Golden gate picnic table reservation site availability checker

parkscraper.py

#!/usr/bin/env python3
# pip install requests beautifulsoup4
import argparse
import re
import datetime
import time
import pickle
from typing import Iterable, List, Dict, Tuple

import requests
from bs4 import BeautifulSoup


BOOK_ID_PATTERN = re.compile(r'btnBook(\d\d\d\d)(\d\d)(\d\d)')


def make_argparser() -> argparse.ArgumentParser:
    argparser = argparse.ArgumentParser()
    argparser.add_argument('--cached', action='store_true', help='Use cached results instead of scraping.')
    argparser.add_argument('--urls', action='store_true', help='Print booking urls in the summary.')
    argparser.add_argument('--weekdays', help='Comma separated list of weekdays to filter to. Mon-Sun, 0-6.')
    argparser.add_argument('--months', default=1, type=int, help='Number of months in the future to scrape.')
    return argparser


class Facility(object):
    def __init__(self, id_, name: str):
        self.id = id_
        self.name = name


FACILTIES: Iterable[Facility] = (
    Facility(1063, 'Esprit Park Picnic Area - Lawn'),
    Facility(1065, 'Esprit Park Picnic Area - North East 2 Tables'),
    Facility(1068, 'Esprit Park Picnic Area - South East 1 Table'),
    Facility(1202, 'GGP - 14th Avenue East Picnic Area'),
    Facility(78,   'GGP - Bunny Meadow Picnic Area'),
    Facility(80,   'GGP - Dahlia Dell Picnic Area'),
    Facility(87,   'GGP - Doughboy Meadow Picnic Area'),
    Facility(90,   'GGP - Elk Glen Picnic Area'),
    Facility(92,   'GGP - George Washington Grove Picnic Area'),
    Facility(94,   'GGP - Hellman Hollow Picnic Area - Table 1 & 2'),
    Facility(103,  'GGP - Hellman Hollow Picnic Area - Table 3 & 4'),
    Facility(96,   'GGP - Hellman Hollow Picnic Area - Table 5 & 6'),
    Facility(97,   'GGP - Hellman Hollow Picnic Area - Table 7, 8, 9'),
    Facility(98,   'GGP - Hellman Hollow Picnic Area - Table 10, 11, 12'),
    Facility(99,   'GGP - Hellman Hollow Picnic Area - Table 13 & 14'),
    Facility(100,  'GGP - Hellman Hollow Picnic Area - Table 15 & 16'),
    Facility(101,  'GGP - Hellman Hollow Picnic Area - Table 17 & 18'),
    Facility(102,  'GGP - Hellman Hollow Picnic Area - Table 19 & 20'),
    Facility(105,  'GGP - Hoover Redwood Grove Picnic Area'),
    Facility(111,  'GGP - Lindley Meadow Picnic Area - Table 1'),
    Facility(118,  'GGP - Lindley Meadow Picnic Area - Table 2'),
    Facility(106,  'GGP - Lindley Meadow Picnic Area - Table 3 & 4'),
    Facility(119,  'GGP - Lindley Meadow Picnic Area - Table 5'),
    Facility(107,  'GGP - Lindley Meadow Picnic Area - Table 6 & 7'),
    Facility(108,  'GGP - Lindley Meadow Picnic Area - Table 8 & 9'),
    Facility(109,  'GGP - Lindley Meadow Picnic Area - Table 10 & 11'),
    Facility(110,  'GGP - Lindley Meadow Picnic Area - Table 12 & 13'),
    Facility(113,  'GGP - Lindley Meadow Picnic Area - Table 14'),
    Facility(114,  'GGP - Lindley Meadow Picnic Area - Table 15'),
    Facility(115,  'GGP - Lindley Meadow Picnic Area - Table 16'),
    Facility(116,  'GGP - Lindley Meadow Picnic Area - Table 17'),
    Facility(120,  'GGP - Marx Meadow Picnic Area - Table 1 & 2'),
    Facility(123,  'GGP - Marx Meadow Picnic Area - Table 3'),
    Facility(124,  'GGP - Marx Meadow Picnic Area - Table 4'),
    Facility(125,  'GGP - Marx Meadow Picnic Area - Table 5'),
    Facility(126,  'GGP - Marx Meadow Picnic Area - Table 6'),
    Facility(122,  'GGP - Marx Meadow Picnic Area - Table 7 & 8'),
    Facility(131,  'GGP - Old Speedway Meadow Picnic Area'),
    Facility(133,  'GGP - Peacock Meadow Picnic Area'),
    Facility(134,  'GGP - Pioneer East Meadow Picnic Area'),
    Facility(135,  'GGP - Pioneer Log Cabin Picnic Area'),
    Facility(139,  'GGP - Stow Lake Boathouse Picnic Area'),
    Facility(2317, 'GGP - Stow Lake South Side Lawn'),
    Facility(141,  'GGP –  Strawberry Hill Near Chinese Pavilion'),
    Facility(142,  'GGP – Strawberry Hill Top Picnic Area'),
    Facility(1555, 'John McLaren Park John F. Shelley Drive Picnic Area - Picnic Area A, West 7 tables + counter'),
    Facility(1562, 'John McLaren Park John F. Shelley Drive Picnic Area - Picnic Area B, East 5 tables + counter'),
    Facility(1778, 'Mountain Lake Park Picnic Area - 8th Ave 2 Tables'),
    Facility(1773, 'Mountain Lake Park Picnic Area - 9th Ave Shelter'),
    Facility(1776, 'Mountain Lake Park Picnic Area - 10th Ave Meadow'),
    Facility(1777, 'Mountain Lake Park Picnic Area - 11th Ave Meadow'),
    Facility(1779, 'Mountain Lake Park Picnic Area - 12th Ave 1 Table'),
)

