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

Cover....1

Title Page....2

Copyright....3

Table of Contents....5

About the Author....13

About the Contributing Editor....14

About the Technical Reviewer....15

Acknowledgments....16

Why I Wrote This Book....17

Foreword....21

Chapter 1: Introduction....23

The Inexact (Data) Science of SEO....23

Noisy Feedback Loop....23

Diminishing Value of the Channel....24

Making Ads Look More like Organic Listings....24

Lack of Sample Data....24

Things That Can’t Be Measured....25

High Costs....26

Why You Should Turn to Data Science for SEO....26

SEO Is Data Rich....26

SEO Is Automatable....27

Data Science Is Cheap....27

Summary....27

Chapter 2: Keyword Research....28

Data Sources....28

Google Search Console (GSC)....29

Import, Clean, and Arrange the Data....30

Segment by Query Type....32

Round the Position Data into Whole Numbers....33

Calculate the Segment Average and Variation....34

Compare Impression Levels to the Average....36

Explore the Data....36

Export Your High Value Keyword List....39

Activation....39

Google Trends....40

Single Keyword....40

Multiple Keywords....41

Visualizing Google Trends....44

Forecast Future Demand....45

Exploring Your Data....46

Decomposing the Trend....48

Fitting Your SARIMA Model....51

Test the Model....54

Forecast the Future....56

Clustering by Search Intent....59

Starting Point....61

Filter Data for Page 1....62

Convert Ranking URLs to a String....62

Compare SERP Distance....64

SERP Competitor Titles....78

Filter and Clean the Data for Sections Covering Only What You Sell....79

Extract Keywords from the Title Tags....81

Filter Using SERPs Data....82

Summary....83

Chapter 3: Technical....84

Where Data Science Fits In....85

Modeling Page Authority....85

Filtering in Web Pages....87

Examine the Distribution of Authority Before Optimization....88

Calculating the New Distribution....91

Internal Link Optimization....98

By Site Level....102

Site-Level URLs That Are Underlinked....111

By Page Authority....118

Page Authority URLs That Are Underlinked....125

Content Type....128

Combining Site Level and Page Authority....130

Anchor Texts....132

Anchor Issues by Site Level....135

Anchor Text Relevance....138

Location....142

Anchor Text Words....143

Core Web Vitals (CWV)....146

Landscape....146

Onsite CWV....162

Summary....171

Chapter 4: Content and UX....172

Content That Best Satisfies the User Query....173

Data Sources....173

Keyword Mapping....173

String Matching....174

String Distance to Map Keyword Evaluation....180

Content Gap Analysis....181

Getting the Data....182

Creating the Combinations....189

Finding the Content Intersection....190

Establishing Gap....192

Content Creation: Planning Landing Page Content....195

Getting SERP Data....197

Crawling the Content....200

Extracting the Headings....203

Cleaning and Selecting Headings....208

Cluster Headings....212

Reflections....218

Summary....219

Chapter 5: Authority....220

Some SEO History....220

A Little More History....221

Authority, Links, and Other....221

Examining Your Own Links....222

Importing and Cleaning the Target Link Data....223

Targeting Domain Authority....227

Domain Authority Over Time....229

Targeting Link Volumes....233

Analyzing Your Competitor’s Links....237

Data Importing and Cleaning....237

Anatomy of a Good Link....242

Link Quality....246

Link Volumes....252

Link Velocity....255

Link Capital....256

Finding Power Networks....259

Taking It Further....264

Summary....265

Chapter 6: Competitors....266

And Algorithm Recovery Too!....266

Defining the Problem....266

Outcome Metric....267

Why Ranking?....267

Features....267

Data Strategy....267

Data Sources....269

Explore, Clean, and Transform....270

Import Data – Both SERPs and Features....271

Start with the Keywords....273

Focus on the Competitors....275

Join the Data....289

Derive New Features....291

Single-Level Factors (SLFs)....295

Rescale Your Data....298

Near Zero Variance (NZVs)....300

Median Impute....305

One Hot Encoding (OHE)....307

Eliminate NAs....309

Modeling the SERPs....310

Evaluate the SERPs ML Model....313

The Most Predictive Drivers of Rank....314

How Much Rank a Ranking Factor Is Worth....317

