SERP N-gram Extractor
Use cases
Fetches SERP results via ValueSERP API and extracts page content using Trafilatura (unlimited timeout).
Generates bigrams via custom find_ngrams() using zip iteration.
Uses NLTK English stopwords filtering and Collections.Counter for frequency analysis.
Normalises text with special character removal and lowercase conversion.
Platform
Python script (requires Python 3.x)
Input
ValueSERP API key
Target search keyword
Geographic location
Device type (desktop/mobile)
Output
Three CSVs: content bigrams with frequency counts, title keywords (frequency > 1), SERP titles with URLs.
Features
- ValueSERP API integration for SERP fetching
- Trafilatura content extraction (unlimited timeout)
- Custom bigram generation via zip(*[input_list[i:] for i in range(n)])
- NLTK English stopwords filtering
- Counter frequency analysis across combined content
- Location, device type, and results page selection (1-10)
How to use
- 1 Enter your ValueSERP API key
- 2 Input target keyword and select location
- 3 Choose device type and number of results pages (1-10)
- 4 Click Submit to fetch SERPs and extract content
- 5 Trafilatura extracts text with unlimited timeout
- 6 Review bigrams, title keywords, and extracted titles
- 7 Download three CSV files for content planning
Want me to run this for you?
I offer this as a managed service. You get the insights without touching the tool.
Related Tools
Competitor Content Gap Finder
ContentDiscover which descriptive words competitors use in titles that you are missing.
Content Block Extractor
ContentExtract content blocks and XPath patterns using Claude Haiku for template analysis.
Content Consolidation Analyser
ContentFind cannibalising pages by clustering URLs that share SERP overlap.
Let's work together
Monthly retainers or one-off projects. No lengthy reports that sit in a drawer.
Let's Talk