view(), name="search"),
 ]
diff --git a/articles/views.py b/articles/views.py
index 06a361f..899a7b1 100644
--- a/articles/views.py
+++ b/articles/views.py
@@ -1,14 +1,17 @@
 import re
+from typing import Any, Dict, Optional
 
+from django.http.request import HttpRequest
+from django.http.response import HttpResponse
 from django.shortcuts import render
 from django.views.generic import ListView
 
 from .models import Article, Source
 
 
-def index(request):
+def index(request: Optional[HttpRequest]) -> HttpResponse:
     context = {
-        "sources": Source.objects.only("name", "url", "publication_type"),
+        "sources": Source.objects.only("title", "url", "publication_type"),
     }
     return render(request, "articles/index.html", context)
 
@@ -18,7 +21,7 @@ class SearchResultsView(ListView):
     fields = ["headline", "url", "body"]
     template_name = "articles/search_results.html"
 
-    def get_context_data(self, **kwargs):
+    def get_context_data(self, **kwargs) -> Dict[str, Any]:
         """Pre-filter sources on the basis of article headlines and queries"""
 
         context = super().get_context_data(**kwargs)
@@ -28,7 +31,7 @@ def get_context_data(self, **kwargs):
             regex = r"(?<![a-zA-Z])" + re.escape(query) + r"(?![a-rA-Rt-zT-Z])"
             context.update(
                 {
-                    "sources": Source.objects.only("name", "url", "publication_type")
+                    "sources": Source.objects.only("title", "url", "publication_type")
                                              .filter(articles__headline__iregex=regex)
                                              .distinct(),
                     "query": query,
diff --git a/docker-compose.yml b/docker-compose.yml
index 20fcf95..414de64 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -15,6 +15,7 @@ services:
     build: &web_build
       context: .
       dockerfile: Dockerfile
+    restart: always
     environment: &web_env
       - DJANGO_SETTINGS_MODULE=${DJANGO_SETTINGS_MODULE}
       - SECRET_KEY=${SECRET_KEY}
@@ -43,7 +44,6 @@ services:
              python manage.py runserver 0.0.0.0:8000"
     ports:
       - "8000:8000"
-    restart: always
     depends_on:
       - db
       - redis
diff --git a/env-sample b/env-sample
index dc55b5f..6878400 100644
--- a/env-sample
+++ b/env-sample
@@ -1,4 +1,4 @@
-# Template of variables that need to be set in .env
+# Template of variables for .env; settings intended for local development
 
 DJANGO_SETTINGS_MODULE=nous_aggregator.settings.base
 
@@ -20,7 +20,7 @@ CSRF_COOKIE_SECURE=False
 SECURE_SSL_REDIRECT=False
 
 # Database
-POSTGRES_HOST_AUTH_METHOD=ident
+POSTGRES_HOST_AUTH_METHOD=trust
 DATABASE_ENGINE=django.db.backends.postgresql
 DATABASE_NAME=postgres
 DATABASE_USER=postgres
diff --git a/fixtures/sources.json b/fixtures/sources.json
index 3c4ce79..f7f22f9 100644
--- a/fixtures/sources.json
+++ b/fixtures/sources.json
@@ -3,9 +3,9 @@
   "model": "articles.source",
   "pk": 1,
   "fields": {
-    "name": "Al Jazeera",
+    "title": "Al Jazeera",
 		"slug": "al-jazeera",
-    "link": "https://www.aljazeera.com/",
+    "url": "https://www.aljazeera.com/",
     "publication_type": "newspaper/journal",
     "language": "en",
     "paths": [
@@ -29,8 +29,8 @@
   "model": "articles.source",
   "pk": 2,
   "fields": {
-    "name": "Associated Press",
-    "link": "https://apnews.com/",
+    "title": "Associated Press",
+    "url": "https://apnews.com/",
     "publication_type": "newspaper/journal",
     "language": "en",
     "paths": [
@@ -46,7 +46,7 @@
     "summary_selectors": {
       "tag": "div",
       "attrs": {
-        "class": "Article"
+        "class": "RichTextStoryBody"
       }
     }
   }
@@ -55,8 +55,8 @@
   "model": "articles.source",
   "pk": 3,
   "fields": {
-    "name": "Christian Science Monitor",
-    "link": "https://www.csmonitor.com/",
+    "title": "Christian Science Monitor",
+    "url": "https://www.csmonitor.com/",
     "publication_type": "newspaper/journal",
     "language": "en",
     "paths": [
@@ -74,7 +74,7 @@
     "summary_selectors": {
       "tag": "div",
       "attrs": {
-        "id": "summary"
+        "class": "story-two"
       }
     }
   }
@@ -83,8 +83,8 @@
   "model": "articles.source",
   "pk": 4,
   "fields": {
-    "name": "Consortium News",
-    "link": "https://consortiumnews.com/",
+    "title": "Consortium News",
+    "url": "https://consortiumnews.com/",
     "publication_type": "newspaper/journal",
     "language": "en",
     "paths": [
@@ -106,8 +106,8 @@
   "model": "articles.source",
   "pk": 5,
   "fields": {
-    "name": "Current Affairs",
-    "link": "https://www.currentaffairs.org/",
+    "title": "Current Affairs",
+    "url": "https://www.currentaffairs.org/",
     "publication_type": "newspaper/journal",
     "language": "en",
     "paths": [
@@ -136,8 +136,8 @@
   "model": "articles.source",
   "pk": 6,
   "fields": {
-    "name": "New York Times",
-    "link": "https://www.nytimes.com/",
+    "title": "New York Times",
+    "url": "https://www.nytimes.com/",
     "publication_type": "newspaper/journal",
     "language": "en",
     "paths": [
@@ -155,7 +155,7 @@
     "summary_selectors": {
       "tag": "section",
       "attrs": {
-        "id": "article-summary"
+        "id": "articleBody"
       }
     }
   }
@@ -164,8 +164,8 @@
   "model": "articles.source",
   "pk": 7,
   "fields": {
-    "name": "NPR",
-    "link": "https://www.npr.org/",
+    "title": "NPR",
+    "url": "https://www.npr.org/",
     "publication_type": "newspaper/journal",
     "language": "en",
     "paths": [
@@ -184,8 +184,8 @@
   "model": "articles.source",
   "pk": 8,
   "fields": {
-    "name": "Reuters",
-    "link": "https://www.reuters.com/",
+    "title": "Reuters",
+    "url": "https://www.reuters.com/",
     "publication_type": "newspaper/journal",
     "language": "en",
     "paths": [
@@ -198,7 +198,7 @@
       "attrs": {}
     },
     "summary_selectors": {
-      "tag": "p",
+      "tag": "div",
       "attrs": {
         "data-testid": "paragraph-0"
       }
@@ -209,8 +209,8 @@
   "model": "articles.source",
   "pk": 9,
   "fields": {
-    "name": "The Atlantic",
-    "link": "https://www.theatlantic.com/",
+    "title": "The Atlantic",
+    "url": "https://www.theatlantic.com/",
     "publication_type": "newspaper/journal",
     "language": "en",
     "paths": [
@@ -227,7 +227,7 @@
     "summary_selectors": {
       "tag": "section",
       "attrs": {
-        "class": "ArticleBody_root__nZ4AR"
+        "class": "ArticleBody_root__2gF81"
       }
     }
   }
@@ -236,8 +236,8 @@
   "model": "articles.source",
   "pk": 10,
   "fields": {
-    "name": "The Intercept",
-    "link": "https://theintercept.com/",
+    "title": "The Intercept",
+    "url": "https://theintercept.com/",
     "publication_type": "newspaper/journal",
     "language": "en",
     "paths": [
@@ -261,8 +261,8 @@
   "model": "articles.source",
   "pk": 11,
   "fields": {
-    "name": "Wall Street Journal",
-    "link": "https://www.wsj.com/",
+    "title": "Wall Street Journal",
+    "url": "https://www.wsj.com/",
     "publication_type": "newspaper/journal",
     "language": "en",
     "paths": [
@@ -281,8 +281,8 @@
   "model": "articles.source",
   "pk": 12,
   "fields": {
-    "name": "UPI",
-    "link": "https://www.upi.com/",
+    "title": "UPI",
+    "url": "https://www.upi.com/",
     "publication_type": "newspaper/journal",
     "language": "en",
     "paths": [
diff --git a/manage.py b/manage.py
index 50a673c..5b2728f 100755
--- a/manage.py
+++ b/manage.py
@@ -4,7 +4,7 @@
 import sys
 
