Fetch San Mateo County Library preschooler events

fetch_events.py

#!/usr/bin/env python3
"""
Fetch San Mateo County Library events for preschoolers from the next 3 days.

Scrapes https://smcl.bibliocommons.com/v2/events with audience filter
for "Preschoolers (0-5 years old)" and a 3-day date window starting today.
"""

import requests
from bs4 import BeautifulSoup
from datetime import datetime, timedelta

BASE_URL = "https://smcl.bibliocommons.com/v2/events"
PRESCHOOLER_AUDIENCE_ID = "564274cf4d0090f742000011"

HEADERS = {
    "User-Agent": (
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) "
        "AppleWebKit/537.36 (KHTML, like Gecko) "
        "Chrome/120.0.0.0 Safari/537.36"
    )
}


def fetch_events(days=3):
    today = datetime.now()
    end = today + timedelta(days=days - 1)

    params = {
        "audiences": PRESCHOOLER_AUDIENCE_ID,
        "startDate": today.strftime("%Y-%m-%d"),
        "endDate": end.strftime("%Y-%m-%d"),
    }

    resp = requests.get(BASE_URL, params=params, headers=HEADERS, timeout=30)
    resp.raise_for_status()

    soup = BeautifulSoup(resp.text, "html.parser")
    items = soup.find_all(class_="cp-events-search-item")

    events = []
    for item in items:
        # Title
        title_tag = item.find(class_="cp-event-title")
        title = title_tag.get_text(strip=True) if title_tag else "N/A"

        # Link
        link_tag = item.find("a", attrs={"data-key": "event-link"})
        link = link_tag["href"] if link_tag else ""

        # Date & time — use the screen-reader spans within cp-event-date-time
        date_time_span = item.find(class_="cp-event-date-time")
        if date_time_span:
            sr_spans = date_time_span.find_all(class_="cp-screen-reader-message")
            date_str = sr_spans[0].get_text(strip=True) if len(sr_spans) > 0 else ""
            time_str = sr_spans[1].get_text(strip=True) if len(sr_spans) > 1 else ""
            date_time = f"{date_str}, {time_str}" if date_str and time_str else date_str or time_str
        else:
            date_time = ""

        # Location — use the screen-reader span to get clean (non-duplicated) text
        location_tag = item.find(class_="cp-event-location-name")
        if location_tag:
            loc_sr = location_tag.find(class_="cp-screen-reader-message")
            if loc_sr:
                location = loc_sr.get_text(strip=True).replace("Event location: ", "")
            else:
                location = location_tag.get_text(strip=True)
        else:
            location = "N/A"

        # Description
        desc_tag = item.find(class_="cp-event-description")
        description = desc_tag.get_text(strip=True) if desc_tag else ""

        events.append({
            "title": title,
            "date_time": date_time,
            "location": location,
            "description": description,
            "link": link,
        })

    return events, today, end


def main():
    events, start, end = fetch_events()

    print(f"San Mateo County Library — Preschooler Events")
    print(f"{start.strftime('%A, %B %d')} through {end.strftime('%A, %B %d, %Y')}")
    print(f"{'=' * 70}")

    if not events:
        print("No events found for this date range.")
        return

    for i, evt in enumerate(events, 1):
        print(f"\n{i}. {evt['title']}")
        print(f"   When:     {evt['date_time']}")
        print(f"   Where:    {evt['location']}")
        if evt["description"]:
            # Wrap long descriptions
            desc = evt["description"]
            if len(desc) > 120:
                desc = desc[:117] + "..."
            print(f"   About:    {desc}")
        print(f"   Link:     {evt['link']}")

    print(f"\n{'=' * 70}")
    print(f"Total: {len(events)} events")


if __name__ == "__main__":
    main()