first

.gitignore

@@ -0,0 +1,40 @@
+# LaTeX build files
+*.aux
+*.log
+*.out
+*.toc
+*.fls
+*.fdb_latexmk
+*.synctex.gz
+
+# PDF (valgfritt)
+*.pdf
+
+# Temporary
+*.blg
+*.bbl
+*.lof
+*.lot
+*.bbl-SAVE-ERROR
+
+# Editor
+.vscode/*
+!.vscode/settings.json.bcf
+
+*.bcf
+*.run.xml
+work/*/
+
+# Ignore raw/generated files
+*.har
+
+
+# Ignore all work output
+work/*
+
+
+# But keep shell scripts
+!work/*.sh
+
+
+.noroff-env

report/.vscode/settings.json

@@ -0,0 +1,78 @@
+{
+  "latex-workshop.latex.autoBuild.run": "onFileChange",
+  "latex-workshop.view.pdf.viewer": "tab",
+  "latex-workshop.synctex.afterBuild.enabled": true,
+  "latex-workshop.message.error.show": false,
+  "latex-workshop.message.warning.show": false,
+
+  "latex-workshop.latex.outDir": ".",
+
+  "latex-workshop.latex.tools": [
+    {
+      "name": "latexmk",
+      "command": "latexmk",
+      "args": [
+        "-pdf",
+        "-interaction=nonstopmode",
+        "-synctex=1",
+        "-f",
+        "%DOC%"
+      ]
+    }
+  ],
+
+  "latex-workshop.latex.recipes": [
+    {
+      "name": "latexmk",
+      "tools": ["latexmk"]
+    }
+  ],
+
+  "latex-workshop.latex.clean.fileTypes": [
+    "*.aux",
+    "*.bbl",
+    "*.bcf",
+    "*.blg",
+    "*.fdb_latexmk",
+    "*.fls",
+    "*.lof",
+    "*.log",
+    "*.lot",
+    "*.out",
+    "*.run.xml",
+    "*.synctex.gz",
+    "*.toc"
+  ],
+
+  "files.watcherExclude": {
+    "**/*.aux": true,
+    "**/*.bbl": true,
+    "**/*.bcf": true,
+    "**/*.blg": true,
+    "**/*.fdb_latexmk": true,
+    "**/*.fls": true,
+    "**/*.lof": true,
+    "**/*.log": true,
+    "**/*.lot": true,
+    "**/*.out": true,
+    "**/*.run.xml": true,
+    "**/*.synctex.gz": true,
+    "**/*.toc": true
+  },
+
+  "search.exclude": {
+    "**/*.aux": true,
+    "**/*.bbl": true,
+    "**/*.bcf": true,
+    "**/*.blg": true,
+    "**/*.fdb_latexmk": true,
+    "**/*.fls": true,
+    "**/*.lof": true,
+    "**/*.log": true,
+    "**/*.lot": true,
+    "**/*.out": true,
+    "**/*.run.xml": true,
+    "**/*.synctex.gz": true,
+    "**/*.toc": true
+  }
+}

report/main.tex

@@ -0,0 +1,80 @@
+% !TeX root = main.tex
+\documentclass[12pt,a4paper]{article}
+
+\usepackage[utf8]{inputenc}
+\usepackage[T1]{fontenc}
+\usepackage[english]{babel}
+\usepackage{lmodern}
+
+\usepackage[a4paper,margin=2.5cm]{geometry}
+\usepackage{setspace}
+\onehalfspacing
+
+\usepackage{graphicx}
+\usepackage{booktabs}
+\usepackage{amsmath}
+\usepackage{hyperref}
+\usepackage{xcolor}
+\usepackage{listings}
+\usepackage{lipsum}
+
+\usepackage{cleveref}
+
+\usepackage[backend=biber,style=authoryear]{biblatex}
+\addbibresource{references.bib}
+
+\hypersetup{
+    colorlinks=true,
+    linkcolor=black,
+    urlcolor=blue,
+    citecolor=blue
+}
+
+\lstset{
+    basicstyle=\ttfamily\small,
+    breaklines=true,
+    frame=single,  
+    numbers=left,
+    numberstyle=\tiny,
+    keywordstyle=\color{blue},
+    commentstyle=\color{gray},
+    stringstyle=\color{teal}
+}
+
+\title{Analysis of Cookie Activity in Web Search Traffic}
+\author{Tord-Vincent Heggland}
+\date{\today}
+
+\begin{document}
+\pagenumbering{roman}
+\maketitle
+\begin{abstract}
+\label{abs:abstr}
+\centering
+\lipsum[1]
+\end{abstract}
+\clearpage
+\tableofcontents
+\clearpage
+\pagenumbering{arabic}
+
+\setcounter{page}{1}
+
+\input{sections/introduction.tex}
+\input{sections/method.tex}
+
+\input{sections/results.tex}
+%\begin{figure}[h]
+ %   \centering
+  %  \includegraphics[width=\textwidth]{figures/Figure1.png}
+   % \caption{Total video game sales by genre in North America (millions of units).}
+    %\label{fig:Figure1}
+%\end{figure}
+\input{sections/discussion.tex}
+\input{sections/conclusion.tex}
+
+\clearpage
+\cite{noauthor_video_nodate}
+\clearpage
+\printbibliography[title={References}]
+\end{document}