 
-def main():
+def main() -> None:
     """Run administrative tasks."""
     os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'nous_aggregator.settings')
     try:
diff --git a/nous_aggregator/asgi.py b/nous_aggregator/asgi.py
index b22f185..751c449 100644
--- a/nous_aggregator/asgi.py
+++ b/nous_aggregator/asgi.py
@@ -10,7 +10,8 @@
 import os
 
 from django.core.asgi import get_asgi_application
+from django.core.handlers.asgi import ASGIHandler
 
 os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'nous_aggregator.settings')
 
-application = get_asgi_application()
+application: ASGIHandler = get_asgi_application()
diff --git a/nous_aggregator/settings/base.py b/nous_aggregator/settings/base.py
index 1c4b325..82d4e5b 100644
--- a/nous_aggregator/settings/base.py
+++ b/nous_aggregator/settings/base.py
@@ -1,5 +1,6 @@
 import os
 from pathlib import Path
+from typing import Any, Dict, List, Union
 
 from decouple import Csv, config
 
@@ -7,7 +8,7 @@
 
 # Build paths inside the project like this: BASE_DIR / 'subdir'.
 # (modified because settings files are nested one level deeper)
-BASE_DIR = Path(__file__).resolve().parent.parent.parent
+BASE_DIR: Path = Path(__file__).resolve().parent.parent.parent
 
 SECRET_KEY = config("SECRET_KEY", default="")
 
@@ -25,7 +26,7 @@
 
 SECURE_PROXY_SSL_HEADER = ('HTTP_X_FORWARDED_PROTO', 'https')
 
-DATABASES = {
+DATABASES: Dict[str, Dict[str, Any]] = {
     "default": {
         "ENGINE": config("DATABASE_ENGINE", default="django.db.backends.postgresql"),
         "NAME": config("DATABASE_NAME", default="postgres"),
@@ -88,8 +89,8 @@
 
 # Logging
 
-LOG_DIR = BASE_DIR / "logs"
-LOGGING = {
+LOG_DIR: Path = BASE_DIR / "logs"
+LOGGING: Dict[str, Union[Dict[str, Dict[str, str]], Dict[str, Dict[str, Union[List[str], bool, str]]], Dict[str, Dict[str, Union[int, str]]], int]] = {
     'version': 1,
     'disable_existing_loggers': False,
     'formatters': {
@@ -170,7 +171,7 @@
 # https://docs.djangoproject.com/en/4.0/howto/static-files/
 
 STATIC_URL = "static/"
-STATIC_ROOT = os.path.join(BASE_DIR, 'static')
+STATIC_ROOT: str = os.path.join(BASE_DIR, 'static')
 
 
 # Default primary key field type
@@ -178,13 +179,13 @@
 
 DEFAULT_AUTO_FIELD = "django.db.models.BigAutoField"
 
-# Timeouts (connection timeout, read timeout) in seconds for requests
-REQUESTS_TIMEOUT = (30, 60)
+# Timeout in seconds for HTTP requests
+REQUESTS_TIMEOUT = 30
 
