Data-Driven SEO with Python: Solve SEO Challenges with Data Science Using Python

Table of Contents
About the Author
About the Contributing Editor
About the Technical Reviewer
Acknowledgments
Why I Wrote This Book
Foreword
Chapter 1: Introduction
	The Inexact (Data) Science of SEO
		Noisy Feedback Loop
		Diminishing Value of the Channel
		Making Ads Look More like Organic Listings
		Lack of Sample Data
		Things That Can’t Be Measured
		High Costs
	Why You Should Turn to Data Science for SEO
		SEO Is Data Rich
		SEO Is Automatable
		Data Science Is Cheap
	Summary
Chapter 2: Keyword Research
	Data Sources
	Google Search Console (GSC)
		Import, Clean, and Arrange the Data
		Segment by Query Type
		Round the Position Data into Whole Numbers
		Calculate the Segment Average and Variation
		Compare Impression Levels to the Average
		Explore the Data
		Export Your High Value Keyword List
		Activation
	Google Trends
		Single Keyword
		Multiple Keywords
		Visualizing Google Trends
	Forecast Future Demand
		Exploring Your Data
		Decomposing the Trend
		Fitting Your SARIMA Model
		Test the Model
		Forecast the Future
	Clustering by Search Intent
		Starting Point
		Filter Data for Page 1
		Convert Ranking URLs to a String
		Compare SERP Distance
	SERP Competitor Titles
		Filter and Clean the Data for Sections Covering Only What You Sell
		Extract Keywords from the Title Tags
		Filter Using SERPs Data
	Summary
Chapter 3: Technical
	Where Data Science Fits In
	Modeling Page Authority
		Filtering in Web Pages
		Examine the Distribution of Authority Before Optimization
		Calculating the New Distribution
	Internal Link Optimization
		By Site Level
			Site-Level URLs That Are Underlinked
		By Page Authority
			Page Authority URLs That Are Underlinked
		Content Type
			Combining Site Level and Page Authority
		Anchor Texts
			Anchor Issues by Site Level
		Anchor Text Relevance
			Location
			Anchor Text Words
		Core Web Vitals (CWV)
			Landscape
			Onsite CWV
		Summary
Chapter 4: Content and UX
	Content That Best Satisfies the User Query
		Data Sources
	Keyword Mapping
		String Matching
			String Distance to Map Keyword Evaluation
	Content Gap Analysis
		Getting the Data
		Creating the Combinations
		Finding the Content Intersection
		Establishing Gap
	Content Creation: Planning Landing Page Content
		Getting SERP Data
			Crawling the Content
		Extracting the Headings
		Cleaning and Selecting Headings
		Cluster Headings
		Reflections
	Summary
Chapter 5: Authority
	Some SEO History
		A Little More History
	Authority, Links, and Other
	Examining Your Own Links
		Importing and Cleaning the Target Link Data
		Targeting Domain Authority
		Domain Authority Over Time
		Targeting Link Volumes
	Analyzing Your Competitor’s Links
		Data Importing and Cleaning
		Anatomy of a Good Link
		Link Quality
		Link Volumes
		Link Velocity
		Link Capital
	Finding Power Networks
		Taking It Further
		Summary
Chapter 6: Competitors
	And Algorithm Recovery Too!
	Defining the Problem
		Outcome Metric
		Why Ranking?
		Features
	Data Strategy
	Data Sources
	Explore, Clean, and Transform
	Import Data – Both SERPs and Features
	Start with the Keywords
	Focus on the Competitors
	Join the Data
	Derive New Features
	Single-Level Factors (SLFs)
	Rescale Your Data
	Near Zero Variance (NZVs)
	Median Impute
	One Hot Encoding (OHE)
	Eliminate NAs
	Modeling the SERPs
	Evaluate the SERPs ML Model
	The Most Predictive Drivers of Rank
	How Much Rank a Ranking Factor Is Worth
	The Winning Benchmark for a Ranking Factor
	Tips to Make Your Model More Robust
	Activation
		Automating This Analysis
		Summary
Chapter 7: Experiments
	How Experiments Fit into the SEO Process
	Generating Hypotheses
		Competitor Analysis
		Website Articles and Social Media
		You/Your Team’s Ideas
		Recent Website Updates
		Conference Events and Industry Peers
		Past Experiment Failures
	Experiment Design
		Zero Inflation
		Split A/A Analysis
		Determining the Sample Size
			Test and Control Assignment
	Running Your Experiment
		Ending A/B Tests Prematurely
		Not Basing Tests on a Hypothesis
		Simultaneous Changes to Both Test and Control
	Non-QA of Test Implementation and Experiment Evaluation
		Split A/B Exploratory Analysis
		Inconclusive Experiment Outcomes
	Summary
Chapter 8: Dashboards
	Data Sources
		Don’t Plug Directly into Google Data Studio
		Using Data Warehouses
	Extract, Transform, and Load (ETL)
		Extracting Data
			Google Analytics
			DataForSEO SERPs API
			Google Search Console (GSC)
			Google PageSpeed API
		Transforming Data
		Loading Data
	Visualization
		Automation
	Summary
Chapter 9: Site Migration Planning
	Verifying Traffic and Ranking Changes
		Identifying the Parent and Child Nodes
		Separating Migration Documents
	Finding the Closest Matching Category URL
		Mapping Current URLs to the New Category URLs
		Mapping the Remaining URLs to the Migration URL
		Importing the URLs
	Migration Forensics
		Traffic Trends
		Segmenting URLs
		Time Trends and Change Point Analysis
		Segmented Time Trends
		Analysis Impact
		Diagnostics
		Road Map
	Summary
Chapter 10: Google Updates
	Algo Updates
	Dedupe
	Domains
		Reach Stratified
		Rankings
		WAVG Search Volume
		Visibility
	Result Types
	Cannibalization
	Keywords
		Token Length
		Token Length Deep Dive
	Target Level
		Keywords
		Pages
	Segments
		Top Competitors
		Visibility
		Snippets
	Summary
Chapter 11: The Future of SEO
	Aggregation
	Distributions
	String Matching
	Clustering
	Machine Learning (ML) Modeling
	Set Theory
	What Computers Can and Can’t Do
	For the SEO Experts
	Summary
Index