aniketpanjwani/local_media_tools/newsletter-events-update-event

import re
url_pattern = r'https?://[^\s<>"\']+'
urls = re.findall(url_pattern, user_input)
if not urls:
    print("ERROR: No valid URLs found in input")
    # STOP HERE

from scripts.url_utils import normalize_url
from schemas.sqlite_storage import SqliteStorage
from pathlib import Path
db_path = Path.home() / ".config" / "local-media-tools" / "data" / "events.db"
storage = SqliteStorage(db_path)
# Normalize URLs
url_map = {normalize_url(url): url for url in urls}
# Check which URLs exist in scraped_pages
for normalized_url, original_url in url_map.items():
    # Find the source_name for this URL (query scraped_pages)
    page_record = None
    with storage._connection() as conn:
        row = conn.execute(
            "SELECT source_name, url, scraped_at FROM scraped_pages WHERE url = ?",
            (normalized_url,),
        ).fetchone()
        if row:
            page_record = dict(row)
    if page_record:
        print(f"ℹ Found: {original_url}")
        print(f"  Source: {page_record['source_name']}")
        print(f"  Last scraped: {page_record['scraped_at']}")
    else:
        print(f"⚠ Not found in database: {original_url}")
        print(f"  Will be scraped as new URL")

from scripts.scrape_firecrawl import FirecrawlClient, FirecrawlError
client = FirecrawlClient()
scraped_pages = []
for normalized_url, original_url in url_map.items():
    try:
        page = client.scrape_url(original_url)
        scraped_pages.append({
            "normalized_url": normalized_url,
            "original_url": original_url,
            "markdown": page.get("markdown", ""),
            "title": page.get("title", ""),
        })
        print(f"✓ Scraped: {original_url}")
    except FirecrawlError as e:
        print(f"✗ Failed to scrape {original_url}: {e}")

from schemas.event import Event, Venue, EventSource
event = Event(
    title=extracted_title,
    venue=Venue(name=venue_name, address=venue_address),
    event_date=parsed_date,
    start_time=parsed_time,
    source=EventSource.WEB_AGGREGATOR,
    source_url=page["original_url"],
    description=description,
    price=price,
    ticket_url=ticket_url,
    confidence=0.9,  # Higher confidence for manual refresh
    needs_review=False,  # User explicitly requested this update
)

from schemas.event import EventCollection
for page in scraped_pages:
    events_from_page = events_by_url.get(page["original_url"], [])
    # 1. Save/update events
    if events_from_page:
        collection = EventCollection(events=events_from_page)
        result = storage.save(collection)
        print(f"  → {len(events_from_page)} events: {result.saved} new, {result.updated} updated")
    else:
        print(f"  → No events extracted from page")
    # 2. Update scraped_pages record
    # Determine source_name (from existing record or ask user)
    if page_record:
        source_name = page_record["source_name"]
    else:
        # For new URLs, try to infer source from config or use domain
        from urllib.parse import urlparse
        source_name = urlparse(page["original_url"]).netloc
    storage.save_scraped_page(
        source_name=source_name,
        url=page["normalized_url"],
        events_count=len(events_from_page),
    )
print(f"\n✓ Update complete")