 # Celery
 CELERY_BROKER_URL = config("CELERY_BROKER_URL", "redis://localhost:6379")
 CELERY_RESULT_BACKEND = config("CELERY_RESULT_BACKEND", "redis://localhost:6379")
-CELERY_BEAT_SCHEDULE = {
+CELERY_BEAT_SCHEDULE: Dict[str, Dict[str, Union[Dict[str, str], List[str], int, str]]] = {
     "get_articles_en": {
         "task": "articles.tasks.get_articles",
         "schedule": scraper_tasks.magazines["en"]["schedule"],
diff --git a/nous_aggregator/settings/local.py b/nous_aggregator/settings/local.py
index c3a5c96..fe00d3c 100644
--- a/nous_aggregator/settings/local.py
+++ b/nous_aggregator/settings/local.py
@@ -1,7 +1,11 @@
 import socket
+from typing import List
 
 from .base import *
 
+hostname: str
+ips: List[str]
+
 SECRET_KEY = "hush-hush"
 
 DEBUG = True
diff --git a/nous_aggregator/urls.py b/nous_aggregator/urls.py
index b24dd1a..2523e9d 100644
--- a/nous_aggregator/urls.py
+++ b/nous_aggregator/urls.py
@@ -13,11 +13,14 @@
     1. Import the include() function: from django.urls import include, path
     2. Add a URL to urlpatterns:  path('blog/', include('blog.urls'))
 """
+from typing import List
+
 from django.conf import settings
 from django.contrib import admin
-from django.urls import path, include
+from django.urls import include, path
+from django.urls.resolvers import URLResolver
 
-urlpatterns = [
+urlpatterns: List[URLResolver] = [
     path("", include("articles.urls")),
     path("articles", include("articles.urls")),
     path("", include("articles.urls")),
diff --git a/nous_aggregator/wsgi.py b/nous_aggregator/wsgi.py
index c944b75..3c4105a 100644
--- a/nous_aggregator/wsgi.py
+++ b/nous_aggregator/wsgi.py
@@ -9,8 +9,9 @@
 
 import os
 
+from django.core.handlers.wsgi import WSGIHandler
 from django.core.wsgi import get_wsgi_application
 
 os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'nous_aggregator.settings')
 
-application = get_wsgi_application()
+application: WSGIHandler = get_wsgi_application()
diff --git a/requirements/base.in b/requirements/base.in
index 36c6922..054be83 100644
--- a/requirements/base.in
+++ b/requirements/base.in
@@ -1,14 +1,13 @@
 # Python
+aiohttp
 beautifulsoup4
 langdetect
-regex
-requests
-requests-html
-python-decouple
 psycopg2
+python-decouple
 pyppeteer
+pyquery
+regex
 sentry-sdk
-websockets
 