report/references.bib

@@ -0,0 +1,9 @@
+
+@online{noauthor_video_nodate,
+	title = {Video Game Sales Dataset Updated -Extra Feat},
+	url = {https://www.kaggle.com/datasets/ibriiee/video-games-sales-dataset-2022-updated-extra-feat},
+	abstract = {Uncover the Gaming Industry Trends with the Most Comprehensive Sales Data},
+	urldate = {2026-04-21},
+	langid = {english},
+	file = {Snapshot:/home/tvh/snap/zotero-snap/common/Zotero/storage/C5LJ5QMG/video-games-sales-dataset-2022-updated-extra-feat.html:text/html},
+}

report/sections/conclusion.tex

@@ -0,0 +1,8 @@
+\section{Conclusion\label{sec:concl}}
+
+
+% \subsection{Summary}
+
+% \subsection{Hypothesis evaluation}
+
+% \subsection{Future work}

report/sections/discussion.tex

@@ -0,0 +1,10 @@
+\section{Discussion\label{sec:discu}}
+
+
+% \subsection{Interpretation of findings}
+
+% \subsection{Privacy implications}
+
+% \subsection{Reliability and limitations}
+
+% \subsection{Ethical considerations}

report/sections/introduction.tex

@@ -0,0 +1,8 @@
+\section{Introduction\label{sec:intro}}
+\subsection{Background\label{sec:intro:background}}
+
+\subsection{Problem statement\label{sec:intro:statement}}
+
+\subsection{Research objectives\label{sec:intro:research}}
+
+\subsection{Hypotheses\label{sec:intro:hypotheses}}

report/sections/method.tex

@@ -0,0 +1,71 @@
+\section{Method\label{sec:metho}}
+
+
+\subsection{Research design\label{sec:metho:research_design}}
+% Stikkord:
+% observational study
+% browser-based network measurements
+% same searches across search engines
+% comparison between search engines, browsers, and network modes
+
+\subsection{Test environment\label{sec:metho:test_environment}}
+% Stikkord:
+% operating system / controlled environment
+% Playwright
+% Chromium and Firefox
+% normal network and Tor proxy
+% clean browser context
+% cookies allowed
+% same wait condition and timeout
+
+\subsection{Search engines and search queries\label{sec:metho:search_engines}}
+% Stikkord:
+% Google
+% Bing
+% DuckDuckGo
+% Brave Search
+% list of search queries
+% same query used across all engines
+
+\subsection{Variables and measurements\label{sec:metho:Variables_measurements}}
+% Stikkord:
+% requests_total
+% unique_domains
+% third_party_requests
+% request_cookies_total
+% response_cookies_total
+% query_params_total
+% post_requests_total
+% tracking_hint_requests
+% transferred_kb_approx
+% page_load_ms
+% HTTP status groups
+
+\subsection{Data collection\label{sec:metho:data_collection}}
+% Stikkord:
+% HAR files
+% one HAR file per search engine/query/browser/network mode
+% capture_search_har script
+% headed browser
+% wait-until load
+% timeout 60000 ms
+% Tor via SOCKS proxy where applicable
+
+\subsection{Data processing\label{sec:metho:data_processing}}
+% Stikkord:
+% HAR files converted to CSV
+% har_entries.csv: one row per HAR entry/request
+% har_summary.csv: one row per HAR file
+% Power Query used to combine summary files
+% folder names used to identify browser/network mode
+
+
+
+\subsection{Limitations of the method\label{sec:metho:limitations}}
+% Stikkord:
+% HAR shows observable browser-side traffic only
+% cannot prove server-side storage
+% Playwright may differ from manual browsing
+% Tor may change website behaviour
+% cookie consent state affects results
+% tracking_hint is keyword-based, not proof of tracking

report/sections/results.tex

@@ -0,0 +1,18 @@
+\section{Results\label{sec:resul}}
+
+
+% \subsection{Dataset overview}
+
+% \subsection{Exploratory Data Analysis}
+
+% \subsection{Cookie activity by search engine}
+
+% \subsection{Third-party request analysis}
+
+% \subsection{Tracking-related domains}
+
+% \subsection{Temporal patterns}
+
+% \subsection{Outliers and anomalies}
+
+% \subsection{Summary of findings}

