search_transcripts.py

import json
import re

TRANSCRIPT_FILE = "all_transcripts.json"

def load_transcripts(file_path):
    try:
        with open(file_path, "r", encoding="utf-8") as f:
            return json.load(f)
    except FileNotFoundError:
        print(f"⚠️ File not found: {file_path}")
        return []
    except json.JSONDecodeError:
        print(f"⚠️ Failed to parse JSON in {file_path}")
        return []

def count_occurrences(text, search_term):
    pattern = re.compile(re.escape(search_term), re.IGNORECASE)
    return len(pattern.findall(text))

def search_transcripts(transcripts, search_term):
    results = []
    for item in transcripts:
        title = item.get("title", "Untitled")
        transcript = item.get("transcript", "")
        count = count_occurrences(transcript, search_term)
        if count > 0:
            results.append((title, count))
    return sorted(results, key=lambda x: x[1], reverse=True)

def display_results(results, search_term):
    if not results:
        print(f"🔍 No results found for '{search_term}'.")
        return
    print(f"\n📊 Search results for: '{search_term}'")
    for rank, (title, count) in enumerate(results, 1):
        print(f"{rank:>2}. {title} — {count} mention(s)")

if __name__ == "__main__":
    search_term = input("Enter the word or phrase to search for: ").strip()
    transcripts = load_transcripts(TRANSCRIPT_FILE)
    matches = search_transcripts(transcripts, search_term)
    display_results(matches, search_term)