 # Django
 django
diff --git a/requirements/base.txt b/requirements/base.txt
index 1042fdf..ff36e21 100644
--- a/requirements/base.txt
+++ b/requirements/base.txt
@@ -4,29 +4,28 @@
 #
 #    ./bin/compile_dependencies.sh
 #
+aiohttp==3.9.3
+    # via -r requirements/base.in
+aiosignal==1.3.1
+    # via aiohttp
 amqp==5.2.0
     # via kombu
 appdirs==1.4.4
     # via pyppeteer
 asgiref==3.7.2
     # via django
+attrs==23.2.0
+    # via aiohttp
 beautifulsoup4==4.12.2
-    # via
-    #   -r requirements/base.in
-    #   bs4
+    # via -r requirements/base.in
 billiard==4.2.0
     # via celery
-bs4==0.0.1
-    # via requests-html
 celery==5.3.6
     # via -r requirements/base.in
 certifi==2023.7.22
     # via
     #   pyppeteer
-    #   requests
     #   sentry-sdk
-charset-normalizer==3.2.0
-    # via requests
 click==8.1.7
     # via
     #   celery
@@ -50,12 +49,14 @@ django==5.0.1
     #   django-on-heroku
 django-on-heroku==1.1.2
     # via -r requirements/base.in
-fake-useragent==1.2.1
-    # via requests-html
+frozenlist==1.4.1
+    # via
+    #   aiohttp
+    #   aiosignal
 gunicorn==21.2.0
     # via -r requirements/base.in
 idna==3.4
-    # via requests
+    # via yarl
 importlib-metadata==6.8.0
     # via pyppeteer
 kombu==5.3.5
@@ -64,10 +65,12 @@ langdetect==1.0.9
     # via -r requirements/base.in
 lxml==4.9.3
     # via pyquery
+multidict==6.0.5
+    # via
+    #   aiohttp
+    #   yarl
 packaging==23.2
     # via gunicorn
-parse==1.19.1
-    # via requests-html
 prompt-toolkit==3.0.43
     # via click-repl
 psycopg2==2.9.9
@@ -77,11 +80,9 @@ psycopg2-binary==2.9.7
 pyee==8.2.2
     # via pyppeteer
 pyppeteer==1.0.2
-    # via
-    #   -r requirements/base.in
-    #   requests-html
+    # via -r requirements/base.in
 pyquery==2.0.0
-    # via requests-html
+    # via -r requirements/base.in
 python-dateutil==2.8.2
     # via celery
 python-decouple==3.8
@@ -90,12 +91,6 @@ redis==5.0.1
     # via -r requirements/base.in
 regex==2023.8.8
     # via -r requirements/base.in
-requests==2.31.0
-    # via
-    #   -r requirements/base.in
-    #   requests-html
-requests-html==0.10.0
-    # via -r requirements/base.in
 sentry-sdk==1.39.2
     # via -r requirements/base.in
 six==1.16.0
@@ -115,22 +110,19 @@ tzdata==2023.4
 urllib3==1.26.18
     # via
     #   pyppeteer
-    #   requests
     #   sentry-sdk
 vine==5.1.0
     # via
     #   amqp
     #   celery
     #   kombu
-w3lib==2.1.2
-    # via requests-html
 wcwidth==0.2.13
     # via prompt-toolkit
 websockets==10.4
-    # via
-    #   -r requirements/base.in
-    #   pyppeteer
+    # via pyppeteer
 whitenoise==6.5.0
     # via django-on-heroku
+yarl==1.9.4
+    # via aiohttp
 zipp==3.16.2
     # via importlib-metadata
diff --git a/requirements/ci.in b/requirements/ci.in
index 61ae914..076ba5b 100644
--- a/requirements/ci.in
+++ b/requirements/ci.in
@@ -6,4 +6,5 @@ bandit
 # Testing
 pyquery
 pytest
+pytest-mock
 pytest-django
diff --git a/requirements/ci.txt b/requirements/ci.txt
index eafbd45..4af1f45 100644
--- a/requirements/ci.txt
+++ b/requirements/ci.txt
@@ -4,6 +4,15 @@
 #
 #    ./bin/compile_dependencies.sh
 #
+aiohttp==3.9.3
+    # via
+    #   -c requirements/base.txt
+    #   -r requirements/base.txt
+aiosignal==1.3.1
+    # via
+    #   -c requirements/base.txt
+    #   -r requirements/base.txt
+    #   aiohttp
 amqp==5.2.0
     # via
     #   -c requirements/base.txt
@@ -19,23 +28,22 @@ asgiref==3.7.2
     #   -c requirements/base.txt
     #   -r requirements/base.txt
     #   django
+attrs==23.2.0
+    # via
+    #   -c requirements/base.txt
+    #   -r requirements/base.txt
+    #   aiohttp
 bandit==1.7.5
     # via -r requirements/ci.in
 beautifulsoup4==4.12.2
     # via
     #   -c requirements/base.txt
     #   -r requirements/base.txt
-    #   bs4
 billiard==4.2.0
     # via
     #   -c requirements/base.txt
     #   -r requirements/base.txt
     #   celery
-bs4==0.0.1
-    # via
-    #   -c requirements/base.txt
-    #   -r requirements/base.txt
-    #   requests-html
 celery==5.3.6
     # via
     #   -c requirements/base.txt
@@ -45,13 +53,7 @@ certifi==2023.7.22
     #   -c requirements/base.txt
     #   -r requirements/base.txt
     #   pyppeteer
-    #   requests
     #   sentry-sdk
-charset-normalizer==3.2.0
-    # via
-    #   -c requirements/base.txt
-    #   -r requirements/base.txt
-    #   requests
 click==8.1.7
     # via
     #   -c requirements/base.txt
@@ -95,11 +97,12 @@ django-on-heroku==1.1.2
     # via
     #   -c requirements/base.txt
     #   -r requirements/base.txt
-fake-useragent==1.2.1
+frozenlist==1.4.1
     # via
     #   -c requirements/base.txt
     #   -r requirements/base.txt
-    #   requests-html
+    #   aiohttp
+    #   aiosignal
 gitdb==4.0.10
     # via gitpython
 gitpython==3.1.41
@@ -112,7 +115,7 @@ idna==3.4
     # via
     #   -c requirements/base.txt
     #   -r requirements/base.txt
-    #   requests
+    #   yarl
 importlib-metadata==6.8.0
     # via
     #   -c requirements/base.txt
@@ -138,17 +141,18 @@ markdown-it-py==3.0.0
     # via rich
 mdurl==0.1.2
     # via markdown-it-py
-packaging==23.2
+multidict==6.0.5
     # via
     #   -c requirements/base.txt
     #   -r requirements/base.txt
-    #   gunicorn
-    #   pytest
-parse==1.19.1
+    #   aiohttp
+    #   yarl
+packaging==23.2
     # via
     #   -c requirements/base.txt
     #   -r requirements/base.txt
-    #   requests-html
+    #   gunicorn
+    #   pytest
 pbr==5.11.1
     # via stevedore
 pluggy==1.3.0
@@ -178,19 +182,20 @@ pyppeteer==1.0.2
     # via
     #   -c requirements/base.txt
     #   -r requirements/base.txt
-    #   requests-html
 pyquery==2.0.0
     # via
     #   -c requirements/base.txt
     #   -r requirements/base.txt
     #   -r requirements/ci.in
-    #   requests-html
 pytest==7.4.2
     # via
     #   -r requirements/ci.in
     #   pytest-django
+    #   pytest-mock
 pytest-django==4.5.2
     # via -r requirements/ci.in
+pytest-mock==3.12.0