results/har_summary_tor_test.csv

@@ -0,0 +1,9 @@
+har_filename,search_engine,query_text,requests_total,unique_domains,third_party_requests,request_cookies_total,response_cookies_total,query_params_total,post_requests_total,tracking_hint_requests,transferred_kb_approx,page_load_ms,status_2xx,status_3xx,status_4xx,status_5xx
+20260507_143612_bing_migraine_symptoms.har,Unknown,migraine symptoms,465,6,0,4922,57,282,11,6,3218.75,1671.0,458,4,1,0
+20260507_143612_brave_migraine_symptoms.har,Unknown,migraine symptoms,172,3,0,0,0,7,9,3,1965.89,5181.12,171,0,0,0
+20260507_143612_duckduckgo_migraine_symptoms.har,DuckDuckGo,migraine symptoms,73,4,0,0,0,930,31,32,2122.14,1543.0,73,0,0,0
+20260507_143612_google_migraine_symptoms.har,Google,migraine symptoms,13,3,6,19,5,21,0,1,4039.12,1278.0,11,1,1,0
+20260507_144223_bing_migraine_symptoms.har,Unknown,migraine symptoms,483,6,0,4816,48,274,15,4,3298.3,6589.0,470,3,2,0
+20260507_144223_brave_migraine_symptoms.har,Unknown,migraine symptoms,197,3,0,0,0,7,9,3,1877.96,5905.22,194,0,3,0
+20260507_144223_duckduckgo_migraine_symptoms.har,DuckDuckGo,migraine symptoms,72,4,0,0,0,984,30,31,2109.12,3062.0,72,0,0,0
+20260507_144223_google_migraine_symptoms.har,Google,migraine symptoms,7,2,3,9,3,13,0,0,1317.34,2353.61,4,1,1,0

results/summary_osloweather.csv

@@ -0,0 +1,9 @@
+har_filename,search_engine,query_text,requests_total,unique_domains,third_party_requests,request_cookies_total,response_cookies_total,query_params_total,post_requests_total,tracking_hint_requests,transferred_kb_approx,page_load_ms,status_2xx,status_3xx,status_4xx,status_5xx
+20260507_164651_bing_weather_oslo.har,Unknown,weather oslo,458,6,0,4224,40,273,13,4,2892.66,5031.0,446,3,2,0
+20260507_164651_brave_weather_oslo.har,Unknown,weather oslo,96,2,0,0,0,1,0,0,806.42,1731.0,95,0,1,0
+20260507_164651_duckduckgo_weather_oslo.har,DuckDuckGo,weather oslo,76,4,0,0,0,981,29,30,2411.64,2986.0,76,0,0,0
+20260507_164651_google_weather_oslo.har,Google,weather oslo,12,3,6,15,3,19,0,2,3990.94,9253.0,10,1,1,0
+20260507_164805_bing_weather_oslo.har,Unknown,weather oslo,614,5,0,6856,71,350,8,8,3299.72,1639.0,608,4,0,0
+20260507_164805_brave_weather_oslo.har,Unknown,weather oslo,154,3,0,0,0,1,9,3,1214.27,1094.0,154,0,0,0
+20260507_164805_duckduckgo_weather_oslo.har,DuckDuckGo,weather oslo,82,4,0,0,0,925,35,30,2449.43,1289.0,82,0,0,0
+20260507_164805_google_weather_oslo.har,Google,weather oslo,2,1,0,4,5,3,0,0,49.69,496.65,1,1,0,0

work/many_search.sh

@@ -0,0 +1,55 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+QUERIES=(
+	"weather oslo"
+	"migraine symptoms"
+	"vitamin d deficiency"
+	"running shoes"
+	"coffee grinder"
+	"best laptop for students"
+	"electric car charging"
+	"cheap flights to london"
+	"home insurance"
+	"python list tutorial"
+	"banana bread recipe"
+	"news norway"
+)
+
+for query in "${QUERIES[@]}"; do
+	echo "Running query: $query"
+
+	capture_search_har \
+		--query "$query" \
+		--browser chromium \
+		--wait-until load \
+		--headed \
+		--output-dir normal_chromium \
+		--timeout-ms 60000
+
+	capture_search_har \
+		--query "$query" \
+		--browser chromium \
+		--wait-until load \
+		--headed \
+		--output-dir tor_chromium \
+		--timeout-ms 60000 \
+		--proxy socks5://127.0.0.1:9050
+
+	capture_search_har \
+		--query "$query" \
+		--browser firefox \
+		--wait-until load \
+		--headed \
+		--output-dir tor_firefox \
+		--timeout-ms 60000 \
+		--proxy socks5://127.0.0.1:9050
+
+	capture_search_har \
+		--query "$query" \
+		--browser firefox \
+		--wait-until load \
+		--headed \
+		--output-dir normal_firefox \
+		--timeout-ms 60000
+done