The Winning Benchmark for a Ranking Factor....320

Tips to Make Your Model More Robust....320

Activation....320

Automating This Analysis....320

Summary....321

Chapter 7: Experiments....322

How Experiments Fit into the SEO Process....322

Generating Hypotheses....323

Competitor Analysis....323

Website Articles and Social Media....323

You/Your Team’s Ideas....324

Recent Website Updates....324

Conference Events and Industry Peers....324

Past Experiment Failures....325

Experiment Design....325

Zero Inflation....329

Split A/A Analysis....332

Determining the Sample Size....341

Test and Control Assignment....343

Running Your Experiment....348

Ending A/B Tests Prematurely....348

Not Basing Tests on a Hypothesis....349

Simultaneous Changes to Both Test and Control....349

Non-QA of Test Implementation and Experiment Evaluation....350

Split A/B Exploratory Analysis....353

Inconclusive Experiment Outcomes....361

Summary....362

Chapter 8: Dashboards....363

Data Sources....363

Don’t Plug Directly into Google Data Studio....364

Using Data Warehouses....364

Extract, Transform, and Load (ETL)....364

Extracting Data....365

Google Analytics....365

DataForSEO SERPs API....371

Google Search Console (GSC)....376

Google PageSpeed API....382

Transforming Data....385

Loading Data....390

Visualization....393

Automation....394

Summary....394

Chapter 9: Site Migration Planning....396

Verifying Traffic and Ranking Changes....396

Identifying the Parent and Child Nodes....398

Separating Migration Documents....404

Finding the Closest Matching Category URL....408

Mapping Current URLs to the New Category URLs....412

Mapping the Remaining URLs to the Migration URL....414

Importing the URLs....418

Migration Forensics....431

Traffic Trends....432

Segmenting URLs....442

Time Trends and Change Point Analysis....456

Segmented Time Trends....459

Analysis Impact....461

Diagnostics....473

Road Map....482

Summary....486

Chapter 10: Google Updates....487

Algo Updates....488

Dedupe....495

Domains....497

Reach Stratified....503

Rankings....511

WAVG Search Volume....513

Visibility....514

Result Types....522

Cannibalization....530

Keywords....538

Token Length....538

Token Length Deep Dive....543

Target Level....551

Keywords....551

Pages....555

Segments....562

Top Competitors....562

Visibility....568

Snippets....575

Summary....579

Chapter 11: The Future of SEO....580

Aggregation....580

Distributions....581

String Matching....581

Clustering....582

Machine Learning (ML) Modeling....582

Set Theory....583

What Computers Can and Can’t Do....583

For the SEO Experts....583

Summary....584

Index....585

Solve SEO problems using data science. This hands-on book is packed with Python code and data science techniques to help you generate data-driven recommendations and automate the SEO workload.

This book is a practical, modern introduction to data science in the SEO context using Python. With social media, mobile, changing search engine algorithms, and ever-increasing expectations of users for super web experiences, too much data is generated for an SEO professional to make sense of in spreadsheets. For any modern-day SEO professional to succeed, it is relevant to find an alternate solution, and data science equips SEOs to grasp the issue at hand and solve it. From machine learning to Natural Language Processing (NLP) techniques, Data-Driven SEO with Python provides tried and tested techniques with full explanations for solving both everyday and complex SEO problems.

This book is ideal for SEO professionals who want to take their industry skills to the next level and enhance their business value, whether they are a new starter or highly experienced in SEO, Python programming, or both.

What You'll Learn

• See how data science works in the SEO context
• Think about SEO challenges in a data driven way
• Apply the range of data science techniques to solve SEO issues
• Understand site migration and relaunches are

Who This Book Is For

SEO practitioners, either at the department head level or all the way to the new career starter looking to improve their skills. Readers should have basic knowledge of Python to perform tasks like querying an API with some data exploration and visualization.