+    # via -r requirements/ci.in
 python-dateutil==2.8.2
     # via
     #   -c requirements/base.txt
@@ -210,15 +215,6 @@ regex==2023.8.8
     # via
     #   -c requirements/base.txt
     #   -r requirements/base.txt
-requests==2.31.0
-    # via
-    #   -c requirements/base.txt
-    #   -r requirements/base.txt
-    #   requests-html
-requests-html==0.10.0
-    # via
-    #   -c requirements/base.txt
-    #   -r requirements/base.txt
 rich==13.5.3
     # via bandit
 sentry-sdk==1.39.2
@@ -265,7 +261,6 @@ urllib3==1.26.18
     #   -c requirements/base.txt
     #   -r requirements/base.txt
     #   pyppeteer
-    #   requests
     #   sentry-sdk
 vine==5.1.0
     # via
@@ -274,11 +269,6 @@ vine==5.1.0
     #   amqp
     #   celery
     #   kombu
-w3lib==2.1.2
-    # via
-    #   -c requirements/base.txt
-    #   -r requirements/base.txt
-    #   requests-html
 wcwidth==0.2.13
     # via
     #   -c requirements/base.txt
@@ -294,6 +284,11 @@ whitenoise==6.5.0
     #   -c requirements/base.txt
     #   -r requirements/base.txt
     #   django-on-heroku
+yarl==1.9.4
+    # via
+    #   -c requirements/base.txt
+    #   -r requirements/base.txt
+    #   aiohttp
 zipp==3.16.2
     # via
     #   -c requirements/base.txt
diff --git a/requirements/dev.txt b/requirements/dev.txt
index 6f08f0f..5bb0ecd 100644
--- a/requirements/dev.txt
+++ b/requirements/dev.txt
@@ -4,6 +4,15 @@
 #
 #    ./bin/compile_dependencies.sh
 #
+aiohttp==3.9.3
+    # via
+    #   -c requirements/ci.txt
+    #   -r requirements/ci.txt
+aiosignal==1.3.1
+    # via
+    #   -c requirements/ci.txt
+    #   -r requirements/ci.txt
+    #   aiohttp
 amqp==5.2.0
     # via
     #   -c requirements/ci.txt
@@ -20,7 +29,11 @@ asgiref==3.7.2
     #   -r requirements/ci.txt
     #   django
 attrs==23.2.0
-    # via pytype
+    # via
+    #   -c requirements/ci.txt
+    #   -r requirements/ci.txt
+    #   aiohttp
+    #   pytype
 bandit==1.7.5
     # via
     #   -c requirements/ci.txt
@@ -30,7 +43,6 @@ beautifulsoup4==4.12.2
     # via
     #   -c requirements/ci.txt
     #   -r requirements/ci.txt
-    #   bs4
 billiard==4.2.0
     # via
     #   -c requirements/ci.txt
@@ -38,11 +50,6 @@ billiard==4.2.0
     #   celery
 black==23.9.1
     # via -r requirements/dev.in
-bs4==0.0.1
-    # via
-    #   -c requirements/ci.txt
-    #   -r requirements/ci.txt
-    #   requests-html
 celery==5.3.6
     # via
     #   -c requirements/ci.txt
@@ -52,13 +59,7 @@ certifi==2023.7.22
     #   -c requirements/ci.txt
     #   -r requirements/ci.txt
     #   pyppeteer
-    #   requests
     #   sentry-sdk
-charset-normalizer==3.2.0
-    # via
-    #   -c requirements/ci.txt
-    #   -r requirements/ci.txt
-    #   requests
 click==8.1.7
     # via
     #   -c requirements/ci.txt
@@ -115,13 +116,14 @@ django-stubs==4.2.4
     # via -r requirements/dev.in
 django-stubs-ext==4.2.2
     # via django-stubs
-fake-useragent==1.2.1
+flake8==6.1.0
+    # via -r requirements/dev.in
+frozenlist==1.4.1
     # via
     #   -c requirements/ci.txt
     #   -r requirements/ci.txt
-    #   requests-html
-flake8==6.1.0
-    # via -r requirements/dev.in
+    #   aiohttp
+    #   aiosignal
 gitdb==4.0.10
     # via
     #   -c requirements/ci.txt
@@ -140,7 +142,7 @@ idna==3.4
     # via
     #   -c requirements/ci.txt
     #   -r requirements/ci.txt
-    #   requests
+    #   yarl
 importlab==0.8
     # via pytype
 importlib-metadata==6.8.0
@@ -187,6 +189,12 @@ mdurl==0.1.2
     #   -c requirements/ci.txt
     #   -r requirements/ci.txt
     #   markdown-it-py
+multidict==6.0.5
+    # via
+    #   -c requirements/ci.txt
+    #   -r requirements/ci.txt
+    #   aiohttp
+    #   yarl
 mypy==1.5.1
     # via
     #   -r requirements/dev.in
@@ -209,11 +217,6 @@ packaging==23.2
     #   black
     #   gunicorn
     #   pytest
-parse==1.19.1
-    # via
-    #   -c requirements/ci.txt
-    #   -r requirements/ci.txt
-    #   requests-html
 pathspec==0.11.2
     # via black
 pbr==5.11.1
@@ -266,21 +269,24 @@ pyppeteer==1.0.2
     # via
     #   -c requirements/ci.txt
     #   -r requirements/ci.txt
-    #   requests-html
 pyquery==2.0.0
     # via
     #   -c requirements/ci.txt
     #   -r requirements/ci.txt
-    #   requests-html
 pytest==7.4.2
     # via
     #   -c requirements/ci.txt
     #   -r requirements/ci.txt
     #   pytest-django
+    #   pytest-mock
 pytest-django==4.5.2
     # via
     #   -c requirements/ci.txt
     #   -r requirements/ci.txt
+pytest-mock==3.12.0
+    # via
+    #   -c requirements/ci.txt
+    #   -r requirements/ci.txt
 python-dateutil==2.8.2
     # via
     #   -c requirements/ci.txt
@@ -306,15 +312,6 @@ regex==2023.8.8
     # via
     #   -c requirements/ci.txt
     #   -r requirements/ci.txt
-requests==2.31.0
-    # via
-    #   -c requirements/ci.txt
-    #   -r requirements/ci.txt
-    #   requests-html
-requests-html==0.10.0
-    # via
-    #   -c requirements/ci.txt
-    #   -r requirements/ci.txt
 rich==13.5.3
     # via
     #   -c requirements/ci.txt
@@ -391,7 +388,6 @@ urllib3==1.26.18
     #   -c requirements/ci.txt
     #   -r requirements/ci.txt
     #   pyppeteer
-    #   requests
     #   sentry-sdk
 vine==5.1.0
     # via
@@ -400,11 +396,6 @@ vine==5.1.0
     #   amqp
     #   celery
     #   kombu
-w3lib==2.1.2
-    # via
-    #   -c requirements/ci.txt
-    #   -r requirements/ci.txt
-    #   requests-html
 wcwidth==0.2.13
     # via
     #   -c requirements/ci.txt
@@ -420,6 +411,11 @@ whitenoise==6.5.0
     #   -c requirements/ci.txt
     #   -r requirements/ci.txt
     #   django-on-heroku
+yarl==1.9.4
+    # via
+    #   -c requirements/ci.txt
+    #   -r requirements/ci.txt
+    #   aiohttp
 zipp==3.16.2
     # via
     #   -c requirements/ci.txt
diff --git a/scraper/parser.py b/scraper/parser.py
index 4389e10..04286da 100644
--- a/scraper/parser.py
+++ b/scraper/parser.py
@@ -1,12 +1,28 @@
 import json
 import logging
-from typing import Optional
+import urllib
+from typing import Generator, Optional
 
