""" Automated SEO Workflow End-to-end keyword research and competitor analysis """ import json import pandas as pd from datetime import datetime import os from keyword_researcher import KeywordResearcher from competitor_analyzer import CompetitorAnalyzer class AutomatedSEOWorkflow: def __init__(self, config_file='config.json'): """ Initialize automated workflow Args: config_file: Path to configuration JSON file """ with open(config_file, 'r') as f: self.config = json.load(f) self.keyword_researcher = KeywordResearcher(config_file) self.competitor_analyzer = CompetitorAnalyzer(config_file) self.results = {} def run_full_analysis(self, property_url=None, days=90, top_n_keywords=20): """ Run complete SEO analysis workflow Args: property_url: GSC property URL (if None, will prompt) days: Days of GSC data to analyze top_n_keywords: Number of top keywords to analyze Returns: Dictionary with all results """ print("\n" + "="*60) print("AUTOMATED SEO WORKFLOW") print("="*60) # Step 1: Connect to GSC and fetch data print("\n[1/5] Connecting to Google Search Console...") self.keyword_researcher.connect() if not property_url: properties = self.keyword_researcher.auth.list_properties() if properties: print("\nAvailable properties:") for i, prop in enumerate(properties, 1): print(f" {i}. {prop}") choice = int(input("\nSelect property number: ")) - 1 property_url = properties[choice] else: print("✗ No properties found!") return None print(f"\n[2/5] Fetching GSC data for {property_url}...") gsc_data = self.keyword_researcher.fetch_gsc_data(property_url, days) if not gsc_data: print("✗ No GSC data retrieved!") return None # Step 2: Analyze keyword opportunities print("\n[3/5] Analyzing keyword opportunities...") opportunities = self.keyword_researcher.analyze_opportunities( gsc_data, min_impressions=self.config['google_search_console'].get('min_impressions', 10) ) print(f" Found {len(opportunities)} keyword opportunities") # Step 3: Cluster keywords print("\n[4/5] Clustering related keywords...") clusters = self.keyword_researcher.cluster_keywords(opportunities) print(f" Created {len(clusters)} keyword clusters") # Step 4: Analyze competitors for top keywords print(f"\n[5/5] Analyzing competitors for top {top_n_keywords} keywords...") top_keywords = opportunities.head(top_n_keywords) competitor_analyses = {} for idx, row in top_keywords.iterrows(): keyword = row['query'] print(f"\n Analyzing: '{keyword}'") # Get competitor URLs (from config) competitor_urls = self.config.get('competitors', []) # Scrape and analyze each competitor analyses = [] for url in competitor_urls[:self.config['analysis_settings'].get('max_competitors_per_keyword', 10)]: content = self.competitor_analyzer.scrape_page_content(url) if content: analysis = self.competitor_analyzer.analyze_content_structure(content, keyword) if analysis: analyses.append(analysis) # Compare competitors if analyses: comparison = self.competitor_analyzer.compare_competitors(analyses) competitor_analyses[keyword] = comparison print(f" ✓ Analyzed {len(analyses)} competitors") print(f" Avg word count: {comparison['avg_word_count']:.0f}") print(f" Avg keyword density: {comparison['avg_keyword_density']:.2f}%") # Step 5: Generate comprehensive report print("\n[6/6] Generating reports...") self.results = { 'property_url': property_url, 'analysis_date': datetime.now().isoformat(), 'total_keywords': len(opportunities), 'total_clusters': len(clusters), 'opportunities': opportunities, 'clusters': clusters, 'competitor_analyses': competitor_analyses } # Export reports reports_dir = self.config['output']['reports_dir'] os.makedirs(reports_dir, exist_ok=True) files = self.keyword_researcher.export_keyword_report( opportunities, clusters, reports_dir ) # Export competitor analysis timestamp = datetime.now().strftime('%Y%m%d_%H%M%S') competitor_json = f"{reports_dir}/competitor_analysis_{timestamp}.json" # Convert DataFrames to dicts for JSON serialization export_data = { 'property_url': property_url, 'analysis_date': datetime.now().isoformat(), 'competitor_analyses': competitor_analyses } with open(competitor_json, 'w') as f: json.dump(export_data, f, indent=2, default=str) print(f" ✓ Saved competitor analysis: {competitor_json}") # Generate master HTML report (both versions) master_html_ts = f"{reports_dir}/master_report_{timestamp}.html" master_html_static = f"{reports_dir}/index.html" self._generate_master_report(master_html_ts) self._generate_master_report(master_html_static) print(f" ✓ Saved master report: {master_html_ts}") print(f" ✓ Saved master report: {master_html_static}") print("\n" + "="*60) print("✓ ANALYSIS COMPLETE!") print("="*60) print(f"\nReports saved to: {reports_dir}/") return self.results def _generate_master_report(self, output_path): """Generate comprehensive HTML report""" opportunities = self.results['opportunities'] clusters = self.results['clusters'] competitor_analyses = self.results['competitor_analyses'] html = f""" SEO Master Report - Conservatory Transformations