FACILTIES_BY_ID = {facility.id: facility for facility in FACILTIES}

WEEKDAY_NAMES = {
    0: 'Monday',
    1: 'Tuesday',
    2: 'Wednesday',
    3: 'Thursday',
    4: 'Friday',
    5: 'Saturday',
    6: 'Sunday'
}


def scrape_month(facility_id, year, month) -> Dict[int, str]:
    startyear = year
    endyear = year
    response = requests.get(f'https://apm.activecommunities.com/sfrecpark/facility_search?IsCalendar=true'
                            f'&facility_id={facility_id}&year={year}&month={month}'
                            f'&startyear={startyear}&endyear={endyear}')
    response.raise_for_status()
    soup = BeautifulSoup(response.text, 'html.parser')
    table = soup.html.body\
        .find('div', id='an-background')\
        .find('div', id='an-wrapper')\
        .find('div', id='an-contentarea')\
        .find('form', id='IronPointForm_1')\
        .find('div', id='ctl06_ctlFacilityCalendar_divCalendar')\
        .find('div', id='ctl06_ctlFacilityCalendar_pnlCalendarAll')\
        .find('div', id='ctl06_ctlFacilityCalendar_pnlCalendarRefresh') \
        .find('div', id='ctl06_ctlFacilityCalendar_pnlCalendar') \
        .find('table', id='ctl06_ctlFacilityCalendar_tblMain')

    available_days: Dict[int, str] = {}

    all_anchors = table.find_all('a')
    for anchor in all_anchors:
        anchor_id = anchor.get('id')
        if not anchor_id:
            continue
        match = BOOK_ID_PATTERN.match(anchor_id)
        if match:
            day = match.group(3)
            try:
                day_num = int(day)
            except ValueError:
                continue
            available_days[day_num] = anchor.get('href', '')

    return available_days


def get_dates(num: int) -> List[datetime.date]:
    today = datetime.date.today()
    dates = [today]
    current_month = today.month
    current_year = today.year
    for i in range(num):
        current_month += 1
        if current_month > 12:
            current_month = 1
            current_year += 1
        dates.append(datetime.date(year=current_year, month=current_month, day=1))
    return dates


def scrape(args):
    dates = get_dates(args.months)
    available_days_by_facility: Dict[int, List[Tuple[datetime.date, str]]] = {}
    for facility in FACILTIES:
        for date in dates:
            # Be considerate, wait between requests
            time.sleep(1.0)

            print(f'GET: Month: {date.month}, Facility: "{facility.name}"')
            available_days = scrape_month(facility.id, date.year, date.month)
            print(f'\tFound {len(available_days)} spot(s).')

            availabilities_list = available_days_by_facility.setdefault(facility.id, [])
            for day, href in available_days.items():
                availabilities_list.append((datetime.date(date.year, date.month, day), href))

    with open('results.bin', 'wb') as f:
        pickle.dump(available_days_by_facility, f)

    print_summary(args, available_days_by_facility)


def display_cached(args):
    with open('results.bin', 'rb') as f:
        data = pickle.load(f)
        print_summary(args, data)


def datekey(date: datetime.date) -> int:
    return date.year * 10000 + date.month * 100 + date.day


def print_summary(args, available_days_by_facility: Dict[int, List[Tuple[datetime.date, str]]]):
    weekdays = None
    if args.weekdays:
        weekdays = {int(day) for day in args.weekdays.split(',')}

    print('--- SUMMARY ---')
    for facility in FACILTIES:
        facility_results = available_days_by_facility.get(facility.id)
        if not facility_results:
            continue

        if weekdays:
            facility_results = [t for t in facility_results if t[0].weekday() in weekdays]

        if len(facility_results) == 0:
            continue

        print(f'🌳 {facility.name}')
        for date, href in sorted(facility_results, key=lambda t: datekey(t[0])):
            entry = f'\t🧺 {WEEKDAY_NAMES[date.weekday()]}\t{date.month}/{date.day} '
            if args.urls:
                print(f'{entry}\t{href}')
            else:
                print(entry)


if __name__ == '__main__':
    args = make_argparser().parse_args()
    if args.cached:
        display_cached(args)
    else:
        scrape(args)