-import langdetect  # type: ignore
-from bs4 import BeautifulSoup  # type: ignore
+import langdetect
+from bs4 import BeautifulSoup
 from django.utils.text import slugify
+from pyquery import PyQuery
 
-logger = logging.getLogger(__name__)
+logger: logging.Logger = logging.getLogger(__name__)
+
+
+def generate_filtered_links(html: str, sitemap: dict) -> Generator[str, None, None]:
+    doc = PyQuery(html)
+    anchors = doc.find("a")
+
+    for anchor in anchors:
+        try:
+            link = anchor.attrib["href"]
+        except KeyError:
+            pass
+        else:
+            if sitemap["filter"].search(link):
+                yield urllib.parse.urljoin(sitemap["base_url"], link)
 
 
 def find_headline(soup: BeautifulSoup, sitemap: dict, url: str) -> Optional[str]:
@@ -29,7 +45,7 @@ def find_headline(soup: BeautifulSoup, sitemap: dict, url: str) -> Optional[str]
 def find_summary(soup: BeautifulSoup, sitemap: dict, url: str) -> Optional[str]:
     """Use `parser` & `sitemap` to extract summary from article"""
 
-    if sitemap["summary_selectors"] is None:
+    if not sitemap["summary_selectors"]:
         return None
 
     try:
diff --git a/scraper/spiders.py b/scraper/spiders.py
index ede8e6d..dd36ed2 100644
--- a/scraper/spiders.py
+++ b/scraper/spiders.py
@@ -1,17 +1,14 @@
 import asyncio
 import logging
 import random
-from http.cookiejar import DefaultCookiePolicy
 
-import pyppeteer
-import requests
-from django.conf import settings
-from requests_html import AsyncHTMLSession, HTMLResponse
-from websockets.exceptions import ConnectionClosedError  # pyre-ignore
+import aiohttp  # pyre-ignore
+from aiohttp import ClientSession
+from aiohttp.web_exceptions import HTTPError
 
 from . import headers, parser
 
-logger = logging.getLogger(__name__)
+logger: logging.Logger = logging.getLogger(__name__)
 
 
 class Spider:
@@ -20,11 +17,6 @@ class Spider:
         headers (list): a collection of HTTP headers
 
     Instance Attributes:
-        event_loop: the event loop is explicitly set on the `Spider` instance and
-            passed to the requests session in order to minimize the risk of
-            attaching Futures to different event loops by accident
-        asession (AsyncHTMLSession): requests session that supports asynchronous
-            requests
         sitemap (dict): contains information about a particular page
         starting_urls (list): the urls where each `Spider` instance searches for
             links
@@ -35,80 +27,57 @@ class Spider:
 
     headers = headers.headers
 
-    def __init__(self, starting_urls: list[str], sitemap: dict):
-        self.event_loop = asyncio.get_event_loop()
-        self.asession = AsyncHTMLSession(loop=self.event_loop)
+    def __init__(self, starting_urls: list[str], sitemap: dict) -> None:
         self.sitemap: dict = sitemap
         self.starting_urls: list[str] = starting_urls
         self.links: set[str] = set()
         self.articles: set[str] = set()
 
-        @property
-        def asession(self):
-            return self._asession
+    async def connect(self, session: ClientSession, url: str) -> str | None:  # pyre-ignore
+        headers = random.choice(self.headers)
 
-        @asession.setter
-        def asession(self, asession: AsyncHTMLSession):
-            self._asession = asession
-            self._asession.cookies.set_policy(DefaultCookiePolicy(allowed_domains=[]))
-
-    async def connect(self, url: str) -> HTMLResponse | None:
-        """GET request wrapper"""
         try:
-            response = await self.asession.get(  # pyre-ignore
-                url,
-                headers=random.choice(self.headers),  # nosec
-                timeout=settings.REQUESTS_TIMEOUT,
-            )
-        except requests.exceptions.RequestException as e:
-            logger.error("Could not fetch %s (%s)", url, e)
+            async with session.get(url, headers=headers) as response:
+                html = await response.text()
+        except HTTPError as exc:
+            logger.error("Could not fetch %s", url, exc_info=exc)
+            return None
+        return html
+
+    async def get_links(self, session: ClientSession, url: str) -> list[str] | None:
+        html = await self.connect(session=session, url=url)
+        if not html:
+            return None
+
+        for link in parser.generate_filtered_links(html=html, sitemap=self.sitemap):
+            self.links.add(link)
+
+    async def scrape(self, session: ClientSession, link: str) -> str | None:
+        html = await self.connect(session=session, url=link)
+        if not html:
             return None
-        return response
-
-    async def get_links(self, url: str) -> None:
-        response = await self.connect(url)
-        if not response:
-            return
-
-        if self.sitemap["javascript_required"]:
-            try:
-                await response.html.arender()
-            except pyppeteer.errors.TimeoutError as e:
-                logger.error("Could not render JavaScript for %s (%s)", url, e)
-        for link in response.html.absolute_links:
-            if self.sitemap["filter"].search(link):
-                self.links.add(link)
-
-    async def scrape(self, url: str) -> None:
-        response = await self.connect(url)
-        if not response:
-            return
-
-        html = response.text
-        article = parser.parse(html, self.sitemap, url)
-        if article:
-            self.articles.add(article)
-
-    async def collect_links(self) -> None:
-        """
-        Create & gather tasks for collection of links
-        """
-        coros = [self.get_links(url) for url in self.starting_urls]
+
+        article = parser.parse(html, sitemap=self.sitemap, url=link)
+        if not article:
+            return None
+
+        self.articles.add(article)
+
+    async def collect_links(self, session: ClientSession, starting_urls: list[str]) -> None:
+        coros = (self.get_links(session, url) for url in starting_urls)
         await asyncio.gather(*coros)
 
-    async def collect_metadata(self) -> None:
-        """
-        Create & gather tasks for scraping
-        """
-        coros = [self.scrape(link) for link in self.links]
+    async def collect_metadata(self, session: ClientSession, links: set[str]) -> None:
+        coros = (self.scrape(session, link) for link in links)
         await asyncio.gather(*coros)
 
