Scrape shows from http://www.thechapelsf.com/music/

chapelsf.py

"""
Scrape shows from http://www.thechapelsf.com/music/

Usage:
    $ python chapelsf.py

Sample output:

    [   {   'artist': 'Emily King',
        'show_date': 'Wed 8/03 Doors: 8:00 pm / Show: 9:00 pm',
        'sold_out': True,
        'ticket_price': '\n$20 adv / $22 door\t  ',
        'ticket_url': 'http://www.thechapelsf.com/music//event/1151171-emily-king-san-francisco/'},
    {   'artist': "Sinner's Happy Hour with Ted Savarese and the TedTones",
        'show_date': 'Thu 8/04 5:00 pm / ',
        'sold_out': False,
        'ticket_price': None,
        'ticket_url': 'http://www.thechapelsf.com/music//event/1261079-sinners-happy-hour-ted-san-francisco/'},
    ...]
"""
import sys

from bs4 import BeautifulSoup
import requests


URL = 'http://www.thechapelsf.com/music/'


def get_markup():
    resp = requests.get(URL)
    if not resp.ok:
        sys.exit('HTTP status received {}'.format(resp.status_code))

    return resp.text


def parse_shows(markup):
    soup = BeautifulSoup(markup, 'html.parser')
    music_listings = soup.find_all(attrs={'class': 'list-view-item'})

    shows = []
    for music_listing in music_listings:
        artist = music_listing.find(attrs={'class': 'headliners'}).find('a').text
        show_date = music_listing.find(attrs={'class': 'dates'}).text
        door_time = music_listing.find(attrs={'class': 'times'}).find('span').text
        show_time = music_listing.find(attrs={'class': 'times'}).find_all('span')[1].text

        ticket_price_tag = music_listing.find(attrs={'class': 'ticket-price'}).find(attrs={'class': 'price-range'})
        if ticket_price_tag:
            ticket_price = ticket_price_tag.text
        else:
            ticket_price = None

        sold_out_tag = music_listing.find(attrs={'class': 'ticket-price'}).find(attrs={'class': 'sold-out'})
        if sold_out_tag:
            sold_out = True
        else:
            sold_out = False
        ticket_url = music_listing.find(attrs={'class': 'headliners'}).find('a')['href']

        shows.append({
            'artist': artist,
            'show_date': '{} {} / {}'.format(show_date, door_time, show_time),
            'ticket_price': ticket_price,
            'sold_out': sold_out,
            'ticket_url': '{}{}'.format(URL, ticket_url)
        })

    return shows


def main():
    markup = get_markup()
    return parse_shows(markup)


if __name__ == '__main__':
    import pprint
    pp = pprint.PrettyPrinter(indent=4)
    pp.pprint(main())

tests.py

"""
Copy paste source from http://www.thechapelsf.com/music/ and save to markup.html

Usage:
    $ py.test tests.py
"""
import pytest

from chapelsf import parse_shows


@pytest.fixture(scope='module')
def markup():
    with open('markup.html') as f:
        data = f.read()

    return data


def test_parse_shows(markup):
    result = parse_shows(markup)

    first = {'show_date': 'Wed 8/03 Doors: 8:00 pm / Show: 9:00 pm', 'ticket_url': 'http://www.thechapelsf.com/music//event/1151171-emily-king-san-francisco/', 'artist': 'Emily King', 'sold_out': True, 'ticket_price': '\n$20 adv / $22 door\t  '}
    assert first == result[0]

    second = {'show_date': 'Thu 8/04 5:00 pm / ', 'ticket_url': 'http://www.thechapelsf.com/music//event/1261079-sinners-happy-hour-ted-san-francisco/', 'artist': "Sinner's Happy Hour with Ted Savarese and the TedTones", 'sold_out': False, 'ticket_price': None}
    assert second == result[1]