A Python utility for batch enriching a list of LinkedIn profiles from a CSV file. It leverages search aggregators (DuckDuckGo Search) to find professional metadata such as name, location, current focus, education, technical skills, and GitHub links, then synthesizes the findings into a structured JSON repository.

enrich_linkedin_profiles.py

import pandas as pd
import json
import time
from duckduckgo_search import DDGS

def enrich_profiles(csv_input, json_output):
    """
    Reads a CSV of LinkedIn URLs and enriches them with professional metadata
    found via search snippets, saving the result to a structured JSON.
    """
    try:
        df = pd.read_csv(csv_input)
        # Assumes the CSV has a column named 'LinkedIn'
        urls = df['LinkedIn'].tolist()
    except Exception as e:
        print(f"Error reading CSV {csv_input}: {e}")
        return
    
    enriched_data = []
    
    print(f"Starting enrichment for {len(urls)} profiles...")
    
    with DDGS() as ddgs:
        for url in urls:
            print(f"Processing: {url}")
            try:
                # Search for the LinkedIn profile to get snippets
                results = list(ddgs.text(url, max_results=3))
                
                # Structure the metadata
                profile_info = {
                    "linkedin_url": url,
                    "name": "Extracting...",
                    "location": "Extracting...",
                    "current_focus": "Extracting...",
                    "education": "Extracting...",
                    "technical_skills": [],
                    "github": "Searching...",
                    "raw_context": " ".join([r['body'] for r in results])
                }
                
                enriched_data.append(profile_info)
                time.sleep(1) # Rate limiting to be respectful
            except Exception as e:
                print(f"Error processing {url}: {e}")
                enriched_data.append({"linkedin_url": url, "error": str(e)})

    with open(json_output, 'w') as f:
        json.dump(enriched_data, f, indent=2)
    print(f"Enrichment complete. Data saved to {json_output}")

if __name__ == "__main__":
    # Update these filenames as needed
    enrich_profiles('input_profiles.csv', 'enriched_metadata.json')