+    async def main(self) -> None:
+        async with aiohttp.ClientSession(
+            timeout=aiohttp.ClientTimeout(60),
+        ) as session:
+            await self.collect_links(session, self.starting_urls)
+            await self.collect_metadata(session, self.links)
+
     def run(self):
-        """
-        Run the `spider` instance inside the event loop
-        """
-        try:
-            self.event_loop.run_until_complete(self.collect_links())
-            self.event_loop.run_until_complete(self.collect_metadata())
-        except ConnectionClosedError as ex:
-            logger.warning("Connection closed", exc_info=ex)
+        loop = asyncio.get_event_loop()
+        loop.run_until_complete(self.main())
diff --git a/scraper/tasks.py b/scraper/tasks.py
index ff45b77..c13fd7d 100644
--- a/scraper/tasks.py
+++ b/scraper/tasks.py
@@ -1,6 +1,6 @@
 magazines = {
     "en": {
-        "schedule": 3600,
+        "schedule": 120,
         "titles": [
             "Al Jazeera",
             "Associated Press",
diff --git a/scraper/tests/conftest.py b/scraper/tests/conftest.py
index 057c6eb..eb13753 100644
--- a/scraper/tests/conftest.py
+++ b/scraper/tests/conftest.py
@@ -1,3 +1,5 @@
+from typing import Dict, List
+
 import pytest
 import regex
 
@@ -18,12 +20,12 @@ def sitemap_aj():
 
 
 @pytest.fixture
-def starting_urls_aj():
+def starting_urls_aj() -> List[str]:
     return ["https://www.aljazeera.com/news/"]
 
 
 @pytest.fixture
-def expected_aj():
+def expected_aj() -> Dict[str, Dict[str, str]]:
     expected = {
         "asian_cup": {
             'headline': 'Asian Cup final brings FIFA World Cup frenzy back to Qatar’s Souq Waqif',
diff --git a/scraper/tests/integration/test_spider.py b/scraper/tests/integration/test_spider.py
index 02b69d2..3e3ca05 100644
--- a/scraper/tests/integration/test_spider.py
+++ b/scraper/tests/integration/test_spider.py
@@ -1,21 +1,41 @@
 import json
 from pathlib import Path
+from typing import Any, Dict
 
 import pytest
+from django.utils.text import slugify
 
-import scraper
+from articles.constants import Language, PublicationType
+from articles.models import Source
 from scraper.spiders import Spider
 
+from ..mocks import MockResponse
 from ..utils import read_file
 
-FILES_DIR = Path(__file__).parent.parent.resolve() / "files" / "articles" / "aj"
+FILES_DIR: Path = Path(__file__).parent.parent.resolve() / "files" / "articles" / "aj"
 
 
 #
 # fixtures
 #
 @pytest.fixture
-def contents():
+def source():
+    return Source(
+        title="Al Jazeera",
+        slug=slugify("Al Jazeera"),
+        publication_type=PublicationType.newspaper,
+        language=Language.en,
+        url="https://www.aljazeera.com/",
+        paths=["news/"],
+        regex="(?<!liveblog)/[0-9]{4}/[0-9]+/[0-9]+/(?!.*terms-and-conditions/|.*community-rules-guidelines/|.*eu-eea-regulatory|.*code-of-ethics|.*liveblog)",
+        javascript_required=False,
+        headline_selectors={'tag': 'h1', 'attrs': {}},
+        summary_selectors={'tag': 'p', 'attrs': {'class': 'article__subhead'}},
+    )
+
+
+@pytest.fixture
+def contents() -> Dict[str, Dict[str, Any]]:
     contents = {
         "_start": {
             "link": "https://www.aljazeera.com/news/",
@@ -87,15 +107,30 @@ def contents():
 #
 # tests
 #
-def test_run_spider(starting_urls_aj, sitemap_aj, contents, expected_aj, requests_mock):
-    spider = Spider(starting_urls_aj, sitemap_aj)
+@pytest.mark.django_db
+def test_run_spider(source, contents, expected_aj, mocker) -> None:
+    #
+    # setup
+    #
+    def return_value(*args, **kwargs):
+        for k, v in contents.items():
+            if args[0] == v["link"]:
+                return MockResponse(text=v["content"])
+
+    mocker.patch("aiohttp.ClientSession.get", side_effect=return_value)
 
-    for item in contents.values():
-        requests_mock.get(item["link"], text=item["content"])
+    #
+    # asserts
+    #
+    sitemap = source.to_dict()
+    starting_urls = [
+        sitemap["base_url"] + path for path in sitemap["paths"]
+    ]
+    spider = Spider(starting_urls, sitemap)
 
     spider.run()
 
-    articles = [json.loads(article) for article in list(spider.articles)]
+    articles = [json.loads(article) for article in spider.articles]
 
     assert len(articles) == 12
 
diff --git a/scraper/tests/mocks.py b/scraper/tests/mocks.py
new file mode 100644
index 0000000..4ad6cd6
--- /dev/null
+++ b/scraper/tests/mocks.py
@@ -0,0 +1,13 @@
+class MockResponse:
+    def __init__(self, status_code: int | None = None, text: str = ""):
+        self.status_code = status_code or 200
+        self._text = text
+
+    async def text(self):
+        return self._text
+
+    async def __aenter__(self):
+        return self
+
+    async def __aexit__(self, exc_type, exc, tb):
+        pass
diff --git a/scraper/tests/unit/test_parsers.py b/scraper/tests/unit/test_parsers.py
index e02d625..da7e008 100644
--- a/scraper/tests/unit/test_parsers.py
+++ b/scraper/tests/unit/test_parsers.py
@@ -7,13 +7,13 @@
 
 from ..utils import read_file
 
-FILES_DIR = Path(__file__).parent.parent.resolve() / "files" / "articles" / "aj"
+FILES_DIR: Path = Path(__file__).parent.parent.resolve() / "files" / "articles" / "aj"
 