🎯 SEO Master Report - Conservatory Transformations

Property: {self.results['property_url']}

Generated: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}

{len(opportunities)}
Total Keywords
{len(clusters)}
Keyword Clusters
{opportunities['clicks'].sum():,}
Total Clicks
{opportunities['impressions'].sum():,}
Total Impressions

📊 Top 20 Keyword Opportunities

These keywords have the highest potential for improvement based on impressions, CTR, and current position.

{opportunities.head(20).to_html(index=False, classes='data-table')}

🎯 Keyword Clusters

Related keywords grouped by topic for content planning.

""" for i, (cluster_name, data) in enumerate(list(clusters.items())[:10], 1): html += f"""

{i}. {cluster_name.title()}

Total Opportunity Score: {data['total_opportunity']:.2f} | Keywords: {data['keyword_count']}

" html += "

🔍 Competitor Analysis

" for keyword, analysis in list(competitor_analyses.items())[:10]: html += f"""

Keyword: "{keyword}"

Competitors Analyzed: {analysis['total_analyzed']}

📝 Content Recommendations:
  • Target Word Count: {analysis['avg_word_count']:.0f} words (Range: {analysis['min_word_count']}-{analysis['max_word_count']})
  • Target Keyword Density: {analysis['avg_keyword_density']:.2f}%
  • Headings: Use ~{analysis['avg_headings']:.0f} headings (H1-H6)
  • Internal Links: Include ~{analysis['avg_internal_links']:.0f} internal links
  • Keyword in Title: {analysis['keyword_in_title_pct']:.0f}% of competitors do this
  • Keyword in H1: {analysis['keyword_in_h1_pct']:.0f}% of competitors do this
  • Schema Markup: {analysis['schema_usage_pct']:.0f}% of competitors use it

Top Competitor Examples:

""" for comp in analysis['competitors'][:5]: title_icon = "✓" if comp['title_has_keyword'] else "✗" h1_icon = "✓" if comp['h1_has_keyword'] else "✗" html += f""" """ html += "
URL Words KW Density Headings In Title In H1
{comp['url'][:50]}... {comp['word_count']} {comp['keyword_density']:.2f}% {comp['total_headings']} {title_icon} {h1_icon}
" html += """
""" with open(output_path, 'w', encoding='utf-8') as f: f.write(html) if __name__ == "__main__": print("\n" + "="*60) print("CONSERVATORY TRANSFORMATIONS - SEO AUTOMATION") print("="*60) workflow = AutomatedSEOWorkflow() # Run full analysis results = workflow.run_full_analysis( property_url=None, # Will prompt for selection days=90, top_n_keywords=20 ) if results: print("\n✓ Analysis complete! Check the reports directory for results.")