 PAGE = "indonesia"
 URL = "https://www.aljazeera.com/news/2024/2/10/big-election-rallies-in-indonesia-on-final-day-of-campaign"
 
 
-def test_find_headline(sitemap_aj, expected_aj):
+def test_find_headline(sitemap_aj, expected_aj) -> None:
     html = read_file(directory=FILES_DIR, file_name=f"{PAGE}.html")
     soup = BeautifulSoup(html, "lxml")
 
@@ -22,7 +22,7 @@ def test_find_headline(sitemap_aj, expected_aj):
     assert headline_text == expected_aj[f"{PAGE}"]["headline"]
 
 
-def test_find_summary(sitemap_aj, expected_aj):
+def test_find_summary(sitemap_aj, expected_aj) -> None:
     html = read_file(directory=FILES_DIR, file_name=f"{PAGE}.html")
     soup = BeautifulSoup(html, "lxml")
 
@@ -31,7 +31,7 @@ def test_find_summary(sitemap_aj, expected_aj):
     assert summary == expected_aj[f"{PAGE}"]["summary"]
 
 
-def test_find_language(sitemap_aj, expected_aj):
+def test_find_language(sitemap_aj, expected_aj) -> None:
     html = read_file(directory=FILES_DIR, file_name=f"{PAGE}.html")
     soup = BeautifulSoup(html, "lxml")
 
@@ -40,7 +40,7 @@ def test_find_language(sitemap_aj, expected_aj):
     assert lang == expected_aj[f"{PAGE}"]["language"]
 
 
-def test_parse(sitemap_aj, expected_aj):
+def test_parse(sitemap_aj, expected_aj) -> None:
     html = read_file(directory=FILES_DIR, file_name=f"{PAGE}.html")
 
     json_data = parse(html, sitemap_aj, url=URL)
diff --git a/scraper/tests/unit/test_spider.py b/scraper/tests/unit/test_spider.py
index d0233f1..d407c91 100644
--- a/scraper/tests/unit/test_spider.py
+++ b/scraper/tests/unit/test_spider.py
@@ -1,51 +1,77 @@
 import json
+import logging
 from pathlib import Path
 
+import aiohttp  # pyre-ignore
 import pytest
-from requests_html import AsyncHTMLSession
+from aiohttp.web_exceptions import HTTPError
 
 from scraper.spiders import Spider
 
+from ..mocks import MockResponse
 from ..utils import read_file
 
-FILES_DIR = Path(__file__).parent.parent.resolve() / "files" / "articles" / "aj"
+FILES_DIR: Path = Path(__file__).parent.parent.resolve() / "files" / "articles" / "aj"
 
 
 @pytest.mark.asyncio
-async def test_collect_links(starting_urls_aj, sitemap_aj, requests_mock):
+async def test_connect_error(starting_urls_aj, sitemap_aj, mocker, caplog):
     spider = Spider(starting_urls_aj, sitemap_aj)
-    spider.asession = AsyncHTMLSession()
 
+    mocker.patch("aiohttp.ClientSession.get", side_effect=HTTPError)
+
+    with caplog.at_level(logging.ERROR):
+        async with aiohttp.ClientSession() as session:
+            html = await spider.connect(session, starting_urls_aj[0])
+
+            assert html is None
+
+            assert len(caplog.messages) == 1
+            assert caplog.messages[0] == f"Could not fetch {starting_urls_aj[0]}"
+
+
+@pytest.mark.asyncio
+async def test_collect_links(starting_urls_aj, sitemap_aj, mocker):
+    spider = Spider(starting_urls_aj, sitemap_aj)
     html = read_file(directory=FILES_DIR, file_name="_start.html")
 
-    requests_mock.get(starting_urls_aj[0], text=html)
+    mock_response = MockResponse(status_code=200, text=html)
+    mocker.patch("aiohttp.ClientSession.get", return_value=mock_response)
 
-    await spider.collect_links()
+    async with aiohttp.ClientSession() as session:
+        await spider.collect_links(session, starting_urls_aj)
 
-    assert len(spider.links) == 12
+        assert len(spider.links) == 12
 
 
 @pytest.mark.asyncio
 async def test_collect_metadata(
-    starting_urls_aj, sitemap_aj, expected_aj, requests_mock
-):
+    starting_urls_aj, sitemap_aj, expected_aj, mocker
+) -> None:
     #
     # setup
     #
     spider = Spider(starting_urls_aj, sitemap_aj)
-    spider.links = ["https://indonesia.com", "https://taiwan.com"]
-    spider.asession = AsyncHTMLSession()
+    spider.links = {"https://indonesia.com", "https://taiwan.com"}
 
     html_indonesia = read_file(directory=FILES_DIR, file_name="indonesia.html")
     html_taiwan = read_file(directory=FILES_DIR, file_name="taiwan.html")
 
-    requests_mock.get("https://indonesia.com", text=html_indonesia)
-    requests_mock.get("https://taiwan.com", text=html_taiwan)
+    def return_value(*args, **kwargs):
+        mock_response1 = MockResponse(status_code=200, text=html_indonesia)
+        mock_response2 = MockResponse(status_code=200, text=html_taiwan)
+
+        if args[0] == "https://indonesia.com":
+            return mock_response1
+        elif args[0] == "https://taiwan.com":
+            return mock_response2
+
+    mocker.patch("aiohttp.ClientSession.get", side_effect=return_value)
 
     #
     # asserts
     #
-    await spider.collect_metadata()
+    await spider.collect_metadata(aiohttp.ClientSession(), spider.links)
 
     articles = [json.loads(article) for article in spider.articles]
 
diff --git a/scraper/tests/utils.py b/scraper/tests/utils.py
index ea7197a..e61ec4a 100644
--- a/scraper/tests/utils.py
+++ b/scraper/tests/utils.py
@@ -1,4 +1,4 @@
-def read_file(directory, file_name):
+def read_file(directory, file_name) -> str:
     start_page = directory / file_name
 
     with open(start_page, "r") as file: